ourdigital/our-claude-skills
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: Add installation tool, Claude.ai export, and skill standardization (#1)

Browse Source 
## Summary

- Add portable installation tool (`install.sh`) for cross-machine setup
- Add Claude.ai export files with proper YAML frontmatter
- Add multi-agent-guide v2.0 with consolidated framework template
- Rename `00-claude-code-setting` → `00-our-settings-audit` (avoid reserved word)
- Add YAML frontmatter to 25+ SKILL.md files for Claude Desktop compatibility

## Commits Included

- `93f604a` feat: Add portable installation tool for cross-machine setup
- `9b84104` feat: Add Claude.ai export for portable skill installation
- `f7ab973` fix: Add YAML frontmatter to Claude.ai export files
- `3fed49a` feat(multi-agent-guide): Add v2.0 with consolidated framework
- `3be26ef` refactor: Rename settings-audit skill and add YAML frontmatter

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
Andrew Yim
2026-02-03 16:48:06 +07:00
committed by GitHub
parent 0bc24d00b9
commit b6a478e1df
72 changed files with 4770 additions and 803 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
CLAUDE.md
View File

@@ -14,11 +14,11 @@ This is a Claude Skills collection repository containing:
## Custom Skills Summary ## Custom Skills Summary
### Claude Code Settings (00) ### Claude Settings Audit (00)
| # | Skill | Purpose | Trigger | | # | Skill | Purpose | Trigger |
|---|-------|---------|---------| |---|-------|---------|---------|
| 00 | claude-code-setting | Settings optimization & token audit | "audit settings", "optimize Claude Code" | | 00 | our-settings-audit | Error diagnosis & token optimization (8 categories) | "settings audit", "exceed response limit", "MCP error" |
### OurDigital Core Workflows (01-09) ### OurDigital Core Workflows (01-09)
@@ -170,7 +170,7 @@ triggers: [] # Explicit trigger keywords
``` ```
our-claude-skills/ our-claude-skills/
├── custom-skills/ ├── custom-skills/
│ ├── 00-claude-code-setting/ │ ├── 00-our-settings-audit/
│ │ │ │
│ ├── 01-ourdigital-research/ │ ├── 01-ourdigital-research/
│ ├── 02-ourdigital-designer/ │ ├── 02-ourdigital-designer/

79
custom-skills/00-claude-code-setting/README.md
View File

@@ -1,79 +0,0 @@
# Claude Code Settings Optimizer
Self-audit and optimize Claude Code configuration for maximum token efficiency.
## Purpose
- Analyze token usage across MCP servers, CLAUDE.md, and extensions
- Identify optimization opportunities
- Auto-fix common issues with backup safety
- Keep working context at 70%+ of 200K limit
## Quick Start
```bash
# Install
cd custom-skills/00-claude-code-setting/code
chmod +x install.sh
./install.sh
# Run audit
python3 scripts/run_audit.py
# Apply fixes
python3 scripts/auto_fix.py --apply
```
## What Gets Analyzed
| Component | Checks |
|-----------|--------|
| **MCP Servers** | serverInstructions presence, token estimates, load strategy |
| **CLAUDE.md** | Line count, token estimate, structure quality |
| **Commands** | Frontmatter, description, size limits |
| **Skills** | SKILL.md presence, size limits |
| **Agents** | Tool restrictions |
## Target Metrics
| Metric | Target | Max |
|--------|--------|-----|
| CLAUDE.md tokens | 2,000 | 3,000 |
| MCP tokens (with Tool Search) | 5,000 | 10,000 |
| Baseline total | <30% | <40% |
| Available for work | >70% | — |
## Files
```
00-claude-code-setting/
├── README.md
└── code/
├── CLAUDE.md # Skill directive
├── install.sh # Installation script
├── commands/
│ └── settings-audit.md # /settings-audit command
├── scripts/
│ ├── run_audit.py # Main orchestrator
│ ├── analyze_tokens.py # Token analysis
│ ├── analyze_extensions.py
│ └── auto_fix.py # Auto-fix with backup
└── references/
└── token-optimization.md
```
## Auto-Fix Capabilities
**Safe (automatic with backup):**
- Add serverInstructions to MCP servers
- Add frontmatter to commands
**Manual review required:**
- Disabling MCP servers
- Restructuring CLAUDE.md
- Removing extensions
## Requirements
- Python 3.8+
- PyYAML (optional, for better frontmatter parsing)

125
custom-skills/00-our-settings-audit/README.md Normal file
View File

@@ -0,0 +1,125 @@
# Claude Settings Optimizer
Self-audit and optimize Claude configuration for maximum token efficiency.
**Supports both Claude Code (CLI) and Claude Desktop (App).**
## Purpose
- **Diagnose all Claude errors** (8 categories covered)
- Analyze token usage across MCP servers, CLAUDE.md, and extensions
- Troubleshoot MCP connection issues
- Identify optimization opportunities
- Auto-fix common issues with backup safety (Code version)
- Keep working context at 70%+ of 200K limit
## Platform Versions
| Version | Path | Use Case |
|---------|------|----------|
| **Claude Code** | `code/` | CLI with automated scripts |
| **Claude Desktop** | `desktop/` | App-based manual guidance |
## Claude Code Quick Start
```bash
# Install
cd custom-skills/00-our-settings-audit/code
chmod +x install.sh
./install.sh
# Run audit
python3 scripts/run_audit.py
# Apply fixes
python3 scripts/auto_fix.py --apply
```
## Claude Desktop Quick Start
Covers **8 error categories**:
| Category | Example Errors |
|----------|----------------|
| Context/Input | "Exceed response limit" |
| Output | "Response could not be fully generated" |
| Length/File | "Message will exceed length limit", "Files larger than 10mb" |
| Usage Limits | "5-hour limit reached", "X messages left" |
| Server/Capacity | "Unexpected capacity constraints" |
| MCP Connection | "Error connecting to [ServerName]" |
| Account | "Account has been disabled", login errors |
| Output Quality | Output cutoff, gibberish, mixed languages |
**When encountering any error:**
1. Use the Quick Diagnosis Tree in `desktop/SKILL.md`
2. Follow category-specific troubleshooting steps
3. Apply prevention checklist recommendations
**For MCP issues**, share your config file:
- macOS: `~/Library/Application Support/Claude/claude_desktop_config.json`
- Windows: `%APPDATA%\Claude\claude_desktop_config.json`
## What Gets Analyzed
| Component | Checks |
|-----------|--------|
| **MCP Servers** | serverInstructions presence, token estimates, load strategy |
| **CLAUDE.md** | Line count, token estimate, structure quality |
| **Commands** | Frontmatter, description, size limits |
| **Skills** | SKILL.md presence, size limits |
| **Agents** | Tool restrictions |
## Target Metrics
| Metric | Target | Max |
|--------|--------|-----|
| CLAUDE.md tokens | 2,000 | 3,000 |
| MCP tokens (with Tool Search) | 5,000 | 10,000 |
| Baseline total | <30% | <40% |
| Available for work | >70% | — |
## Files
```
00-our-settings-audit/
├── README.md
├── code/ # Claude Code (CLI)
│ ├── CLAUDE.md # Skill directive
│ ├── install.sh # Installation script
│ ├── commands/
│ │ └── settings-audit.md # /settings-audit command
│ ├── scripts/
│ │ ├── run_audit.py # Main orchestrator
│ │ ├── analyze_tokens.py # Token analysis
│ │ ├── analyze_extensions.py
│ │ └── auto_fix.py # Auto-fix with backup
│ └── references/
│ └── token-optimization.md
│
└── desktop/ # Claude Desktop (App)
├── skill.yaml # Skill metadata
├── SKILL.md # Diagnosis workflow (8 error categories)
├── references/
│ ├── config-locations.md # Config file paths
│ ├── mcp-token-estimates.md # Token budget guide
│ └── our-settings-audit.md # Claude.ai project reference
└── examples/
└── sample-audit-report.md # Example output
```
## Auto-Fix Capabilities
**Safe (automatic with backup):**
- Add serverInstructions to MCP servers
- Add frontmatter to commands
**Manual review required:**
- Disabling MCP servers
- Restructuring CLAUDE.md
- Removing extensions
## Requirements
- Python 3.8+
- PyYAML (optional, for better frontmatter parsing)

0
custom-skills/00-claude-code-setting/code/CLAUDE.md → custom-skills/00-our-settings-audit/code/CLAUDE.md
View File

0
custom-skills/00-claude-code-setting/code/commands/settings-audit.md → custom-skills/00-our-settings-audit/code/commands/settings-audit.md
View File

0
custom-skills/00-claude-code-setting/code/install.sh → custom-skills/00-our-settings-audit/code/install.sh
View File

0
custom-skills/00-claude-code-setting/code/references/token-optimization.md → custom-skills/00-our-settings-audit/code/references/token-optimization.md
View File

0
custom-skills/00-claude-code-setting/code/scripts/analyze_extensions.py → custom-skills/00-our-settings-audit/code/scripts/analyze_extensions.py
View File

0
custom-skills/00-claude-code-setting/code/scripts/analyze_tokens.py → custom-skills/00-our-settings-audit/code/scripts/analyze_tokens.py
View File

0
custom-skills/00-claude-code-setting/code/scripts/auto_fix.py → custom-skills/00-our-settings-audit/code/scripts/auto_fix.py
View File

0
custom-skills/00-claude-code-setting/code/scripts/requirements.txt → custom-skills/00-our-settings-audit/code/scripts/requirements.txt
View File

0
custom-skills/00-claude-code-setting/code/scripts/run_audit.py → custom-skills/00-our-settings-audit/code/scripts/run_audit.py
View File

0
custom-skills/00-claude-code-setting/code/settings-audit-report.json → custom-skills/00-our-settings-audit/code/settings-audit-report.json
View File

0
custom-skills/00-claude-code-setting/code/settings-audit-report.md → custom-skills/00-our-settings-audit/code/settings-audit-report.md
View File

633
custom-skills/00-our-settings-audit/desktop/SKILL.md Normal file
View File

@@ -0,0 +1,633 @@
---
name: our-settings-audit
description: |
Diagnose all Claude Desktop errors and optimize context usage.
Covers 8 error categories: context limits, output interruption,
length/file errors, usage limits, server capacity, MCP connection,
account issues, and output quality problems.
Triggers: settings audit, exceed response limit, MCP error, token error.
---
# Claude Desktop Settings Checker
Diagnose Claude Desktop errors and optimize context usage.
## Error Quick Reference
| Error Type | Message Pattern | Category |
|------------|-----------------|----------|
| Context too large | "Exceed response limit" | Input |
| Output interrupted | "Response could not be fully generated" | Output |
| Length exceeded | "Message will exceed the length limit" | Input |
| Conversation limit | "This conversation reached its maximum length" | Input |
| File too large | "Files larger than 10mb" / "X% over the length limit" | File |
| Rate limited | "5-hour limit reached" / "X messages left" | Usage |
| Server overload | "Due to unexpected capacity constraints" | Server |
| MCP failure | "Error connecting to [ServerName]" | MCP |
| Account issue | "Account has been disabled" | Account |
## Quick Diagnosis Tree
```
Error occurred?
│
├─ BEFORE response started?
│ ├─ "Exceed response limit" → Reduce input context
│ ├─ "Length limit" → Break into smaller messages
│ ├─ "File too large" → Reduce file size or excerpt
│ ├─ "Capacity constraints" → Wait and retry
│ └─ "MCP error" → Check MCP configuration
│
├─ DURING response?
│ ├─ "Could not be fully generated" → Request smaller output
│ └─ Output suddenly stopped → Retry or chunk request
│
└─ BEFORE even sending?
├─ "5-hour limit reached" → Wait for reset
├─ "Messages left" → Near usage limit
└─ "Account disabled" → Contact support
```
## Understanding Token Limits
| Model | Context Window | Output Limit | Practical Available |
|-------|---------------|--------------|---------------------|
| Claude 3.5 Sonnet | 200K tokens | ~8K tokens | ~150K after system |
| Claude 3 Opus | 200K tokens | ~4K tokens | ~150K after system |
| Claude 3 Haiku | 200K tokens | ~4K tokens | ~160K after system |
---
# CATEGORY 1: Input/Context Errors
## Error: "Exceed response limit"
**Causes:**
1. Loaded context too large (MCP tools + skills + files)
2. Conversation history accumulated
3. Multiple large files attached
## Quick Diagnosis
When user reports "Exceed response limit":
### Step 1: Check Loaded Context
Ask user to share their `claude_desktop_config.json`:
- macOS: `~/Library/Application Support/Claude/claude_desktop_config.json`
- Windows: `%APPDATA%\Claude\claude_desktop_config.json`
Analyze:
- [ ] Number of MCP servers configured
- [ ] Servers with many tools (>20 tools each)
- [ ] Missing or poor `serverInstructions`
### Step 2: Estimate Token Usage
| Component | Tokens (approx) | Notes |
|-----------|-----------------|-------|
| Per MCP server | 500-2,000 | Base overhead |
| Per tool definition | 100-500 | Depends on schema complexity |
| Playwright MCP | ~13,500 | 20+ tools, detailed schemas |
| Notion MCP | ~5,000 | Moderate |
| GitHub MCP | ~18,000 | Many tools |
| Custom SKILL.md | 200-2,000 | Depends on length |
| Attached file | Variable | ~4 tokens per word |
**Red flags:**
- More than 5 MCP servers active
- Any server without `serverInstructions`
- Total MCP tools > 100
### Step 3: Review Loaded Skills
Check for:
- Skills with long SKILL.md files (>1,000 words)
- Multiple skills loaded simultaneously
- Skills with embedded reference data
## Optimization Recommendations
### MCP Server Optimization
**Priority 1: Add serverInstructions**
Every MCP server needs concise instructions:
```json
{
"mcpServers": {
"playwright": {
"command": "...",
"serverInstructions": "Browser automation for web testing. Use for: screenshots, page analysis, form testing. Keywords: browser, DOM, screenshot"
}
}
}
```
Pattern: `[Purpose]. Use for: [case1], [case2]. Keywords: [kw1], [kw2]`
**Priority 2: Reduce Active Servers**
Keep only essential servers active. Disable or remove:
- Servers used less than weekly
- Servers with overlapping functionality
- Servers with 30+ tools (like Zapier)
### Conversation Management
**Before complex tasks:**
1. Start fresh conversation for unrelated work
2. Avoid attaching multiple large files
3. Request concise outputs
**During long sessions:**
1. Start new conversation at natural breakpoints
2. Summarize important context before continuing
3. Remove completed file attachments
### Project File Optimization
For project skills and configurations:
| File Type | Target Length | Max |
|-----------|--------------|-----|
| SKILL.md | 500 words | 1,000 words |
| Project instructions | 200 words | 500 words |
| Embedded data | 0 | Move to external |
**Optimization techniques:**
1. Move reference data to separate files (load on demand)
2. Use tables instead of prose
3. Remove redundant information
4. Link to documentation instead of embedding
## Token Budget Calculator
Help user calculate their baseline:
```
System overhead: ~10,000 tokens (fixed)
MCP servers: [count] × ~3,000 = [estimate]
Loaded skills: [count] × ~500 = [estimate]
Project instructions: ~[estimate based on length]
────────────────────────────────────────────────
Baseline total: [sum]
Available for work: 200,000 - [sum] = [remaining]
Available percentage: [remaining/200,000 × 100]%
```
**Targets:**
- Baseline: < 40,000 tokens (20%)
- Available: > 160,000 tokens (80%)
**Warning zone:**
- Baseline > 60,000 tokens: Likely to hit limits
- Available < 140,000 tokens: Reduce configuration
## Output Format
After diagnosis, provide:
```markdown
## Settings Check Report
### Configuration Summary
- MCP Servers: [count] ([tokens estimate])
- Active Skills: [count] ([tokens estimate])
- Baseline Total: ~[X] tokens ([Y]%)
- Available: ~[Z] tokens ([W]%)
### Issues Found
1. [Critical]: [issue description]
2. [Warning]: [issue description]
### Recommended Actions
1. [Action with specific steps]
2. [Action with specific steps]
### Quick Wins (immediate impact)
- [ ] [Specific change]
- [ ] [Specific change]
```
## Common Scenarios
### Scenario: Too Many MCP Servers
**Symptoms:** Errors on first message of conversation
**Solution:** Disable non-essential servers, add serverInstructions
### Scenario: Long Conversation History
**Symptoms:** Errors after many exchanges
**Solution:** Start new conversation, summarize context
### Scenario: Large File Attachments
**Symptoms:** Errors when attaching files
**Solution:** Attach smaller excerpts, use file references
### Scenario: Complex Skill Loaded
**Symptoms:** Errors when using specific skill
**Solution:** Refactor skill, move data to references
---
## Error 2: "Response could not be fully generated"
This error occurs when **output generation** is interrupted mid-stream.
### Causes
| Cause | Description | Frequency |
|-------|-------------|-----------|
| **Output token limit** | Response exceeded ~4K-8K output limit | Common |
| **Safety filter** | Content flagged during generation | Occasional |
| **Network interruption** | Connection dropped mid-stream | Occasional |
| **Server timeout** | Generation took too long | Rare |
| **Rate limiting** | Too many requests in short time | Rare |
### Common Triggers
**1. Requesting too much output:**
```
❌ "Write a complete 50-page report on..."
❌ "Generate the entire application code"
❌ "List all 500 items with full descriptions"
✅ "Write section 1: introduction and overview"
✅ "Generate the authentication module first"
✅ "List items 1-50 with descriptions"
```
**2. Vague prompts (produce longer responses):**
```
❌ "Explain everything about machine learning"
✅ "Explain gradient descent in 3 paragraphs"
```
**3. Code generation without scope:**
```
❌ "Build me a full-stack e-commerce site"
✅ "Create the product listing component with pagination"
```
### Solutions
| Situation | Fix |
|-----------|-----|
| Long report/document | Request section by section |
| Large codebase | Generate module by module |
| Comprehensive list | Paginate (1-50, 51-100, etc.) |
| Detailed explanation | Ask for "brief" or "concise" version |
| Transient failure | Simply retry the request |
### Prompting Techniques
**Add output constraints:**
- "In under 500 words..."
- "Provide a concise summary..."
- "List the top 10..."
- "Focus only on..."
**Chunk large tasks:**
- "First, outline the structure"
- "Now write section 1"
- "Continue with section 2"
**Request format control:**
- "Use bullet points, not paragraphs"
- "Provide a table summary"
- "Give me just the key points"
### When to Retry vs. Rephrase
| Scenario | Action |
|----------|--------|
| Error on first attempt | Retry once |
| Error persists after retry | Rephrase with smaller scope |
| Error always at same point | Content may be triggering filter |
| Error after long generation | Request was too ambitious |
---
# CATEGORY 3: Length & File Errors
## Error: "Your message will exceed the length limit"
**Full message:** "Your message will exceed the length limit for this chat..."
**Causes:**
- Single message too long (approaching context limit)
- Too much text pasted at once
**Solutions:**
1. Break content into smaller chunks
2. Summarize key sections before sending
3. Ask Claude to identify relevant portions first
4. Start a new conversation
## Error: "This conversation reached its maximum length"
**Cause:** Accumulated conversation history filled context window
**Solutions:**
1. Start a new conversation
2. Copy essential context to new chat
3. Use shorter exchanges going forward
## Error: "Message is X% over the length limit"
**Full message:** "Message is X% over the length limit. Try replacing the attached file with smaller excerpts."
**Cause:** Attached file(s) too large for remaining context
**Solutions:**
1. Extract relevant excerpts only
2. Summarize large documents before attaching
3. Split across multiple messages
4. Use file references instead of full content
## Error: "You may not upload files larger than 10MB"
**Cause:** Single file exceeds 10MB limit
**Solutions:**
1. Compress file if possible
2. Split into smaller files
3. Extract text content only
4. Use external link and describe content
---
# CATEGORY 4: Usage & Rate Limit Errors
## Error: "5-hour limit reached - resets [time]"
**Cause:** Hit plan's usage cap within 5-hour window
**Solutions:**
1. Wait until reset time shown
2. Upgrade plan for higher limits
3. Optimize prompts to use fewer tokens
## Error: "Approaching 5-hour limit"
**Cause:** Warning before hitting limit
**Solutions:**
1. Prioritize remaining important tasks
2. Use concise prompts
3. Avoid exploratory conversations
## Error: "X messages left until [time]"
**Cause:** Near message limit (free tier)
**Solutions:**
1. Combine multiple questions into one
2. Wait for reset
3. Consider paid plan
## Error: "5-hour limit resets [time] - continuing with extra usage"
**Note:** This is informational for paid plans with extra usage enabled
**Action:** Extra usage automatically continues; monitor costs
---
# CATEGORY 5: Server & Capacity Errors
## Error: "Due to unexpected capacity constraints, Claude is unable to respond"
**Cause:** High system-wide demand
**Solutions:**
1. Wait 2-5 minutes and retry
2. Try during off-peak hours
3. Check [status.claude.com](https://status.claude.com) for incidents
## HTTP Error Codes
| Code | Meaning | Solution |
|------|---------|----------|
| 500 | Internal Server Error | Wait and retry |
| 429 | Too Many Requests | Slow down, wait |
| 403 | Forbidden | Check account status |
| 400 | Bad Request | Check input format |
## Error: "Claude AI Saving Chat Failed"
**Cause:** Issue saving conversation to servers
**Solutions:**
1. Refresh the page
2. Check internet connection
3. Copy important content locally
4. Try again later
---
# CATEGORY 6: MCP Connection Errors
## Error: "There was an error connecting to [ServerName]"
**Causes:**
1. Server not running
2. Incorrect configuration
3. Transport type mismatch (stdio vs HTTP)
4. Authentication failure
### Diagnosis Steps
**Step 1: Check server logs**
- macOS: `~/Library/Logs/Claude/mcp-server-SERVERNAME.log`
- Windows: `%APPDATA%\Claude\logs\mcp-server-SERVERNAME.log`
**Step 2: Verify configuration**
```bash
# macOS
cat ~/Library/Application\ Support/Claude/claude_desktop_config.json
# Windows PowerShell
Get-Content "$env:APPDATA\Claude\claude_desktop_config.json"
```
**Step 3: Test server independently**
```bash
# Test if server starts
npx @anthropic-ai/mcp-server-name
```
### Common MCP Issues
| Issue | Symptom | Fix |
|-------|---------|-----|
| Transport mismatch | HTTP server with stdio config | Add `"transport": "http"` |
| Path with spaces | Server fails on Windows | Use escaped paths or `%APPDATA%` |
| Missing env vars | Auth failures | Add to `"env"` in config |
| Server not installed | "command not found" | Run `npm install -g` first |
| Port conflict | Server won't start | Change port or kill existing |
### After Config Changes
**Critical:** Completely quit and restart Claude Desktop after any config changes.
## Error: "Required parameter" validation errors
**Cause:** MCP tool schema mismatch (regression bug)
**Solutions:**
1. Update Claude Desktop to latest version
2. Check MCP server for updates
3. Temporarily disable problematic server
---
# CATEGORY 7: Account Errors
## Error: "Your account has been disabled"
**Full message:** "Your account has been disabled after an automatic review of your recent activities."
**Cause:** Automated system flagged account
**Solutions:**
1. Contact Anthropic support
2. Review Terms of Service
3. Do not create new accounts (may worsen situation)
## Error: "This organization has been disabled"
**Cause:** Organization-level suspension
**Solution:** Organization admin must contact Anthropic
## Error: "There was an error logging you in"
**Causes:**
- VPN interference
- Browser extensions blocking
- Cached credentials issue
**Solutions:**
1. Disable VPN
2. Disable browser extensions temporarily
3. Clear browser cache and cookies
4. Try incognito/private window
5. Check [status.claude.com](https://status.claude.com)
## Error: "Error Sending Codes - Check Your Phone Number"
**Cause:** Phone verification failed during signup
**Solutions:**
1. Verify correct country code
2. Check all digits entered correctly
3. Try different phone number
4. Wait and retry later
---
# CATEGORY 8: Output Quality Issues
## Issue: Output Suddenly Stops (Cutoff)
**Symptoms:** Response ends mid-sentence or mid-code
**Causes:**
1. Hit output token limit (~4K-8K)
2. Safety filter triggered
3. Server timeout
**Solutions:**
1. Ask "Please continue from where you stopped"
2. Request smaller chunks upfront
3. Be more specific in scope
## Issue: Gibberish or Nonsensical Output
**Symptoms:** Incoherent text, random characters
**Causes:**
1. Model confusion from complex prompt
2. Conflicting instructions
3. Edge case in training
**Solutions:**
1. Simplify prompt
2. Start new conversation
3. Rephrase request differently
## Issue: Mixed Languages or Character Issues
**Symptoms:** Unexpected language switches, formatting problems
**Causes:**
1. Ambiguous language context
2. Copy-pasted special characters
**Solutions:**
1. Explicitly state desired language
2. Clean input text of special characters
3. Add "Please respond in [language]"
## Issue: Claude Refuses to Respond
**Symptoms:** Declines request citing policy
**Causes:**
1. Request triggered safety guidelines
2. Ambiguous phrasing interpreted as harmful
**Solutions:**
1. Rephrase more clearly
2. Explain legitimate use case
3. Break into smaller, clearer requests
---
## Prevention Checklist
### Context/Input Errors
- [ ] Maximum 5 MCP servers active
- [ ] All servers have serverInstructions
- [ ] Skills under 1,000 words
- [ ] Start fresh conversations for new topics
- [ ] Avoid attaching files over 50KB (prefer excerpts)
- [ ] Individual files under 10MB
### Output Errors
- [ ] Break large requests into chunks
- [ ] Use specific scope in prompts
- [ ] Request concise/brief outputs when possible
- [ ] Paginate lists and tables (50 items max)
- [ ] Generate code module by module
- [ ] Retry once before rephrasing
### Usage Limits
- [ ] Monitor "messages left" warnings
- [ ] Combine related questions into single prompts
- [ ] Use concise prompts to conserve tokens
- [ ] Know your plan's reset schedule
### MCP Stability
- [ ] Test MCP servers independently before adding
- [ ] Keep server logs accessible for debugging
- [ ] Restart Claude Desktop after config changes
- [ ] Update MCP servers regularly
- [ ] Document working configurations
### General Best Practices
- [ ] Check [status.claude.com](https://status.claude.com) when experiencing issues
- [ ] Keep Claude Desktop updated
- [ ] Clear browser cache periodically (web version)
- [ ] Disable VPN if experiencing login issues
- [ ] Back up important conversations locally

76
custom-skills/00-our-settings-audit/desktop/examples/sample-audit-report.md Normal file
View File

@@ -0,0 +1,76 @@
# Sample Settings Check Report
## Configuration Summary
| Component | Count | Tokens (est.) | Status |
|-----------|-------|---------------|--------|
| MCP Servers | 6 | ~45,000 | ⚠️ High |
| Active Skills | 3 | ~1,500 | ✓ OK |
| Project Files | 2 | ~2,000 | ✓ OK |
| **Baseline Total** | — | ~48,500 | ⚠️ Warning |
| **Available** | — | ~151,500 (76%) | Marginal |
## Issues Found
### Critical
1. **GitHub MCP server loading all tools** (~18,000 tokens)
- 25+ tools loaded but only 3-4 commonly used
- Missing `serverInstructions`
### Warnings
1. **Zapier MCP enabled** (~25,000 tokens)
- 50+ tools, rarely used
- Consider disabling
2. **Playwright missing serverInstructions**
- Tool discovery inefficient
- Add: `"serverInstructions": "Browser automation..."`
3. **Custom skill SKILL.md is 1,500 words**
- Exceeds 1,000 word recommendation
- Move reference data to separate file
## Recommended Actions
### Immediate (save ~35,000 tokens)
1. **Disable Zapier MCP** (saves ~25,000)
```json
// Remove or comment out in claude_desktop_config.json
// "zapier": { ... }
```
2. **Add serverInstructions to all servers** (saves ~5,000)
```json
"github": {
"command": "...",
"serverInstructions": "GitHub operations. Use for: repos, issues, PRs. Keywords: github, repo, issue, pull request"
}
```
3. **Refactor long skill** (saves ~1,000)
- Move data tables to `references/` directory
- Keep SKILL.md under 500 words
### Secondary
4. Consider starting fresh conversations for unrelated tasks
5. Review GitHub usage - if only for viewing, use web instead
## After Optimization
| Component | Tokens (est.) | Status |
|-----------|---------------|--------|
| MCP Servers | ~15,000 | ✓ Good |
| Skills + Files | ~2,500 | ✓ Good |
| **Baseline Total** | ~17,500 | ✓ Good |
| **Available** | ~182,500 (91%) | ✓ Excellent |
## Quick Wins Checklist
- [x] Disable Zapier MCP
- [x] Add serverInstructions to Playwright
- [x] Add serverInstructions to GitHub
- [x] Add serverInstructions to Notion
- [ ] Refactor jamie-brand skill (move procedures data)
- [ ] Review PostgreSQL usage frequency

77
custom-skills/00-our-settings-audit/desktop/references/config-locations.md Normal file
View File

@@ -0,0 +1,77 @@
# Claude Desktop Configuration Locations
## Primary Config File
### macOS
```
~/Library/Application Support/Claude/claude_desktop_config.json
```
### Windows
```
%APPDATA%\Claude\claude_desktop_config.json
```
### Linux
```
~/.config/Claude/claude_desktop_config.json
```
## MCP Server Configuration Example
```json
{
"mcpServers": {
"playwright": {
"command": "npx",
"args": ["-y", "@anthropic-ai/mcp-playwright"],
"serverInstructions": "Browser automation. Use for: screenshots, page testing, DOM inspection. Keywords: browser, page, screenshot, navigate"
},
"notion": {
"command": "npx",
"args": ["-y", "@anthropic-ai/mcp-notion", "--token", "YOUR_TOKEN"],
"serverInstructions": "Notion workspace access. Use for: search pages, create content, update databases. Keywords: notion, page, database, workspace"
}
}
}
```
## Key Fields
| Field | Purpose | Token Impact |
|-------|---------|--------------|
| `command` | Executable path | Minimal |
| `args` | Arguments | Minimal |
| `serverInstructions` | Usage hints | Reduces discovery overhead |
| `env` | Environment vars | None |
## serverInstructions Best Practices
**Good:**
```json
"serverInstructions": "File system access. Use for: read/write files, directory listing. Keywords: file, read, write, directory"
```
**Bad (too vague):**
```json
"serverInstructions": "Various file operations"
```
**Bad (too long):**
```json
"serverInstructions": "This MCP server provides comprehensive file system access capabilities including reading files, writing files, creating directories, listing directory contents, and more. It can be used for any operation that requires..."
```
## Viewing Current Configuration
Ask user to run:
**macOS/Linux:**
```bash
cat ~/Library/Application\ Support/Claude/claude_desktop_config.json | python3 -m json.tool
```
**Windows (PowerShell):**
```powershell
Get-Content "$env:APPDATA\Claude\claude_desktop_config.json" | ConvertFrom-Json | ConvertTo-Json -Depth 10
```

88
custom-skills/00-our-settings-audit/desktop/references/mcp-token-estimates.md Normal file
View File

@@ -0,0 +1,88 @@
# MCP Server Token Estimates
Approximate token usage for common MCP servers when loaded.
## Official Anthropic Servers
| Server | Tools | Tokens (est.) | Recommendation |
|--------|-------|---------------|----------------|
| Playwright | 20+ | 13,500 | Keep if testing |
| Filesystem | 8 | 4,000 | Essential |
| Memory | 5 | 3,000 | Optional |
| Brave Search | 2 | 1,500 | Alternative to web |
| Fetch | 2 | 1,200 | Keep for web access |
## Third-Party Servers
| Server | Tools | Tokens (est.) | Recommendation |
|--------|-------|---------------|----------------|
| Notion | 10 | 5,000 | Keep if using Notion |
| GitHub | 25+ | 18,000 | Lazy load only |
| PostgreSQL | 15 | 8,000 | Lazy load only |
| Slack | 12 | 6,000 | Lazy load only |
| Figma | 15 | 10,000 | Lazy load only |
| Zapier | 50+ | 25,000+ | **Avoid** |
| Firecrawl | 5 | 3,500 | Useful for SEO |
| Perplexity | 2 | 1,500 | Alternative to web |
## Token Budget Guidelines
### Conservative Setup (High Available Context)
```
2-3 essential MCP servers
Total: ~10,000-15,000 tokens
Available: 185,000+ tokens (92%+)
```
### Standard Setup
```
4-5 MCP servers
Total: ~20,000-30,000 tokens
Available: 170,000+ tokens (85%+)
```
### Heavy Setup (Risk Zone)
```
6+ MCP servers
Total: 40,000+ tokens
Available: <160,000 tokens (<80%)
⚠️ Higher chance of "Exceed response limit"
```
## Reduction Strategies
### If using GitHub MCP heavily:
- Start conversation specifically for GitHub work
- Don't load other heavy servers simultaneously
### If using multiple API servers:
- Choose ONE per category:
- Web search: Brave OR Perplexity (not both)
- Automation: Zapier OR n8n (not both)
- Database: PostgreSQL OR MySQL (not both)
### If testing/development:
- Playwright OR Puppeteer (not both)
- Load only when actively testing
## Impact of serverInstructions
**Without serverInstructions:**
- Full tool schemas loaded (~500 tokens per tool)
- Discovery overhead on each interaction
**With serverInstructions:**
- Reduced discovery queries
- More efficient tool selection
- Saves ~30-50% on tool-related tokens
## Quick Reference
**Token estimation formula:**
```
Server tokens ≈ (number of tools × 400) + 500 base
```
**Example:**
- 10 tools = (10 × 400) + 500 = 4,500 tokens
- 25 tools = (25 × 400) + 500 = 10,500 tokens

349
custom-skills/00-our-settings-audit/desktop/references/our-settings-audit.md Normal file
View File

@@ -0,0 +1,349 @@
# Claude Settings Audit Guide
> **Purpose**: Condensed reference for Claude.ai Projects
> **Source**: 00-claude-settings-audit skill
> **Version**: 1.0
Comprehensive reference for diagnosing Claude Desktop errors and optimizing context usage.
## Error Quick Reference
| Error Type | Message Pattern | Category |
|------------|-----------------|----------|
| Context too large | "Exceed response limit" | Input |
| Output interrupted | "Response could not be fully generated" | Output |
| Length exceeded | "Message will exceed the length limit" | Input |
| Conversation limit | "Conversation reached maximum length" | Input |
| File too large | "Files larger than 10mb" | File |
| Rate limited | "5-hour limit reached" | Usage |
| Server overload | "Unexpected capacity constraints" | Server |
| MCP failure | "Error connecting to [ServerName]" | MCP |
| Account issue | "Account has been disabled" | Account |
## Quick Diagnosis Tree
```
Error occurred?
│
├─ BEFORE response started?
│ ├─ "Exceed response limit" → Reduce input context
│ ├─ "Length limit" → Break into smaller messages
│ ├─ "File too large" → Reduce file size or excerpt
│ ├─ "Capacity constraints" → Wait and retry
│ └─ "MCP error" → Check MCP configuration
│
├─ DURING response?
│ ├─ "Could not be fully generated" → Request smaller output
│ └─ Output suddenly stopped → Retry or chunk request
│
└─ BEFORE even sending?
├─ "5-hour limit reached" → Wait for reset
├─ "Messages left" → Near usage limit
└─ "Account disabled" → Contact support
```
---
## Token Limits by Model
| Model | Context Window | Output Limit | Practical Available |
|-------|---------------|--------------|---------------------|
| Claude 3.5 Sonnet | 200K tokens | ~8K tokens | ~150K after system |
| Claude 3 Opus | 200K tokens | ~4K tokens | ~150K after system |
| Claude 3 Haiku | 200K tokens | ~4K tokens | ~160K after system |
---
# ERROR CATEGORIES
## 1. Input/Context Errors
### "Exceed response limit"
**Causes:**
- Loaded context too large (MCP tools + skills + files)
- Conversation history accumulated
- Multiple large files attached
**Solutions:**
1. Reduce MCP servers (max 5 recommended)
2. Add `serverInstructions` to all MCP servers
3. Start fresh conversation
4. Attach file excerpts instead of full files
### "Message will exceed the length limit"
**Solutions:**
1. Break content into smaller chunks
2. Summarize key sections before sending
3. Start a new conversation
### "Conversation reached maximum length"
**Solutions:**
1. Start a new conversation
2. Copy essential context to new chat
---
## 2. Output Errors
### "Response could not be fully generated"
**Causes:**
- Output exceeded ~4K-8K token limit
- Safety filter triggered
- Network interruption
- Server timeout
**Solutions:**
1. Request smaller chunks of output
2. Add constraints: "In under 500 words..."
3. Be more specific in scope
4. Retry once before rephrasing
**Prompting techniques:**
- "Provide a concise summary..."
- "List the top 10..."
- "First, outline the structure"
- "Use bullet points, not paragraphs"
---
## 3. File Errors
### "Files larger than 10MB"
**Solutions:**
1. Compress file if possible
2. Split into smaller files
3. Extract text content only
### "Message is X% over the length limit"
**Solutions:**
1. Extract relevant excerpts only
2. Summarize large documents
3. Split across multiple messages
---
## 4. Usage Limit Errors
### "5-hour limit reached"
**Solutions:**
1. Wait until reset time shown
2. Upgrade plan for higher limits
3. Optimize prompts to use fewer tokens
### "X messages left until [time]"
**Solutions:**
1. Combine multiple questions into one
2. Wait for reset
3. Consider paid plan
---
## 5. Server/Capacity Errors
### "Unexpected capacity constraints"
**Solutions:**
1. Wait 2-5 minutes and retry
2. Try during off-peak hours
3. Check status.claude.com for incidents
### HTTP Error Codes
| Code | Meaning | Solution |
|------|---------|----------|
| 500 | Internal Server Error | Wait and retry |
| 429 | Too Many Requests | Slow down, wait |
| 403 | Forbidden | Check account status |
| 400 | Bad Request | Check input format |
---
## 6. MCP Connection Errors
### "Error connecting to [ServerName]"
**Causes:**
1. Server not running
2. Incorrect configuration
3. Transport type mismatch (stdio vs HTTP)
4. Authentication failure
**Diagnosis steps:**
1. Check server logs:
- macOS: `~/Library/Logs/Claude/mcp-server-SERVERNAME.log`
- Windows: `%APPDATA%\Claude\logs\mcp-server-SERVERNAME.log`
2. Verify configuration in `claude_desktop_config.json`
3. Test server independently
**Common fixes:**
| Issue | Fix |
|-------|-----|
| Transport mismatch | Add `"transport": "http"` to config |
| Path with spaces | Use escaped paths |
| Missing env vars | Add to `"env"` in config |
| Server not installed | Run `npm install -g` first |
**Critical:** Restart Claude Desktop after config changes.
---
## 7. Account Errors
### "Account has been disabled"
**Solutions:**
1. Contact Anthropic support
2. Review Terms of Service
3. Do not create new accounts
### "Error logging you in"
**Solutions:**
1. Disable VPN
2. Clear browser cache and cookies
3. Try incognito window
4. Check status.claude.com
---
## 8. Output Quality Issues
### Output Suddenly Stops
**Solutions:**
1. Ask "Please continue from where you stopped"
2. Request smaller chunks upfront
3. Be more specific in scope
### Gibberish Output
**Solutions:**
1. Simplify prompt
2. Start new conversation
3. Rephrase request differently
### Claude Refuses to Respond
**Solutions:**
1. Rephrase more clearly
2. Explain legitimate use case
3. Break into smaller requests
---
# TOKEN BUDGET GUIDELINES
## MCP Server Token Estimates
| Server | Tokens (approx) |
|--------|-----------------|
| Playwright | ~13,500 |
| Notion | ~5,000 |
| GitHub | ~18,000 |
| Filesystem | ~4,000 |
| Zapier | ~25,000+ (avoid) |
## serverInstructions Pattern
Every MCP server should have:
```json
"serverInstructions": "[Purpose]. Use for: [case1], [case2]. Keywords: [kw1], [kw2]"
```
Example:
```json
"serverInstructions": "Browser automation. Use for: screenshots, page testing. Keywords: browser, DOM, screenshot"
```
## Budget Calculator
```
System overhead: ~10,000 tokens (fixed)
MCP servers: [count] × ~3,000 = [estimate]
Loaded skills: [count] × ~500 = [estimate]
Project instructions: ~[estimate]
────────────────────────────────────────────
Baseline total: [sum]
Available for work: 200,000 - [sum] = [remaining]
```
**Targets:**
- Baseline: < 40,000 tokens (20%)
- Available: > 160,000 tokens (80%)
---
# PREVENTION CHECKLIST
## Context/Input
- [ ] Maximum 5 MCP servers active
- [ ] All servers have serverInstructions
- [ ] Skills under 1,000 words
- [ ] Start fresh conversations for new topics
- [ ] Files under 10MB, prefer excerpts
## Output
- [ ] Break large requests into chunks
- [ ] Use specific scope in prompts
- [ ] Paginate lists (50 items max)
- [ ] Retry once before rephrasing
## Usage Limits
- [ ] Monitor "messages left" warnings
- [ ] Combine related questions
- [ ] Use concise prompts
## MCP Stability
- [ ] Test servers before adding
- [ ] Restart app after config changes
- [ ] Keep servers updated
## General
- [ ] Check status.claude.com when issues occur
- [ ] Keep Claude Desktop updated
- [ ] Back up important conversations
---
# CONFIGURATION LOCATIONS
## Config Files
**macOS:**
```
~/Library/Application Support/Claude/claude_desktop_config.json
```
**Windows:**
```
%APPDATA%\Claude\claude_desktop_config.json
```
## Log Files
**macOS:**
```
~/Library/Logs/Claude/mcp-server-SERVERNAME.log
```
**Windows:**
```
%APPDATA%\Claude\logs\mcp-server-SERVERNAME.log
```
---
*Reference: Claude Settings Audit Skill v1.0*
*Last updated: 2025-02*

39
custom-skills/00-our-settings-audit/desktop/skill.yaml Normal file
View File

@@ -0,0 +1,39 @@
# OurDigital Settings Audit
# Comprehensive error diagnosis and context optimization
name: our-settings-audit
description: |
Diagnose all Claude Desktop errors and optimize context usage.
Covers 8 error categories: context limits, output interruption,
length/file errors, usage limits, server capacity, MCP connection,
account issues, and output quality problems.
allowed-tools:
- Read
- Glob
- Grep
license: Internal-use Only
triggers:
- settings audit
- settings check
- audit settings
- exceed response limit
- response could not be generated
- length limit
- file too large
- conversation limit
- 5-hour limit
- messages left
- rate limit
- capacity constraints
- server error
- MCP error
- server connection failed
- account disabled
- login error
- output cutoff
- token error
- gibberish output

7
custom-skills/11-seo-on-page-audit/desktop/SKILL.md
View File

@@ -1,3 +1,10 @@
---
name: seo-on-page-audit
description: |
On-page SEO analyzer for meta tags, headings, links, images, and Open Graph.
Triggers: on-page SEO, meta tags, title tag, heading structure, alt text.
---
# SEO On-Page Audit # SEO On-Page Audit
## Purpose ## Purpose

7
custom-skills/12-seo-local-audit/desktop/SKILL.md
View File

@@ -1,3 +1,10 @@
---
name: seo-local-audit
description: |
Local business SEO auditor for NAP consistency, Google Business Profile, and citations.
Triggers: local SEO, NAP audit, Google Business Profile, GBP optimization, local citations.
---
# SEO Local Audit # SEO Local Audit
## Purpose ## Purpose

7
custom-skills/13-seo-schema-validator/desktop/SKILL.md
View File

@@ -1,3 +1,10 @@
---
name: seo-schema-validator
description: |
Structured data validator for JSON-LD, Microdata, and RDFa against schema.org.
Triggers: validate schema, JSON-LD check, structured data, rich results eligibility.
---
# SEO Schema Validator # SEO Schema Validator
## Purpose ## Purpose

7
custom-skills/14-seo-schema-generator/desktop/SKILL.md
View File

@@ -1,3 +1,10 @@
---
name: seo-schema-generator
description: |
JSON-LD structured data generator from templates for various content types.
Triggers: generate schema, create JSON-LD, schema markup, structured data generator.
---
# SEO Schema Generator # SEO Schema Generator
## Purpose ## Purpose

7
custom-skills/15-seo-core-web-vitals/desktop/SKILL.md
View File

@@ -1,3 +1,10 @@
---
name: seo-core-web-vitals
description: |
Core Web Vitals analyzer for LCP, FID, CLS, and INP optimization recommendations.
Triggers: Core Web Vitals, page speed, LCP optimization, CLS fix, INP analysis.
---
# SEO Core Web Vitals # SEO Core Web Vitals
## Purpose ## Purpose

7
custom-skills/16-seo-search-console/desktop/SKILL.md
View File

@@ -1,3 +1,10 @@
---
name: seo-search-console
description: |
Google Search Console data analyzer for performance, queries, and index coverage.
Triggers: Search Console, GSC analysis, search performance, rankings, CTR optimization.
---
# SEO Search Console # SEO Search Console
## Purpose ## Purpose

7
custom-skills/17-seo-gateway-architect/desktop/SKILL.md
View File

@@ -1,3 +1,10 @@
---
name: seo-gateway-architect
description: |
Gateway page strategy planner for keyword research, content architecture, and SEO KPIs.
Triggers: SEO strategy, gateway pages, keyword research, content architecture.
---
# SEO Gateway Page Strategist # SEO Gateway Page Strategist
This skill helps you create comprehensive SEO-focused gateway page strategies for Korean medical/service websites, optimized for both Naver and Google. This skill helps you create comprehensive SEO-focused gateway page strategies for Korean medical/service websites, optimized for both Naver and Google.

7
custom-skills/18-seo-gateway-builder/desktop/SKILL.md
View File

@@ -1,3 +1,10 @@
---
name: seo-gateway-builder
description: |
Gateway page content builder with templates, schema markup, and local SEO optimization.
Triggers: build gateway page, create landing page, local service page, location pages.
---
# Gateway Page Content Builder # Gateway Page Content Builder
A comprehensive skill for building high-quality, SEO-optimized gateway page content for local services, medical practices, and business locations. A comprehensive skill for building high-quality, SEO-optimized gateway page content for local services, medical practices, and business locations.

7
custom-skills/19-seo-technical-audit/desktop/SKILL.md
View File

@@ -1,3 +1,10 @@
---
name: seo-technical-audit
description: |
Technical SEO analyzer for robots.txt, sitemap, and crawlability fundamentals.
Triggers: technical SEO, robots.txt, sitemap validation, crawlability, URL accessibility.
---
# SEO Technical Audit # SEO Technical Audit
## Purpose ## Purpose

7
custom-skills/20-gtm-audit/desktop/SKILL.md
View File

@@ -1,3 +1,10 @@
---
name: gtm-audit
description: |
GTM container audit using Chrome DevTools and DTM Agent for tag verification.
Triggers: audit GTM, GTM analysis, tag debugging, dataLayer inspection.
---
# GTM Audit Skill # GTM Audit Skill
Automated audit workflow for GTM containers using **Chrome DevTools MCP** for browser inspection and **DTM Agent MCP** for GTM API operations. Automated audit workflow for GTM containers using **Chrome DevTools MCP** for browser inspection and **DTM Agent MCP** for GTM API operations.

7
custom-skills/22-gtm-guardian/desktop/SKILL.md
View File

@@ -1,3 +1,10 @@
---
name: gtm-guardian
description: |
GTM tagging lifecycle manager: analysis, planning, taxonomy, implementation guide.
Triggers: GTM strategy, tagging plan, event taxonomy, implementation guide.
---
# GTM Guardian (Desktop) # GTM Guardian (Desktop)
GTM(Google Tag Manager) 태깅 전략 수립부터 구현까지의 전체 라이프사이클을 지원하는 7단계 워크플로우 스킬. GTM(Google Tag Manager) 태깅 전략 수립부터 구현까지의 전체 라이프사이클을 지원하는 7단계 워크플로우 스킬.

7
custom-skills/31-notion-organizer/desktop/SKILL.md
View File

@@ -1,3 +1,10 @@
---
name: notion-organizer
description: |
Notion workspace manager for database optimization, property cleanup, and bulk operations.
Triggers: organize Notion, workspace cleanup, database schema, property standardization.
---
# Notion Organizer Skill # Notion Organizer Skill
## Purpose ## Purpose

7
custom-skills/32-notion-writer/desktop/SKILL.md
View File

@@ -1,3 +1,10 @@
---
name: notion-writer
description: |
Markdown to Notion page writer with database row creation support.
Triggers: write to Notion, export to Notion, push content, create Notion page.
---
# Notion Writer Skill # Notion Writer Skill
Push markdown content to Notion pages or databases via Claude Code. Push markdown content to Notion pages or databases via Claude Code.

7
custom-skills/40-jamie-brand-editor/desktop/SKILL.md
View File

@@ -1,3 +1,10 @@
---
name: jamie-brand-editor
description: |
Jamie Plastic Surgery branded content generator for blog posts and marketing.
Triggers: write Jamie blog, Jamie content, brand copywriting, 제이미 콘텐츠.
---
# Jamie Brand Editor Skill # Jamie Brand Editor Skill
> **Purpose**: Generate branded content for Jamie Plastic Surgery Clinic > **Purpose**: Generate branded content for Jamie Plastic Surgery Clinic

7
custom-skills/41-jamie-brand-audit/desktop/SKILL.md
View File

@@ -1,3 +1,10 @@
---
name: jamie-brand-audit
description: |
Jamie Plastic Surgery brand compliance reviewer and content evaluator.
Triggers: review content, brand audit, 제이미 브랜드 검토, tone and manner check.
---
# Jamie Clinic Brand Guardian Skill # Jamie Clinic Brand Guardian Skill
> **브랜드**: 제이미성형외과 (Jamie Plastic Surgery Clinic) > **브랜드**: 제이미성형외과 (Jamie Plastic Surgery Clinic)

7
custom-skills/43-jamie-youtube-manager/desktop/SKILL.md
View File

@@ -1,3 +1,10 @@
---
name: jamie-youtube-manager
description: |
Jamie Clinic YouTube channel SEO auditor and content manager.
Triggers: YouTube SEO, video audit, 제이미 유튜브, channel optimization.
---
# Jamie YouTube Manager Skill # Jamie YouTube Manager Skill
> **Purpose**: YouTube Channel SEO Auditor & Content Manager for Jamie Plastic Surgery Clinic > **Purpose**: YouTube Channel SEO Auditor & Content Manager for Jamie Plastic Surgery Clinic

7
custom-skills/44-jamie-youtube-subtitle-checker/desktop/SKILL.md
View File

@@ -1,3 +1,10 @@
---
name: jamie-youtube-subtitle-checker
description: |
SBV subtitle file typo corrector and YouTube metadata generator for Jamie Clinic.
Triggers: check subtitles, subtitle QA, SBV correction, 자막 교정.
---
# Jamie YouTube Subtitle Editor Skill # Jamie YouTube Subtitle Editor Skill
> **Purpose**: SBV 자막 파일 오타 교정 및 YouTube 메타데이터 생성 > **Purpose**: SBV 자막 파일 오타 교정 및 YouTube 메타데이터 생성

7
custom-skills/45-jamie-instagram-manager/desktop/SKILL.md
View File

@@ -1,3 +1,10 @@
---
name: jamie-instagram-manager
description: |
Jamie Clinic Instagram account manager for engagement, content planning, and boost strategy.
Triggers: Instagram management, 제이미 인스타그램, IG strategy, social media.
---
# Jamie Instagram Manager Skill # Jamie Instagram Manager Skill
> **Purpose**: Dedicated Instagram Account Manager for Jamie Plastic Surgery Clinic > **Purpose**: Dedicated Instagram Account Manager for Jamie Plastic Surgery Clinic

7
custom-skills/90-reference-curator/01-reference-discovery/desktop/SKILL.md
View File

@@ -1,3 +1,10 @@
---
name: reference-discovery
description: |
Search and discover authoritative reference sources with credibility validation.
Triggers: find sources, search documentation, discover references, source validation.
---
# Reference Discovery # Reference Discovery
Searches for authoritative sources, validates credibility, and produces curated URL lists for crawling. Searches for authoritative sources, validates credibility, and produces curated URL lists for crawling.

7
custom-skills/90-reference-curator/02-web-crawler-orchestrator/desktop/SKILL.md
View File

@@ -1,3 +1,10 @@
---
name: web-crawler-orchestrator
description: |
Multi-backend web crawler with Firecrawl MCP, rate limiting, and format handling.
Triggers: crawl URLs, fetch pages, scrape content, web crawler.
---
# Web Crawler Orchestrator # Web Crawler Orchestrator
Manages crawling operations using Firecrawl MCP with rate limiting and format handling. Manages crawling operations using Firecrawl MCP with rate limiting and format handling.

7
custom-skills/90-reference-curator/03-content-repository/desktop/SKILL.md
View File

@@ -1,3 +1,10 @@
---
name: content-repository
description: |
MySQL storage manager for reference library with versioning and deduplication.
Triggers: store content, manage repository, document database, content storage.
---
# Content Repository # Content Repository
Manages MySQL storage for the reference library system. Handles document storage, version control, deduplication, and retrieval. Manages MySQL storage for the reference library system. Handles document storage, version control, deduplication, and retrieval.

7
custom-skills/90-reference-curator/04-content-distiller/desktop/SKILL.md
View File

@@ -1,3 +1,10 @@
---
name: content-distiller
description: |
Raw content summarizer extracting key concepts, code snippets, and structured output.
Triggers: distill content, summarize document, extract key concepts, compress content.
---
# Content Distiller # Content Distiller
Transforms raw crawled content into structured, high-quality reference materials. Transforms raw crawled content into structured, high-quality reference materials.

7
custom-skills/90-reference-curator/05-quality-reviewer/desktop/SKILL.md
View File

@@ -1,3 +1,10 @@
---
name: quality-reviewer
description: |
Content quality evaluator with multi-criteria scoring and decision routing.
Triggers: review quality, score content, QA review, approve refactor reject.
---
# Quality Reviewer # Quality Reviewer
Evaluates distilled content for quality, routes decisions, and triggers refactoring or additional research when needed. Evaluates distilled content for quality, routes decisions, and triggers refactoring or additional research when needed.

7
custom-skills/90-reference-curator/06-markdown-exporter/desktop/SKILL.md
View File

@@ -1,3 +1,10 @@
---
name: markdown-exporter
description: |
Export approved content to markdown files or JSONL for fine-tuning.
Triggers: export markdown, generate files, create JSONL, export content.
---
# Markdown Exporter # Markdown Exporter
Exports approved content as structured markdown files for Claude Projects or fine-tuning. Exports approved content as structured markdown files for Claude Projects or fine-tuning.

7
custom-skills/90-reference-curator/07-pipeline-orchestrator/desktop/SKILL.md
View File

@@ -1,3 +1,10 @@
---
name: pipeline-orchestrator
description: |
Full reference curation pipeline coordinator with QA loop and state management.
Triggers: run pipeline, orchestrate workflow, full curation, pipeline start.
---
# Pipeline Orchestrator # Pipeline Orchestrator
Coordinates the full reference curation workflow, handling QA loops and state management. Coordinates the full reference curation workflow, handling QA loops and state management.

22
custom-skills/91-multi-agent-guide/.claude-plugin/plugin.json
View File

@@ -1,7 +1,7 @@
{ {
"name": "multi-agent-guide", "name": "multi-agent-guide",
"version": "1.0.0", "version": "2.0.0",
"description": "Multi-agent collaboration framework for complex projects. Sets up agent hierarchies, ownership rules, guardrails, handoff protocols, and CI/CD integration for Claude, Gemini, Codex, and Human agents working together.", "description": "Multi-agent collaboration framework for complex projects. Sets up agent hierarchies, ownership rules, guardrails, handoff protocols, and CI/CD integration for Claude, Gemini, Codex, and Human agents working together. v2.0 includes consolidated MULTI_AGENT_FRAMEWORK.md template and quick-setup command.",
"author": { "author": {
"name": "OurDigital", "name": "OurDigital",
"email": "ourdigital@example.com" "email": "ourdigital@example.com"
@@ -12,7 +12,21 @@
"guardrails", "guardrails",
"ownership", "ownership",
"ci-cd", "ci-cd",
"project-management" "project-management",
"framework",
"claude",
"gemini",
"codex"
], ],
"license": "MIT" "license": "MIT",
"commands": [
{
"name": "multi-agent-setup",
"description": "Quick setup for multi-agent collaboration"
},
{
"name": "setup-agents",
"description": "Full interactive multi-agent setup"
}
]
} }

20
custom-skills/91-multi-agent-guide/README.md
View File

@@ -1,7 +1,13 @@
# Multi-Agent Guide Plugin # Multi-Agent Guide Plugin v2.0
A Claude Code plugin for setting up multi-agent collaboration frameworks in complex software projects. A Claude Code plugin for setting up multi-agent collaboration frameworks in complex software projects.
## What's New in v2.0
- **Consolidated Framework**: Single `MULTI_AGENT_FRAMEWORK.md` (~250 lines vs ~2,400)
- **Quick Setup**: `/multi-agent-setup` command for rapid deployment
- **Production-Tested**: Based on dintel-data-agent and our-seo-agent
## Overview ## Overview
This plugin helps you establish a structured collaboration framework for projects where multiple AI agents (Claude Code, Gemini, Codex, and Human) work together. It provides: This plugin helps you establish a structured collaboration framework for projects where multiple AI agents (Claude Code, Gemini, Codex, and Human) work together. It provides:
@@ -46,15 +52,19 @@ The skill activates automatically when you mention:
- "multi-agent guide" - "multi-agent guide"
- "agent coordination" - "agent coordination"
### Explicit Command ### Explicit Commands
Use the slash command: **Quick Setup (Recommended):**
```
/multi-agent-setup
```
Rapid deployment with minimal questions. Creates consolidated framework.
**Full Setup:**
``` ```
/setup-agents /setup-agents
``` ```
Interactive setup with full customization options.
This will guide you through the complete setup process interactively.
## What Gets Created ## What Gets Created

95
custom-skills/91-multi-agent-guide/commands/quick-setup.md Normal file
View File

@@ -0,0 +1,95 @@
---
name: multi-agent-setup
description: Quick setup for multi-agent collaboration using the consolidated framework
---
# Quick Multi-Agent Setup
You are setting up multi-agent collaboration using the consolidated MULTI_AGENT_FRAMEWORK.md template.
## Your Task
Perform a rapid setup with minimal questions:
### Step 1: Quick Assessment
Check the project structure:
```bash
ls -la
ls src/ 2>/dev/null || ls lib/ 2>/dev/null || echo "No src directory"
```
### Step 2: Ask ONE Question
Use AskUserQuestion to ask:
```
Which agents will participate in this project?
- Claude + Gemini + Codex (Full team)
- Claude + Codex (Dev focused)
- Claude + Gemini (Research focused)
- Claude only (Solo with guidelines)
```
### Step 3: Create Files
Based on the answer, create these files:
**Always create:**
```
.agent-state/tasks.yaml
.agent-state/locks.yaml
MULTI_AGENT_FRAMEWORK.md ← Use template from skill
tools/check-ownership.py
```
**If Gemini included:**
```
GEMINI.md
```
**If Codex included:**
```
CODEX.md
```
### Step 4: Customize Framework
In MULTI_AGENT_FRAMEWORK.md:
1. Replace `{{PROJECT_NAME}}` with actual project name
2. Replace `{{DATE}}` with current date
3. Adjust ownership matrix based on project structure
### Step 5: Summary
Output a concise summary:
```markdown
## Multi-Agent Framework Installed
**Files Created:**
- `.agent-state/tasks.yaml`
- `.agent-state/locks.yaml`
- `MULTI_AGENT_FRAMEWORK.md`
- `tools/check-ownership.py`
- [Additional agent files if created]
**Next Steps:**
1. Set agent identity: `export AGENT_AUTHOR=claude`
2. Review ownership matrix in `MULTI_AGENT_FRAMEWORK.md`
3. Start using `[Agent] type(scope): message` commit format
**Commands:**
- Check ownership: `python tools/check-ownership.py <file>`
- View tasks: `cat .agent-state/tasks.yaml`
- View locks: `cat .agent-state/locks.yaml`
```
## Template Location
Use the consolidated framework template from:
`${SKILL_DIR}/templates/multi-agent-framework.md`
## Key Principle
**Speed over completeness** - Get the framework running quickly. Users can customize later.

34
custom-skills/91-multi-agent-guide/skills/multi-agent-guide/SKILL.md
View File

@@ -1,7 +1,7 @@
--- ---
name: multi-agent-guide name: multi-agent-guide
description: Use when user asks to "set up multi-agent collaboration", "initialize multi-agent project", "create agent guardrails", "set up team AI collaboration", "configure agent ownership rules", "create agent handoff protocols", mentions "multi-agent guide", "multi-agent setup", "agent coordination", "AI agent collaboration", or wants to configure a project for multiple AI agents (Claude, Gemini, Codex) working together with proper ownership rules, task management, and CI/CD integration. description: Use when user asks to "set up multi-agent collaboration", "initialize multi-agent project", "create agent guardrails", "set up team AI collaboration", "configure agent ownership rules", "create agent handoff protocols", mentions "multi-agent guide", "multi-agent setup", "agent coordination", "AI agent collaboration", or wants to configure a project for multiple AI agents (Claude, Gemini, Codex) working together with proper ownership rules, task management, and CI/CD integration.
version: 1.0.0 version: 2.0.0
allowed-tools: Read, Glob, Grep, Write, Edit, Bash, AskUserQuestion allowed-tools: Read, Glob, Grep, Write, Edit, Bash, AskUserQuestion
--- ---
@@ -9,6 +9,24 @@ allowed-tools: Read, Glob, Grep, Write, Edit, Bash, AskUserQuestion
This skill helps you set up a comprehensive multi-agent collaboration framework for complex software projects where multiple AI agents (Claude Code, Gemini, Codex, and Human) work together. This skill helps you set up a comprehensive multi-agent collaboration framework for complex software projects where multiple AI agents (Claude Code, Gemini, Codex, and Human) work together.
## What's New in v2.0
| Feature | Description |
|---------|-------------|
| **Consolidated Framework** | Single `MULTI_AGENT_FRAMEWORK.md` (~250 lines vs ~2,400 in separate files) |
| **Quick Setup Command** | `/multi-agent-setup` for rapid deployment |
| **Simplified Templates** | One unified template instead of 5 separate files |
| **Production-Tested** | Based on dintel-data-agent and our-seo-agent implementations |
## Quick Start
For rapid setup, use:
```
/multi-agent-setup
```
This creates the essential files in under 2 minutes.
## Overview ## Overview
The multi-agent setup creates: The multi-agent setup creates:
@@ -371,8 +389,9 @@ Supporting files in this skill:
| File | Purpose | | File | Purpose |
|------|---------| |------|---------|
| `templates/agents-md.md` | AGENTS.md template | | `templates/multi-agent-framework.md` | **Consolidated framework (RECOMMENDED)** |
| `templates/guardrails-md.md` | GUARDRAILS.md template | | `templates/agents-md.md` | AGENTS.md template (legacy) |
| `templates/guardrails-md.md` | GUARDRAILS.md template (legacy) |
| `templates/claude-md.md` | CLAUDE.md template | | `templates/claude-md.md` | CLAUDE.md template |
| `templates/gemini-md.md` | GEMINI.md template | | `templates/gemini-md.md` | GEMINI.md template |
| `templates/codex-md.md` | CODEX.md template | | `templates/codex-md.md` | CODEX.md template |
@@ -383,6 +402,15 @@ Supporting files in this skill:
| `examples/minimal-setup/` | Minimal 2-agent setup example | | `examples/minimal-setup/` | Minimal 2-agent setup example |
| `examples/full-setup/` | Full 3-agent setup example | | `examples/full-setup/` | Full 3-agent setup example |
### Template Selection Guide
| Use Case | Template |
|----------|----------|
| New projects | `multi-agent-framework.md` (consolidated) |
| Existing projects with separate files | Keep existing AGENTS.md + GUARDRAILS.md |
| Quick setup | `/multi-agent-setup` command |
| Full customization | Individual templates (agents-md, guardrails-md, etc.) |
--- ---
## Commands ## Commands

256
custom-skills/91-multi-agent-guide/skills/multi-agent-guide/templates/multi-agent-framework.md Normal file
View File

@@ -0,0 +1,256 @@
# Multi-Agent Development Framework
**Version:** 1.0
**Applies to:** {{PROJECT_NAME}}
**Last Updated:** {{DATE}}
---
## 1. Agent Hierarchy
```
Human (Final Authority)
│
▼
┌─────────────┐
│ Claude Code │ ← Lead Agent
│ Orchestrator│
└──────┬──────┘
│
┌─────────────────┼─────────────────┐
▼ ▼ ▼
┌─────────┐ ┌─────────┐ ┌─────────┐
│ Gemini │ │ Codex │ │ Human │
│Research │ │ Speed │ │ Approve │
└─────────┘ └─────────┘ └─────────┘
```
| Agent | Role | Scope |
|-------|------|-------|
| **Claude** | Lead / Orchestrator | Architecture, core logic, integration, git, final review |
| **Gemini** | Sub-agent | Google APIs, documentation, research, visualization |
| **Codex** | Sub-agent | Tests, boilerplate, models, docstrings, utilities |
| **Human** | Authority | Business decisions, priorities, release approval |
---
## 2. File Ownership
### 2.1 Standard Ownership Matrix
| Pattern | Owner | Examples |
|---------|-------|----------|
| `src/*/core/`, `src/*/services/` | Claude | Business logic, orchestration |
| `src/*/api/`, `src/*/mcp/` | Claude | API clients, MCP servers |
| `src/*/connectors/` | Claude | Data source integrations |
| `src/*/visualization/`, `src/*/app/` | Gemini | Dashboards, charts |
| `docs/*.md` | Gemini | User documentation |
| `tests/` | Codex | All test files |
| `src/*/utils/`, `src/*/models.py` | Codex | Utilities, Pydantic models |
### 2.2 Shared Files (Require Claude Approval)
| Files | Rule |
|-------|------|
| `pyproject.toml`, `requirements*.txt` | Claude approves dependency changes |
| `.github/workflows/` | Claude approves CI/CD changes |
| `CLAUDE.md`, `AGENTS.md`, `GUARDRAILS.md` | Claude only |
| `PROJECT_PLAN.md` | Human approves roadmap changes |
### 2.3 Unrestricted Files
Any agent can modify: `.agent-state/*`, `.gitignore`, `README.md`
---
## 3. State Management
All state tracked in `.agent-state/` directory:
```
.agent-state/
├── tasks.yaml # Task registry
└── locks.yaml # File locks
```
### 3.1 Task Entry
```yaml
tasks:
- id: "TASK-001"
agent: "codex"
status: "in_progress" # pending | in_progress | completed | abandoned | blocked
description: "Add unit tests for crawler"
files: ["tests/test_crawler.py"]
claimed_at: "{{DATE}}T10:00:00Z"
expires_at: "{{DATE}}T22:00:00Z"
```
### 3.2 Lock Entry
```yaml
locks:
- path: "src/crawler.py"
agent: "claude"
task_id: "TASK-001"
lock_type: "exclusive" # exclusive | shared | override
expires_at: "{{DATE}}T22:00:00Z"
```
### 3.3 Expiration Rules
| Scenario | Duration |
|----------|----------|
| Standard task | 12 hours |
| Complex refactoring | 24 hours |
| Emergency fix | 4 hours |
| Override (Claude) | 4 hours |
---
## 4. Workflow
### 4.1 Task Claiming
```bash
# 1. Set identity
export AGENT_AUTHOR=codex
# 2. Check state
cat .agent-state/tasks.yaml
cat .agent-state/locks.yaml
# 3. Claim task (add to tasks.yaml)
git commit -m "[Codex] chore: claim TASK-001"
# 4. Do work, then commit
git commit -m "[Codex] test(crawler): add unit tests"
# 5. Complete (update status, remove locks)
git commit -m "[Codex] chore: complete TASK-001"
```
### 4.2 Conflict Resolution
```
1. Ownership Matrix → Owner has priority
↓
2. Active Locks → Lock holder has priority
↓
3. Task Assignment → Assigned agent has priority
↓
4. Escalate to Claude → Final decision
```
---
## 5. Handoff Protocols
### 5.1 Claude → Sub-agent
```markdown
## Task for [Gemini/Codex]
**Type:** [API | Docs | Tests | Models]
**Priority:** [High | Medium | Low]
### Objective
[What needs to be done]
### Deliverables
- [ ] Implementation
- [ ] Tests (if applicable)
- [ ] Documentation update
```
### 5.2 Sub-agent → Claude (Escalation)
```markdown
## Escalation to Claude
**Reason:** [Architecture | Integration | Security | Complexity]
### Completed
[What was finished]
### Blocking Issue
[What needs Claude's decision]
```
---
## 6. Commit Standards
### 6.1 Format
```
[Agent] type(scope): description
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
```
### 6.2 Types & Tags
| Type | Purpose | Agent Tags |
|------|---------|------------|
| `feat` | New feature | `[Claude]` |
| `fix` | Bug fix | `[Gemini]` |
| `docs` | Documentation | `[Codex]` |
| `test` | Tests | `[Human]` |
| `refactor` | Refactoring | `[CI]` |
| `chore` | Maintenance | |
---
## 7. Quality Gates
### 7.1 Pre-merge Checklist
- [ ] Tests pass (`pytest`)
- [ ] Code quality passes (`black`, `isort`, `flake8`, `mypy`)
- [ ] Ownership check passes
- [ ] No hardcoded secrets
- [ ] Documentation updated
- [ ] Agent attribution in commits
### 7.2 Coverage Targets
| Scope | Minimum | Target |
|-------|---------|--------|
| Overall | 70% | 80% |
| Core modules | 80% | 90% |
| New code | 80% | 100% |
---
## 8. Quick Reference
### Environment Setup
```bash
export AGENT_AUTHOR=claude # claude | gemini | codex | human
pip install -e ".[dev]"
pre-commit install
```
### Ownership Lookup
```
Core logic, APIs, services → Claude
Visualization, dashboards → Gemini
Documentation → Gemini
Tests, fixtures → Codex
Utilities, models → Codex
Dependencies, CI/CD → Shared (Claude approves)
```
### Escalation Triggers
- Architectural decisions needed
- Multi-file integration required
- Security concerns
- Performance optimization
---
*Generated by Multi-Agent Guide Skill v2.0*

0
custom-skills/AUDIT_REPORT.md → custom-skills/99_archive/doc/AUDIT_REPORT.md
View File

0
custom-skills/99_archive/REFACTORING_PLAN.md → custom-skills/99_archive/doc/REFACTORING_PLAN.md
View File

571
custom-skills/OUR_SKILL_PROJECT_PLAN_v1.1.md
View File

@@ -1,571 +0,0 @@
# OurDigital Custom Claude Skill Project Plan
> **Version**: 1.1
> **Created**: 2026-01-31
> **Updated**: 2026-01-31
> **Author**: OurDigital (Andrew Yim)
> **Purpose**: Claude Desktop & Claude Code 기반 맞춤 Claude Skill 패키지 구현 가이드
---
## 1. Background
### 1.1 OurDigital 프로필
**OurDigital**은 D.intelligence의 Entrepreneur **Andrew Yim**의 개인 활동 프로필이다.
| 구분 | 내용 |
|------|------|
| **사업 영역** | Data Analysis, Data Analytics, Google Tag Manager, Data Intelligence Service |
| **컨설팅 서비스** | SMB 영역 종합 컨설팅, 코칭 서비스 (OurDigital Lab 운영) |
| **블로그 채널** | blog.ourdigital.org (Korean), journal.ourdigital.org (English), ourstory.day (Personal Essays) |
### 1.2 활동 영역
- **SEO Specialist**: Technical SEO, On-page SEO, AEO/GEO, Brand Visibility Audit
- **Brand Marketing Consultant**: 브랜드 마케팅, 콘텐츠 마케팅, 디지털 마케팅, 로컬 마케팅
- **Data Analyst**: 데이터 분석, 마케팅 자동화, GTM 관리
- **AI/Data Literacy Evangelist**: AI 리터러시, 데이터 리터러시 교육 및 전파
### 1.3 프로젝트 목적
OurDigital의 전문화된 맞춤 목적 도구를 **Claude Skill 패키지**로 구현하여:
1. 반복적인 워크플로우의 효율화
2. 일관된 브랜드 보이스와 품질 유지
3. 외부 AI 도구(Perplexity, Gemini, DALL-E 등)와의 효과적인 협업
4. 도메인 특화 지식의 체계적 관리
5. Claude Desktop과 Claude Code 환경 모두에서 일관된 운용
---
## 2. Requirements
### 2.1 Claude Skill 적합성 기준
Anthropic의 Agent Skills 가이드 및 skill-creator 프레임워크에 따른 적합성 기준:
| 기준 | 설명 |
|------|------|
| **명확한 트리거** | "언제 이 스킬을 사용할지"가 분명해야 함 |
| **집중된 범위** | Unix 철학: 1-3가지 핵심 기능에 집중 (800-1,200 words) |
| **재사용 가능한 리소스** | scripts/, references/, assets/로 번들할 가치 |
| **Claude가 모르는 지식** | 절차적 지식, 도메인 특화 정보, 조직 고유 맥락 |
| **명확한 경계** | 다른 스킬과 중복 없이 독립적 작동 |
### 2.2 OurDigital 스킬 트리거 규칙 ⭐ NEW
**중요**: 다른 범용 스킬과의 충돌 방지를 위해, ourdigital 스킬은 반드시 `ourdigital` 키워드가 포함된 경우에만 트리거된다.
| 트리거 패턴 | 예시 |
|------------|------|
| **명시적 호출** | "ourdigital 블로그 작성해줘", "ourdigital research 프롬프트" |
| **스킬명 직접 호출** | "ourdigital-blog로 초안 작성", "ourdigital-designer 사용" |
| **OurDigital 컨텍스트** | "OurDigital 브랜드 가이드 확인", "ourdigital 스킬 만들어줘" |
**트리거되지 않는 경우**: "블로그 써줘", "리서치 해줘" (일반 요청은 범용 스킬 또는 Claude 기본 기능 사용)
### 2.3 Progressive Disclosure 설계 원칙
```
Level 1: Metadata (name + description) - 항상 컨텍스트에 로드 (~100 words)
Level 2: SKILL.md body - 스킬 트리거 시 로드 (<5k words, 권장 <2k words)
Level 3: Bundled resources - 필요 시 Claude가 로드 (Unlimited)
```
### 2.4 YAML Frontmatter 규약 ⭐ NEW
Anthropic Claude Skill 권장 규약에 따른 메타데이터 표준:
```yaml
---
name: ourdigital-skill-name
description: |
[트리거 조건 명시] ourdigital 키워드와 함께 사용 시 활성화.
[핵심 기능 1줄 요약]
Triggers:
- "ourdigital [keyword1]", "ourdigital [keyword2]"
- "ourdigital-skill-name [action]"
Features:
- 기능 1
- 기능 2
version: "1.0"
author: OurDigital
environment: Desktop | Code | Both
dependencies:
python: ">=3.11"
packages: ["package1", "package2"]
---
```
### 2.5 스킬 디렉토리 표준 구조 ⭐ UPDATED
```
ourdigital-skill-name/
├── Desktop/ # Claude Desktop 버전
│ ├── SKILL.md # Desktop용 스킬 정의
│ ├── scripts/ # Desktop 환경용 스크립트
│ ├── references/ # 참조 문서
│ └── assets/ # 템플릿, 이미지 등
│
├── Code/ # Claude Code 버전
│ ├── SKILL.md # Code용 스킬 정의
│ ├── scripts/ # Code 환경용 스크립트
│ ├── references/ # 참조 문서
│ └── assets/ # 템플릿, 이미지 등
│
├── shared/ # 공통 리소스
│ ├── references/ # 공통 참조 문서
│ ├── assets/ # 공통 에셋
│ └── templates/ # 공통 템플릿
│
├── docs/ # 문서화 ⭐ NEW
│ ├── CHANGELOG.md # 변경 이력
│ ├── SETUP.md # 설치/설정 가이드
│ └── logs/ # 업데이트 로그 파일
│
└── README.md # 스킬 개요
```
---
## 3. Package Environment Standards ⭐ NEW
### 3.1 공통 환경 요건
OurDigital 스킬 패키지는 일관된 환경에서 운용되도록 다음 표준을 따른다:
| 항목 | 표준 | 비고 |
|------|------|------|
| **Python 버전** | >= 3.11 | pyenv 또는 conda로 관리 |
| **가상 환경** | `.venv-ourdigital/` | 프로젝트 루트에 위치 |
| **환경 변수 파일** | `.env.ourdigital` | 민감 정보 포함, .gitignore 등록 |
| **설정 파일** | `config/ourdigital.yaml` | 스킬 공통 설정 |
### 3.2 인증 및 자격증명 관리
```
~/.ourdigital/
├── credentials/
│ ├── notion.json # Notion API 토큰
│ ├── ghost.json # Ghost Admin API 키
│ ├── google.json # Google API 자격증명
│ └── figma.json # Figma API 토큰
├── config.yaml # 전역 설정
└── .env # 환경 변수 (심볼릭 링크)
```
### 3.3 환경 변수 표준
```bash
# .env.ourdigital
OURDIGITAL_ENV=development|production
OURDIGITAL_CONFIG_PATH=~/.ourdigital/config.yaml
OURDIGITAL_CREDENTIALS_PATH=~/.ourdigital/credentials/
# Notion
NOTION_API_TOKEN=secret_xxxxx
NOTION_WORKING_WITH_AI_DB=f8f19ede-32bd-43ac-9f60-0651f6f40afe
# Ghost CMS
GHOST_BLOG_URL=https://blog.ourdigital.org
GHOST_BLOG_ADMIN_KEY=xxxxx
GHOST_JOURNAL_URL=https://journal.ourdigital.org
GHOST_JOURNAL_ADMIN_KEY=xxxxx
```
### 3.4 패키지 의존성 관리
```
ourdigital-skills/
├── pyproject.toml # 전체 패키지 의존성
├── requirements/
│ ├── base.txt # 공통 의존성
│ ├── desktop.txt # Desktop 전용
│ └── code.txt # Code 전용
└── setup.py # 패키지 설치 스크립트
```
---
## 4. Skill Architecture
### 4.1 전체 스킬 구성 (10개)
```
┌─────────────────────────────────────────────────────────────────┐
│ META LAYER (기반 스킬) │
│ ┌─────────────────────────┐ ┌─────────────────────────────┐ │
│ │ ourdigital-skill-creator│ │ ourdigital-brand-guide │ │
│ │ (스킬 생성/관리) │ │ (브랜드 기준/스타일 가이드) │ │
│ └─────────────────────────┘ └─────────────────────────────┘ │
└─────────────────────────────────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────────────────────────────┐
│ CONTENT LAYER (콘텐츠 제작) │
│ ┌──────────────────┐ ┌──────────────────┐ ┌─────────────────┐ │
│ │ ourdigital-blog │ │ourdigital-journal│ │ourdigital- │ │
│ │ (한국어 블로그) │ │(영문 에세이) │ │research │ │
│ └──────────────────┘ └──────────────────┘ │(리서치 프롬프트) │ │
│ └─────────────────┘ │
└─────────────────────────────────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────────────────────────────┐
│ PRODUCTION LAYER (제작 지원) │
│ ┌──────────────────┐ ┌──────────────────┐ ┌─────────────────┐ │
│ │ourdigital-document│ │ourdigital-designer│ │ourdigital- │ │
│ │(문서/프레젠테이션)│ │(비주얼 프롬프트) │ │ad-manager │ │
│ └──────────────────┘ └──────────────────┘ │(광고 카피) │ │
│ └─────────────────┘ │
└─────────────────────────────────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────────────────────────────┐
│ SUPPORT LAYER (업무 지원) │
│ ┌─────────────────────────┐ ┌─────────────────────────────┐ │
│ │ ourdigital-trainer │ │ ourdigital-backoffice │ │
│ │ (교육자료/평가) │ │ (견적/계약/비용분석) │ │
│ └─────────────────────────┘ └─────────────────────────────┘ │
└─────────────────────────────────────────────────────────────────┘
```
### 4.2 개별 스킬 정의
#### 4.2.1 ourdigital-skill-creator (메타 스킬)
| 항목 | 내용 |
|------|------|
| **역할** | 스킬 적합성 평가, 인터랙티브 요구사항 분석, 스킬 제작, 이력 관리 |
| **트리거** | "ourdigital 스킬 만들기", "ourdigital skill 적합성", "ourdigital 스킬 제작" |
| **핵심 기능** | 1) 니즈의 Claude Skill 적합성 평가 2) **인터랙티브 질의-응답 기반 요구사항 정의** 3) 최적화된 스킬 생성 4) **Notion DB 이력 관리** |
| **특수 기능** | 수정 이력 관리, 학습 포인트 축적, Notion 연동 |
**인터랙티브 워크플로우** ⭐ NEW:
```
1. [니즈 파악] 사용자의 초기 요청 수신
↓
2. [적합성 검토] Claude Skill 적합성 평가 질문
↓
3. [요구사항 정의] 단계별 질의-응답 (최소 3~5개 질문)
- 스킬 목적과 핵심 기능
- 트리거 조건과 사용 시나리오
- 필요한 외부 도구/리소스
- 기대 출력 형식
- Desktop/Code 환경 요구사항
↓
4. [스킬 생성] 요구사항 기반 스킬 초안 생성
↓
5. [검증] 사용자 확인 및 피드백 반영
↓
6. [저장] Notion DB + docs/ 이력 기록
```
**번들 리소스:**
```
ourdigital-skill-creator/
├── Desktop/
│ └── SKILL.md
├── Code/
│ └── SKILL.md
├── shared/
│ ├── scripts/
│ │ ├── init_skill.py
│ │ ├── validate_skill.py
│ │ └── sync_notion.py # Notion 연동
│ ├── references/
│ │ ├── suitability-criteria.md
│ │ ├── skill-patterns.md
│ │ └── qa-templates.md # 질의 템플릿
│ └── templates/
│ └── skill-template/
├── docs/
│ ├── CHANGELOG.md
│ └── logs/
└── README.md
```
---
#### 4.2.2 ourdigital-brand-guide (기준 참조 스킬)
| 항목 | 내용 |
|------|------|
| **역할** | 글쓰기/페르소나/시각 스타일 기준 관리, 브랜드 적합성 판별 |
| **트리거** | "ourdigital 브랜드 가이드", "ourdigital 스타일 체크", "ourdigital 톤앤매너" |
| **핵심 기능** | 1) 글쓰기 스타일 기준 2) 페르소나 특징/스타일 3) 시각 요소 기준 4) 산출물 브랜드 적합성 판별 |
---
#### 4.2.3 ourdigital-blog (콘텐츠 제작)
| 항목 | 내용 |
|------|------|
| **역할** | 한국어 블로그 초안 작성, SEO 최적화 편집 |
| **트리거** | "ourdigital 블로그", "ourdigital blog 초안", "ourdigital 한국어 포스트" |
| **핵심 기능** | 1) 블로그 초안 작성 2) SEO 메타데이터 생성 3) Ghost CMS 포맷 |
| **출력 채널** | blog.ourdigital.org (Ghost CMS) |
---
#### 4.2.4 ourdigital-journal (콘텐츠 제작)
| 항목 | 내용 |
|------|------|
| **역할** | 영문 에세이/리서치 작성 및 포스팅 |
| **트리거** | "ourdigital journal", "ourdigital 영문 에세이", "ourdigital English article" |
| **핵심 기능** | 1) 영문 에세이 작성 2) 리서치 기반 아티클 3) 학술적 글쓰기 스타일 |
| **출력 채널** | journal.ourdigital.org (Ghost CMS) |
---
#### 4.2.5 ourdigital-research (프롬프트 엔지니어링)
| 항목 | 내용 |
|------|------|
| **역할** | Deep Research용 구조화된 프롬프트 생성 |
| **트리거** | "ourdigital research 프롬프트", "ourdigital deep research", "ourdigital 조사 요청" |
| **핵심 기능** | 1) 조사 목적/용도 확인 대화 2) 구조화된 리서치 프롬프트 생성 3) 외부 도구 최적화 |
---
#### 4.2.6 ourdigital-document (문서 제작)
| 항목 | 내용 |
|------|------|
| **역할** | 문서 구성/초안 작성, 프레젠테이션 프롬프트 생성 |
| **트리거** | "ourdigital 문서", "ourdigital 기획서", "ourdigital 프레젠테이션" |
| **핵심 기능** | 1) 문서 구성 및 개요 2) Word/Google Doc/Markdown 초안 3) Gamma/Figma용 프롬프트 |
---
#### 4.2.7 ourdigital-designer (프롬프트 엔지니어링)
| 항목 | 내용 |
|------|------|
| **역할** | Visual AI용 구조화된 프롬프트 생성, Figma 연동 |
| **트리거** | "ourdigital 디자인", "ourdigital 비주얼", "ourdigital 이미지 생성" |
| **핵심 기능** | 1) 디자인 방향 설정 2) AI 이미지 생성 프롬프트 3) Figma Connector 연동 |
---
#### 4.2.8 ourdigital-ad-manager (마케팅 실행)
| 항목 | 내용 |
|------|------|
| **역할** | 광고 카피라이팅, 키워드 검색량 조사 |
| **트리거** | "ourdigital 광고 카피", "ourdigital 검색 광고", "ourdigital 키워드" |
| **핵심 기능** | 1) 검색 광고 카피 2) 디스플레이 광고 카피 3) 브랜디드 콘텐츠 4) 키워드 검색량 웹 서치 |
---
#### 4.2.9 ourdigital-trainer (교육 지원)
| 항목 | 내용 |
|------|------|
| **역할** | 교육자료 구성, 진행 계획, 참여자 평가 |
| **트리거** | "ourdigital 교육", "ourdigital 트레이닝", "ourdigital 워크샵" |
| **핵심 기능** | 1) 주제별 교육자료 구성 2) 교육 진행 계획 3) 참여자 평가 설계 |
---
#### 4.2.10 ourdigital-backoffice (업무 지원)
| 항목 | 내용 |
|------|------|
| **역할** | 견적서, 서비스 소개서, 계약서, 비용 분석 |
| **트리거** | "ourdigital 견적서", "ourdigital 계약서", "ourdigital 비용 분석" |
| **핵심 기능** | 1) 견적서 작성 2) 서비스 소개서 3) 계약서 초안 (법적 검토 필요 명시) 4) 비용 분석 |
---
## 5. Development History Management ⭐ NEW
### 5.1 Notion Database 연동
**대상 데이터베이스**: [Working with AI](https://www.notion.so/dintelligence/f529bd7b67ce4033bb70ce951d65c9e8)
| 필드 | 용도 |
|------|------|
| **Name** | 스킬명 + 버전 (예: "ourdigital-blog v1.2") |
| **Type** | "Skill Development" |
| **Category** | "OurDigital Skills" |
| **AI used** | "Claude Opus" 또는 "Claude Code" |
| **Topic** | 해당 스킬 카테고리 |
**저장 시점**:
- 스킬 신규 생성 시
- 스킬 수정/업데이트 시
- 버전 릴리즈 시
### 5.2 로컬 문서 관리
각 스킬의 `docs/` 디렉토리에 다음 파일 유지:
```markdown
# docs/CHANGELOG.md
## [1.1.0] - 2026-01-31
### Added
- 새로운 기능 설명
### Changed
- 변경된 기능 설명
### Fixed
- 수정된 버그 설명
### Notion Ref
- https://notion.so/page-id
```
```markdown
# docs/logs/2026-01-31-update.md
## 업데이트 정보
- **일시**: 2026-01-31 15:30 KST
- **버전**: 1.0 → 1.1
- **작업자**: Andrew Yim
- **Claude 세션**: [링크]
## 변경 내용
...
## Notion 동기화
- DB 레코드 ID: xxx
- 동기화 시간: 2026-01-31 15:35 KST
```
---
## 6. Implementation Plan
### 6.1 구현 단계
```
Phase 1: 기반 스킬 (Week 1-2)
├── ourdigital-skill-creator (Notion 연동 포함)
└── ourdigital-brand-guide
Phase 2: 핵심 콘텐츠 스킬 (Week 3-4)
├── ourdigital-blog
├── ourdigital-journal
└── ourdigital-research
Phase 3: 제작 지원 스킬 (Week 5-6)
├── ourdigital-document
├── ourdigital-designer
└── ourdigital-ad-manager
Phase 4: 업무 지원 스킬 (Week 7-8)
├── ourdigital-trainer
└── ourdigital-backoffice
```
### 6.2 Phase 1 상세 계획
#### Task 1.1: ourdigital-skill-creator 구현
| 단계 | 작업 | 산출물 |
|------|------|--------|
| 1 | 디렉토리 구조 생성 (Desktop/Code 분리) | `/ourdigital-skill-creator/` |
| 2 | Desktop용 SKILL.md 작성 | `Desktop/SKILL.md` |
| 3 | Code용 SKILL.md 작성 | `Code/SKILL.md` |
| 4 | 인터랙티브 Q&A 템플릿 | `shared/references/qa-templates.md` |
| 5 | Notion 동기화 스크립트 | `shared/scripts/sync_notion.py` |
| 6 | 공통 환경 설정 | `pyproject.toml`, `.env.ourdigital` |
| 7 | 검증 및 테스트 | 실제 스킬 생성 테스트 |
### 6.3 Claude Code 실행 가이드
```bash
# 프로젝트 루트 설정
cd /path/to/ourdigital-skills
# 가상 환경 생성
python -m venv .venv-ourdigital
source .venv-ourdigital/bin/activate
# 의존성 설치
pip install -r requirements/base.txt
# Phase 1 실행 (Claude Code)
claude "OUR_SKILL_PROJECT_PLAN.md를 참조하여 ourdigital-skill-creator 스킬을 구현해줘. Code 버전으로 시작해줘."
# 스킬 검증
python shared/scripts/validate_skill.py ourdigital-skill-creator
# Notion 동기화
python shared/scripts/sync_notion.py ourdigital-skill-creator --action=create
```
---
## 7. Quality Checklist
### 7.1 스킬 완성도 체크리스트
각 스킬 구현 완료 시 확인:
- [ ] Desktop/SKILL.md 완성 (frontmatter 규약 준수)
- [ ] Code/SKILL.md 완성 (frontmatter 규약 준수)
- [ ] description에 `ourdigital` 트리거 키워드 포함
- [ ] SKILL.md body 800-1,200 words 이내
- [ ] shared/ 공통 리소스 완성
- [ ] docs/CHANGELOG.md 초기화
- [ ] 환경 변수 문서화 (docs/SETUP.md)
- [ ] 실제 사용 시나리오 테스트
- [ ] Notion DB 레코드 생성
### 7.2 스킬 간 의존성 확인
```
ourdigital-skill-creator ──┬── 모든 스킬 생성/관리/이력 관리
│
ourdigital-brand-guide ────┼── 모든 산출물 품질 기준
│
ourdigital-blog ───────────┼── ourdigital-research (리서치 프롬프트)
│ ourdigital-designer (피처드 이미지)
│
ourdigital-document ───────┼── ourdigital-brand-guide (브랜드 적합성)
│ ourdigital-designer (프레젠테이션 비주얼)
```
---
## 8. Appendix
### 8.1 참조 문서
| 문서 | 위치 | 용도 |
|------|------|------|
| Anthropic Agent Skills | `/mnt/project/02-agent-skills.md` | 스킬 설계 원칙 |
| skill-creator | `/mnt/skills/examples/skill-creator/` | 기본 스킬 생성 프레임워크 |
| jamie-journal-editor | `/mnt/skills/user/jamie-journal-editor/` | 참조 패턴 (유사 블로그 에디터) |
| ourdigital-research-publisher | `/mnt/skills/user/ourdigital-research-publisher/` | 기존 리서치 스킬 |
### 8.2 외부 도구 연동
| 도구 | 연동 방식 | 관련 스킬 |
|------|----------|----------|
| Ghost CMS | API / Admin | ourdigital-blog, ourdigital-journal |
| Notion | MCP Connector + API | 전체 (문서 저장, 이력 관리) |
| Perplexity | 프롬프트 생성 → 수동 실행 | ourdigital-research |
| Gamma | 프롬프트 생성 → MCP | ourdigital-document |
| Figma | MCP Connector | ourdigital-designer |
| DALL-E/Midjourney | 프롬프트 생성 → 수동 실행 | ourdigital-designer |
### 8.3 버전 이력
| 버전 | 날짜 | 변경 내용 |
|------|------|----------|
| 1.0 | 2026-01-31 | 초기 프로젝트 계획 수립 |
| 1.1 | 2026-01-31 | 트리거 규칙 추가, Desktop/Code 분리, 환경 표준화, Notion 이력 관리 |
---
**End of Document**

232
custom-skills/_ourdigital-shared/README.md
View File

@@ -1,129 +1,155 @@
# OurDigital Skills - Shared Environment # OurDigital Shared Environment
Shared configuration, dependencies, and environment setup for all OurDigital Claude Skills. Shared configuration, dependencies, and installation tools for OurDigital Skills package.
## Quick Setup ## Quick Install
### 1. Create Virtual Environment
```bash ```bash
cd /path/to/our-claude-skills/custom-skills # Clone the repository (on new machine)
python -m venv .venv-ourdigital git clone https://github.com/ourdigital/our-claude-skills.git
source .venv-ourdigital/bin/activate # macOS/Linux cd our-claude-skills/custom-skills/_ourdigital-shared
# Run installer
./install.sh
``` ```
### 2. Install Dependencies ## Installation Options
```bash ```bash
# For Claude Code environment ./install.sh # Full interactive install
pip install -r _ourdigital-shared/requirements/code.txt ./install.sh --update # Update existing installation
./install.sh --uninstall # Remove installation
# For Claude Desktop environment ./install.sh --validate # Check installation status
pip install -r _ourdigital-shared/requirements/desktop.txt ./install.sh --skip-creds # Skip credentials setup
./install.sh --skip-venv # Skip virtual environment
# Or install as package ./install.sh --help # Show all options
pip install -e _ourdigital-shared/
``` ```
### 3. Configure Environment Variables ## What Gets Installed
```bash | Component | Location | Description |
# Copy template |-----------|----------|-------------|
cp _ourdigital-shared/.env.ourdigital.template ~/.env.ourdigital | Environment file | `~/.env.ourdigital` | API keys and secrets |
| Config directory | `~/.ourdigital/` | Configuration and credentials |
# Edit with your credentials | Virtual environment | `.venv-ourdigital/` | Python dependencies |
nano ~/.env.ourdigital
```
### 4. Set Up Credentials Directory
```bash
mkdir -p ~/.ourdigital/credentials
# Add your credential files:
# - ~/.ourdigital/credentials/notion.json
# - ~/.ourdigital/credentials/ghost.json
# - ~/.ourdigital/credentials/google.json
```
## Directory Structure ## Directory Structure
``` ```
_ourdigital-shared/ ~/.ourdigital/
├── pyproject.toml # Package configuration ├── config.yaml # Global configuration
├── .env.ourdigital.template # Environment variables template ├── credentials/ # Service account JSONs
├── requirements/ │ └── *.json
│ ├── base.txt # Common dependencies └── logs/ # Installation logs
│ ├── desktop.txt # Desktop-specific
│ └── code.txt # Code-specific ~/.env.ourdigital # Environment variables (chmod 600)
├── config/
│ └── ourdigital.yaml # Global configuration
└── README.md # This file
``` ```
## Configuration ## Manual Setup
### Environment Variables If you prefer manual setup:
Key variables in `.env.ourdigital`: ### 1. Create directories
```bash
| Variable | Description | mkdir -p ~/.ourdigital/credentials
|----------|-------------| chmod 700 ~/.ourdigital ~/.ourdigital/credentials
| `OURDIGITAL_ENV` | Environment (development/production) |
| `NOTION_API_TOKEN` | Notion integration token |
| `NOTION_WORKING_WITH_AI_DB` | Primary Notion database ID |
| `GHOST_BLOG_ADMIN_KEY` | Ghost CMS admin API key |
### Config File
`config/ourdigital.yaml` contains:
- Brand settings (name, tagline, values)
- Channel configurations
- Color palette
- Typography settings
- Skill numbering conventions
- Export paths
## Usage in Skills
### Loading Configuration
```python
import yaml
from pathlib import Path
def load_config():
config_path = Path(__file__).parent.parent / "_ourdigital-shared/config/ourdigital.yaml"
with open(config_path) as f:
return yaml.safe_load(f)
config = load_config()
print(config['brand']['tagline'])
``` ```
### Loading Environment ### 2. Copy environment template
```bash
```python cp .env.ourdigital.template ~/.env.ourdigital
from dotenv import load_dotenv chmod 600 ~/.env.ourdigital
import os
load_dotenv(os.path.expanduser("~/.env.ourdigital"))
notion_token = os.getenv("NOTION_API_TOKEN")
``` ```
## Skill Numbering ### 3. Edit credentials
```bash
nano ~/.env.ourdigital
# Add your API keys
```
| Range | Category | ### 4. Create virtual environment
|-------|----------| ```bash
| 01-09 | OurDigital Core (brand, blog, journal, research, etc.) | python3 -m venv .venv-ourdigital
| 10 | Meta (skill-creator) | source .venv-ourdigital/bin/activate
| 11-19 | SEO Tools | pip install -r requirements/base.txt
| 20-29 | GTM/Analytics Tools | ```
| 31-39 | Notion Tools |
| 40-49 | Jamie Clinic Tools |
## Version ## Credentials Required
- Package Version: 1.0.0 | Service | Variable | How to Get |
- Python Requirement: >= 3.11 |---------|----------|------------|
- Author: OurDigital (Andrew Yim) | Notion | `NOTION_API_TOKEN` | [Notion Integrations](https://www.notion.so/my-integrations) |
| Ghost Blog | `GHOST_BLOG_ADMIN_KEY` | Ghost Admin → Integrations |
| Ghost Journal | `GHOST_JOURNAL_ADMIN_KEY` | Ghost Admin → Integrations |
| Figma | `FIGMA_ACCESS_TOKEN` | [Figma Settings](https://www.figma.com/developers/api#access-tokens) |
### Using 1Password CLI
If you have 1Password CLI (`op`) installed:
```bash
# Sign in
eval $(op signin)
# Installer will auto-fetch credentials
./install.sh
```
## Validation
Check your installation status:
```bash
# Quick check
./install.sh --validate
# Detailed check
python scripts/validate_install.py --verbose
```
## Cross-Machine Sync
To sync skills to another machine:
```bash
# On new machine
git clone https://github.com/ourdigital/our-claude-skills.git
cd our-claude-skills/custom-skills/_ourdigital-shared
./install.sh
# Credentials need to be set up separately (security)
# Either use 1Password CLI or manually copy ~/.env.ourdigital
```
## Troubleshooting
### Permission denied
```bash
chmod +x install.sh
```
### Python version
```bash
# Check version (need 3.11+)
python3 --version
# Use pyenv if needed
pyenv install 3.11
pyenv local 3.11
```
### Missing credentials
```bash
# Check what's missing
python scripts/validate_install.py --verbose
```
## File Reference
| File | Purpose |
|------|---------|
| `install.sh` | Main installer script |
| `.env.ourdigital.template` | Environment template |
| `config/ourdigital.yaml` | Default configuration |
| `requirements/base.txt` | Common dependencies |
| `requirements/code.txt` | Claude Code dependencies |
| `scripts/validate_install.py` | Installation validator |

53
custom-skills/_ourdigital-shared/claude-ai-export/INSTALL-CLAUDE-AI.md Normal file
View File

@@ -0,0 +1,53 @@
# Installing OurDigital Skills in Claude.ai
## Option 1: Upload Bundle (Recommended)
1. Go to [claude.ai](https://claude.ai)
2. Create a new **Project** (e.g., "OurDigital Workspace")
3. Click **Project Knowledge** → **Add Content**
4. Upload `ourdigital-skills-bundle.md`
5. Done! Use "our" or "ourdigital" prefix to trigger skills
## Option 2: Add as Custom Instructions
1. Go to Claude.ai → **Settings** → **Custom Instructions**
2. Copy the content from `ourdigital-skills-bundle.md`
3. Paste into Custom Instructions
4. Save
## Option 3: Individual Skills
Upload only the skills you need from the `individual/` folder:
- `01-brand-guide.md`
- `02-blog.md`
- `03-journal.md`
- etc.
## Testing After Install
Try these prompts:
```
our brand guide
our blog "AI 마케팅의 미래"
our research SEO trends 2026
our 견적서 GTM 구축
```
## Files in This Export
```
claude-ai-export/
├── INSTALL-CLAUDE-AI.md # This file
├── ourdigital-skills-bundle.md # All 10 skills combined
└── individual/ # Individual skill files
├── 01-brand-guide.md
├── 02-blog.md
└── ...
```
## Updating Skills
When skills are updated:
1. Pull latest from GitHub
2. Re-upload the bundle file
3. Or regenerate with: `python scripts/export_for_claude_ai.py`

137
custom-skills/_ourdigital-shared/claude-ai-export/individual/01-brand-guide.md Normal file
View File

@@ -0,0 +1,137 @@
---
name: ourdigital-brand-guide
description: |
OurDigital brand standards and style guide.
Triggers (ourdigital or our prefix):
- "our brand guide", "our 브랜드 가이드", "our 톤앤매너"
---
# OurDigital Brand Guide
**Purpose**: Brand standards and style
**Triggers**: Use "our" or "ourdigital" prefix
---
# OurDigital Brand Guide
Reference skill for OurDigital brand standards, writing style, and visual identity.
## Activation
Activate with "ourdigital" or "our" prefix:
- "ourdigital 브랜드 가이드" / "our 브랜드 가이드"
- "ourdigital 톤앤매너 체크" / "our 톤앤매너"
- "our brand guide", "our style check"
## Brand Foundation
### Core Identity
| Element | Content |
|---------|---------|
| **Brand Name** | OurDigital Clinic |
| **Tagline** | 우리 디지털 클리닉 \| Your Digital Health Partner |
| **Mission** | 디지털 마케팅 클리닉 for SMBs, 자영업자, 프리랜서, 비영리단체 |
| **Promise** | 진단-처방-측정 가능한 성장 |
### Core Values
| 가치 | English | 클리닉 메타포 |
|------|---------|--------------|
| 데이터 중심 | Data-driven | 정밀 검사 |
| 실행 지향 | In-Action | 실행 가능한 처방 |
| 마케팅 과학 | Marketing Science | 근거 중심 의학 |
### Brand Philosophy
**"Precision + Empathy + Evidence"**
## Channel Tone Matrix
| Channel | Domain | Personality | Tone |
|---------|--------|-------------|------|
| Main Hub | ourdigital.org | Professional & Confident | Data-driven, Solution-oriented |
| Blog | blog.ourdigital.org | Analytical & Personal | Educational, Thought-provoking |
| Journal | journal.ourdigital.org | Conversational & Poetic | Reflective, Cultural Observer |
| OurStory | ourstory.day | Intimate & Reflective | Authentic, Personal Journey |
## Writing Style Characteristics
### Korean (한국어)
1. **철학-기술 융합체**: 기술 분석과 실존적 질문을 자연스럽게 결합
2. **역설 활용**: 긴장과 모순 구조로 논증 전개
3. **수사적 질문**: 선언적 권위보다 질문을 통한 참여
4. **우울한 낙관주의**: 불안과 상실을 인정하되 절망하지 않음
### English
1. **Philosophical-Technical Hybridization**: Technical content with human implications
2. **Paradox as Device**: Structure arguments around tensions
3. **Rhetorical Questions**: Interrogative engagement over authority
4. **Melancholic Optimism**: Acknowledge anxiety without despair
### Do's and Don'ts
**Do's:**
- Use paradox to structure arguments
- Ask rhetorical questions to engage readers
- Connect technical content to human implications
- Blend Korean and English naturally for technical terms
- Reference historical context and generational shifts
**Don'ts:**
- Avoid purely declarative, authoritative tone
- Don't separate technical analysis from cultural impact
- Avoid simplistic or overly optimistic narratives
- Don't provide prescriptive conclusions without exploration
## Visual Identity
### Primary Colors
| Token | Color | HEX | Usage |
|-------|-------|-----|-------|
| --d-black | D.Black | #221814 | Footer, dark backgrounds |
| --d-olive | D.Olive | #cedc00 | Primary accent, CTA buttons |
| --d-green | D.Green | #287379 | Links hover, secondary accent |
| --d-blue | D.Blue | #0075c0 | Links |
| --d-beige | D.Beige | #f2f2de | Light text on dark |
| --d-gray | D.Gray | #ebebeb | Alt backgrounds |
### Typography
- **Korean**: Noto Sans KR
- **English**: Noto Sans, Inter
- **Grid**: 12-column responsive layout
## Brand Compliance Check
When reviewing content, verify:
1. **Tone Match**: Does it match the channel's personality?
2. **Value Alignment**: Reflects Data-driven, In-Action, Marketing Science?
3. **Philosophy Check**: Precision + Empathy + Evidence present?
4. **Language Style**: Appropriate blend of Korean/English terms?
5. **Visual Consistency**: Uses approved color palette?
## Quick Reference
### Key Messages
| Use | Message |
|-----|---------|
| Tagline | 우리 디지털 클리닉 \| Your Digital Health Partner |
| Value Prop | 데이터로 진단하고, 실행으로 처방합니다 |
| Process | 진단 → 처방 → 측정 |
| Differentiator | 25년 경험의 마케팅 사이언티스트 |
### CTA Patterns
| Context | CTA |
|---------|-----|
| General | 무료 상담 신청하기 |
| SEO | SEO 진단 신청하기 |
[... see full documentation for more ...]

137
custom-skills/_ourdigital-shared/claude-ai-export/individual/02-blog.md Normal file
View File

@@ -0,0 +1,137 @@
---
name: ourdigital-blog
description: |
Korean blog draft creation for blog.ourdigital.org.
Triggers (ourdigital or our prefix):
- "our blog", "our 블로그", "our 한국어 포스트"
---
# OurDigital Blog
**Purpose**: Korean blog drafts
**Triggers**: Use "our" or "ourdigital" prefix
---
# OurDigital Blog
Korean blog draft creation skill for blog.ourdigital.org.
## Activation
Activate with "ourdigital" or "our" prefix:
- "ourdigital 블로그 써줘" / "our 블로그 써줘"
- "ourdigital blog draft" / "our blog draft"
- "our 한국어 포스트 [주제]"
## Channel Profile
| Field | Value |
|-------|-------|
| **URL** | blog.ourdigital.org |
| **Language** | Korean (전문용어 영문 병기) |
| **Tone** | Analytical & Personal, Educational |
| **Platform** | Ghost CMS |
| **Frequency** | 주 1-2회 |
| **Length** | 1,500-3,000자 |
## Workflow
### Phase 1: Topic Clarification
Ask clarifying questions (max 3):
1. **주제 확인**: 정확한 토픽이 무엇인가요?
2. **대상 독자**: 타겟 오디언스는? (마케터/개발자/경영진/일반)
3. **깊이 수준**: 개요 / 심층분석 / 실무가이드 중 어느 수준?
### Phase 2: Research (Optional)
If topic requires current information:
- Use `web_search` for latest trends/data
- Use `Notion:notion-search` for past research
- Reference internal documents if available
### Phase 3: Draft Generation
Generate blog draft following brand style:
**Structure:**
```
1. 도입부 (Hook + Context)
2. 본론 (3-5 핵심 포인트)
- 각 포인트: 주장 → 근거 → 함의
3. 결론 (Summary + 열린 질문)
```
**Writing Style:**
- 철학-기술 융합: 기술 분석 + 인간적 함의
- 역설 활용: 긴장/모순으로 논증 구조화
- 수사적 질문: 독자 참여 유도
- 우울한 낙관주의: 불안 인정, 절망 거부
**Language Rules:**
- 한글 기본, 전문용어는 영문 병기
- 예: "검색엔진최적화(SEO)"
- 문장: 복합문 허용, 상호연결된 개념 반영
- 단락: 관찰 → 분석 → 철학적 함의
### Phase 4: SEO Metadata
Generate metadata:
```yaml
title: [60자 이내, 키워드 포함]
meta_description: [155자 이내]
slug: [영문 URL slug]
tags: [3-5개 태그]
featured_image_prompt: [DALL-E/Midjourney 프롬프트]
```
### Phase 5: Output Format
**Markdown Output:**
```markdown
---
title: "포스트 제목"
meta_description: "메타 설명"
slug: "url-slug"
tags: ["tag1", "tag2"]
---
# 포스트 제목
[본문 내용]
---
*Originally drafted with Claude for OurDigital Blog*
```
## Ghost CMS Integration
Export options:
1. **Markdown file** → Ulysses → Ghost
2. **Direct API** → Ghost Admin API (if configured)
API endpoint: `GHOST_BLOG_URL` from environment
## Brand Compliance
Before finalizing, verify:
- [ ] 분석적 + 개인적 톤 유지
- [ ] 기술 내용에 인간적 함의 포함
- [ ] 수사적 질문으로 독자 참여
- [ ] 전문용어 영문 병기
- [ ] 1,500-3,000자 범위
## Quick Commands
| Command | Action |
|---------|--------|
| "ourdigital 블로그 [주제]" | Full workflow |
| "ourdigital blog SEO" | SEO metadata only |
| "ourdigital blog 편집" | Edit existing draft |
## References
[... see full documentation for more ...]

137
custom-skills/_ourdigital-shared/claude-ai-export/individual/03-journal.md Normal file
View File

@@ -0,0 +1,137 @@
---
name: ourdigital-journal
description: |
English essay creation for journal.ourdigital.org.
Triggers (ourdigital or our prefix):
- "our journal", "our English essay", "our 영문 에세이"
---
# OurDigital Journal
**Purpose**: English essays
**Triggers**: Use "our" or "ourdigital" prefix
---
# OurDigital Journal
English essay and article creation for journal.ourdigital.org.
## Activation
Activate with "ourdigital" or "our" prefix:
- "ourdigital journal" / "our journal"
- "ourdigital English essay" / "our English essay"
- "our 영문 에세이 [topic]"
- "ourdigital 영문 에세이 [주제]"
## Channel Profile
| Field | Value |
|-------|-------|
| **URL** | journal.ourdigital.org |
| **Language** | English |
| **Tone** | Conversational & Poetic, Reflective |
| **Platform** | Ghost CMS |
| **Frequency** | 월 2-4회 |
| **Length** | 1,000-2,000 words |
## Workflow
### Phase 1: Topic Exploration
Ask clarifying questions:
1. **Topic**: What specific angle interests you?
2. **Audience**: Tech professionals / General readers / Academic?
3. **Depth**: Personal reflection / Industry analysis / Cultural observation?
### Phase 2: Research (Optional)
If topic requires current context:
- Use `web_search` for recent developments
- Reference scholarly perspectives if applicable
- Draw from historical or cultural parallels
### Phase 3: Essay Generation
Generate essay following the reflective style:
**Structure:**
```
1. Opening (Evocative scene or question)
2. Exploration (3-4 interconnected observations)
3. Synthesis (Weaving threads together)
4. Closing (Open-ended reflection)
```
**Writing Style:**
- Philosophical-Technical Hybridization
- Paradox as primary rhetorical device
- Rhetorical questions for engagement
- Melancholic optimism in tone
**Distinctive Qualities:**
- Temporal awareness (historical context)
- Epistemic humility (acknowledging limits)
- Cultural bridging (Korean-global perspectives)
### Phase 4: SEO Metadata
Generate metadata:
```yaml
title: [Evocative, under 70 characters]
meta_description: [Compelling summary, 155 characters]
slug: [english-url-slug]
tags: [3-5 relevant tags]
```
### Phase 5: Output Format
**Markdown Output:**
```markdown
---
title: "Essay Title"
meta_description: "Description"
slug: "url-slug"
tags: ["tag1", "tag2"]
---
# Essay Title
[Essay content with paragraphs that flow naturally]
---
*Published in [OurDigital Journal](https://journal.ourdigital.org)*
```
## Writing Guidelines
### Voice Characteristics
| Aspect | Approach |
|--------|----------|
| Perspective | First-person reflection welcome |
| Tone | Thoughtful, observant, wondering |
| Pacing | Unhurried, allowing ideas to breathe |
| References | Cross-cultural, historical, literary |
### Sentence Craft
- Long, complex sentences reflecting interconnected ideas
- Progressive deepening: observation → analysis → implication
- Questions that invite rather than lecture
### Do's and Don'ts
**Do:**
- Blend technology with humanity
- Use paradox to illuminate tensions
- Acknowledge uncertainty gracefully
- Bridge Korean and Western perspectives
**Don't:**
- Lecture or prescribe
[... see full documentation for more ...]

137
custom-skills/_ourdigital-shared/claude-ai-export/individual/04-research.md Normal file
View File

@@ -0,0 +1,137 @@
---
name: ourdigital-research
description: |
Research workflow with paper and blog output.
Triggers (ourdigital or our prefix):
- "our research", "our 리서치", "our deep research"
---
# OurDigital Research
**Purpose**: Research prompts
**Triggers**: Use "our" or "ourdigital" prefix
---
# OurDigital Research
Transform questions into comprehensive research papers and polished blog posts for OurDigital channels.
## Activation
Activate with "ourdigital" or "our" prefix:
- "ourdigital research [topic]" / "our research [topic]"
- "our 리서치", "our deep research"
- "ourdigital 리서치 해줘"
- "ourdigital deep research on [topic]"
## Workflow Overview
```
Phase 1: Discovery → Phase 2: Research Planning → Phase 3: Deep Research
↓
Phase 4: Research Paper → Phase 5: Notion Save → Phase 6: Blog Draft
↓
Phase 7: Ulysses Export → Phase 8: Publishing Guidance
```
## Phase 1: Discovery
**Goal**: Understand user's question and refine scope.
1. Acknowledge the topic/question
2. Ask clarifying questions (max 3 per turn):
- Target audience? (전문가/일반인/마케터)
- Depth level? (개요/심층분석/실무가이드)
- Specific angles or concerns?
3. Confirm research scope before proceeding
**Output**: Clear research objective statement
## Phase 2: Research Planning
**Goal**: Create structured research instruction.
Generate research plan with:
- Primary research questions (3-5)
- Secondary questions for depth
- Suggested tools/sources:
- Web search for current info
- Google Drive for internal docs
- Notion for past research
- Amplitude for analytics data (if relevant)
- Expected deliverables
**Output**: Numbered research instruction list
## Phase 3: Deep Research
**Goal**: Execute comprehensive multi-source research.
Tools to leverage:
- `web_search` / `web_fetch`: Current information, statistics, trends
- `google_drive_search`: Internal documents, past reports
- `Notion:notion-search`: Previous research, related notes
- `conversation_search`: Past chat context
Research execution pattern:
1. Start broad (overview searches)
2. Deep dive into key subtopics
3. Find supporting data/statistics
4. Identify expert opinions and case studies
5. Cross-reference and validate
**Output**: Organized research findings with citations
## Phase 4: Research Paper (Artifact)
**Goal**: Synthesize findings into comprehensive document.
Create HTML artifact with:
```
Structure:
├── Executive Summary (핵심 요약)
├── Background & Context (배경)
├── Key Findings (주요 발견)
│ ├── Finding 1 with evidence
│ ├── Finding 2 with evidence
│ └── Finding 3 with evidence
├── Analysis & Implications (분석 및 시사점)
├── Recommendations (제언)
├── References & Sources (참고자료)
└── Appendix (부록) - if needed
```
Style: Professional, data-driven, bilingual key terms
## Phase 5: Notion Save
**Goal**: Archive research to Working with AI database.
Auto-save to Notion with:
- **Database**: Working with AI (data_source_id: f8f19ede-32bd-43ac-9f60-0651f6f40afe)
- **Properties**:
- Name: [Research topic]
- Status: "Done"
- AI used: "Claude Desktop"
- AI summary: 2-3 sentence summary
## Phase 6: Blog Draft
**Goal**: Transform research into engaging blog post.
Prompt user for channel selection:
1. blog.ourdigital.org (Korean)
2. journal.ourdigital.org (English)
3. ourstory.day (Korean, personal)
Generate draft using appropriate style guide:
- Korean channels: See `02-ourdigital-blog`
- English channels: See `03-ourdigital-journal`
## Phase 7: Ulysses Export
**Goal**: Deliver MD file for Ulysses editing.
[... see full documentation for more ...]

137
custom-skills/_ourdigital-shared/claude-ai-export/individual/05-document.md Normal file
View File

@@ -0,0 +1,137 @@
---
name: ourdigital-document
description: |
Notion-to-presentation workflow.
Triggers (ourdigital or our prefix):
- "our document", "our 발표자료", "our presentation"
---
# OurDigital Document
**Purpose**: Presentations
**Triggers**: Use "our" or "ourdigital" prefix
---
# OurDigital Document
Transform Notion research into branded presentations for OurDigital workflows.
## Activation
Activate with "ourdigital" or "our" prefix:
- "ourdigital document" / "our document"
- "ourdigital 발표자료" / "our 발표자료"
- "our presentation [topic]"
- "ourdigital presentation on [topic]"
## Workflow Overview
```
Phase 1: Research Collection → Phase 2: Content Synthesis → Phase 3: Presentation Planning
↓
Phase 4: Slide Generation → Phase 5: Brand Application → Phase 6: Export
```
## Phase 1: Research Collection
**Goal**: Extract research content from Notion.
Input sources:
- **Notion Page**: `notion://page/[ID]` - Single research document
- **Notion Database**: `notion://database/[ID]` - Collection query
- **Multiple Sources**: Comma-separated URLs for synthesis
Tools to use:
- `Notion:notion-search` - Find related content
- `Notion:notion-fetch` - Extract page content
**Output**: Structured research.json with findings
## Phase 2: Content Synthesis
**Goal**: Analyze and structure extracted content.
Processing:
1. Identify key topics and themes
2. Extract supporting data/statistics
3. Prioritize by relevance and impact
4. Generate executive summary
**Output**: synthesis.json with:
- Executive summary
- Key topics (ranked)
- Agenda items
- Supporting data points
## Phase 3: Presentation Planning
**Goal**: Create slide-by-slide structure.
Presentation types:
| Type | Slides | Focus |
|------|--------|-------|
| Executive Summary | 3-5 | High-level findings, KPIs |
| Research Report | 10-20 | Detailed methodology, data viz |
| Meeting Prep | 5-10 | Agenda-driven, decision points |
**Output**: Slide plan with:
- Title + subtitle per slide
- Content outline
- Speaker notes
- Visual suggestions
## Phase 4: Slide Generation
**Goal**: Generate presentation content.
Slide structure:
```
├── Title Slide (project name, date, author)
├── Agenda (numbered topics)
├── Content Slides (1-3 per topic)
│ ├── Key finding header
│ ├── Supporting points (3-5 bullets)
│ └── Data visualization placeholder
├── Summary Slide (key takeaways)
└── Next Steps / Q&A
```
## Phase 5: Brand Application
**Goal**: Apply OurDigital corporate styling.
Brand elements:
- **Colors**: OurDigital palette from `01-ourdigital-brand-guide`
- **Fonts**: Poppins (headings), Lora (body)
- **Logo**: Positioned per brand guidelines
- **Spacing**: Consistent margins and padding
Configuration: `shared/references/brand-config.json`
## Phase 6: Export
**Goal**: Generate final deliverable.
Output formats:
- **PowerPoint (.pptx)**: Full presentation with animations
- **Figma Slides**: Web-based collaborative format
- **HTML Preview**: Quick review before final export
Export paths:
- Desktop: `~/Downloads/presentations/`
- Figma: Via Figma API
## Quick Commands
| Command | Action |
|---------|--------|
| "ourdigital document [Notion URL]" | Full pipeline |
| "ourdigital 발표자료 만들어줘" | Korean trigger |
| "ourdigital presentation → pptx" | PowerPoint output |
| "ourdigital presentation → figma" | Figma output |
## Presentation Templates
[... see full documentation for more ...]

137
custom-skills/_ourdigital-shared/claude-ai-export/individual/06-designer.md Normal file
View File

@@ -0,0 +1,137 @@
---
name: ourdigital-designer
description: |
Visual storytelling and image prompt generation.
Triggers (ourdigital or our prefix):
- "our design", "our 썸네일", "our image prompt"
---
# OurDigital Designer
**Purpose**: Image prompts
**Triggers**: Use "our" or "ourdigital" prefix
---
# OurDigital Designer
Transform philosophical essays into sophisticated visual narratives through minimalist, conceptually rich featured images.
## Activation
Activate with "ourdigital" or "our" prefix:
- "ourdigital design" / "our design"
- "ourdigital 썸네일" / "our 썸네일"
- "our image prompt for [topic]"
## Core Philosophy
OurDigital images are visual philosophy—not illustrations but parallel texts that invite contemplation. Each image captures the essay's philosophical core through:
- **Abstract metaphors** over literal representations
- **Contemplative minimalism** with 20%+ negative space
- **Cultural fusion** of Korean-Western aesthetics
- **Emotional resonance** through color psychology
## Workflow
### Phase 1: Extract Essay Essence
Analyze the content for:
- **Core insight**: What philosophical truth?
- **Emotional tone**: What feeling to evoke?
- **Key metaphor**: What visual symbol?
### Phase 2: Select Visual Approach
| Essay Type | Visual Strategy | Color Mood |
|-----------|-----------------|------------|
| Technology | Organic-digital hybrids | Cool blues → warm accents |
| Social | Network patterns, human fragments | Desaturated → hope spots |
| Philosophy | Zen space, symbolic objects | Monochrome + single accent |
| Cultural | Layered traditions, fusion forms | Earth tones → modern hues |
### Phase 3: Generate Prompt
Build structured prompt with:
```
[Style] + [Subject] + [Composition] + [Color] + [Technical specs]
```
### Phase 4: Quality Check
✅ **Must have:**
- Captures philosophical insight
- Works at 200px thumbnail
- Timeless (2-3 year relevance)
- Cross-cultural readability
❌ **Must avoid:**
- Tech clichés (circuits, binary)
- Stock photo aesthetics
- Literal interpretations
- Trendy effects
## Quick Templates
### AI & Humanity
```
"Translucent human silhouette dissolving into crystalline data structures.
Monochrome with teal accent. Boundary dissolution between organic/digital.
1200x630px, minimalist vector style."
```
### Social Commentary
```
"Overlapping circles forming maze pattern, tiny humans in separate chambers.
Blue-gray palette, warm light leaks for hope. Subtle Korean patterns.
High negative space. 1200x630px."
```
### Digital Transformation
```
"Traditional forms metamorphosing into particle streams. Paper texture → digital grain.
Earth tones shifting to cool blues. Sacred geometry underlying.
1200x630px, contemplative mood."
```
## Visual Metaphor Shortcuts
| Concept | Visual Metaphor |
|---------|-----------------|
| Algorithm | Constellation patterns |
| Identity | Layered masks, fingerprints |
| Network | Root systems, neural paths |
| Time | Spirals, sediment layers |
| Knowledge | Light sources, growing trees |
## Color Psychology
| Mood | Palette |
|------|---------|
| Critical | Deep blue-gray + red accent |
| Hopeful | Warm amber + sky blue |
| Philosophical | Near black + off white + gold |
| Anxious | Charcoal + grey-blue + digital green |
## Technical Specs
- **Dimensions**: 1200x630px (OG standard)
- **Style**: Vector illustration + subtle textures
- **Colors**: 60-30-10 rule (dominant-secondary-accent)
- **Format**: WebP primary, JPG fallback
## Quick Commands
| Command | Action |
|---------|--------|
| "ourdigital design [topic]" | Generate image prompt |
| "ourdigital 썸네일 [주제]" | Korean trigger |
| "ourdigital visual → midjourney" | MidJourney optimized |
| "ourdigital visual → dalle" | DALL-E optimized |
## References
- `shared/references/visual-metaphors.md` - Concept dictionary
[... see full documentation for more ...]

137
custom-skills/_ourdigital-shared/claude-ai-export/individual/07-ad-manager.md Normal file
View File

@@ -0,0 +1,137 @@
---
name: ourdigital-ad-manager
description: |
Ad copywriting and keyword research.
Triggers (ourdigital or our prefix):
- "our ad copy", "our 광고 카피", "our keyword"
---
# OurDigital Ad Manager
**Purpose**: Ad copywriting
**Triggers**: Use "our" or "ourdigital" prefix
---
# OurDigital Ad Manager
Create compelling ad copy and research keywords for OurDigital marketing campaigns.
## Activation
Activate with "ourdigital" or "our" prefix:
- "ourdigital ad copy" / "our ad copy"
- "ourdigital 광고 카피" / "our 광고 카피"
- "our keyword research [topic]"
## Workflow
### Phase 1: Campaign Brief
Gather information:
- **Product/Service**: What are we advertising?
- **Target audience**: Who are we reaching?
- **Campaign goal**: Awareness, consideration, or conversion?
- **Platform**: Google, Naver, Meta, Display?
- **Budget tier**: Affects keyword competitiveness
### Phase 2: Keyword Research
For search campaigns:
1. **Seed keywords**: Core terms from brief
2. **Volume research**: Web search for search volume data
3. **Intent mapping**: Informational → Transactional
4. **Competitor analysis**: Top-ranking ad copy patterns
Tools to use:
- `web_search`: Search volume and trends
- `web_fetch`: Competitor ad copy analysis
### Phase 3: Ad Copy Creation
Generate platform-specific copy following character limits and best practices.
## Search Ad Copy
### Google Ads Format
```
Headline 1: [30 chars] - Primary keyword + value prop
Headline 2: [30 chars] - Benefit or CTA
Headline 3: [30 chars] - Differentiator
Description 1: [90 chars] - Expand on value
Description 2: [90 chars] - CTA + urgency
```
**Best Practices:**
- Include keyword in Headline 1
- Numbers and specifics increase CTR
- Test emotional vs. rational appeals
- Include pricing if competitive
### Naver Search Ad Format
```
제목: [25자] - 핵심 키워드 + 가치
설명: [45자] - 혜택 + 행동 유도
```
**Korean Ad Copy Tips:**
- 존댓말 일관성 유지
- 숫자와 구체적 혜택 강조
- 신뢰 요소 포함 (경력, 인증)
## Display Ad Copy
### Headlines by Format
| Format | Max Length | Focus |
|--------|------------|-------|
| Leaderboard | 25 chars | Brand + single benefit |
| Medium Rectangle | 30 chars | Offer + CTA |
| Responsive | 30 chars | Multiple variations |
### Copy Formula
```
[Problem Recognition] + [Solution Hint] + [CTA]
"여전히 [문제]? [해결책]으로 [결과]"
```
## Branded Content
For native advertising and sponsored content:
### OurDigital Tone
- **Authority without arrogance**: Share expertise, invite questions
- **Data-backed claims**: Statistics increase credibility
- **Subtle CTAs**: Education first, promotion second
### Content Types
| Type | Length | CTA Style |
|------|--------|-----------|
| Sponsored Article | 800-1,200 words | Soft (learn more) |
| Native Ad | 100-200 words | Medium (discover) |
| Social Sponsored | 50-100 words | Direct (get started) |
## Keyword Research Output
### Research Report Structure
```
## Keyword Analysis: [Topic]
### Primary Keywords
| Keyword | Volume | Difficulty | Intent |
|---------|--------|------------|--------|
| [kw1] | 10K | Medium | Trans |
### Long-tail Opportunities
- [keyword phrase 1]: Low competition, high intent
- [keyword phrase 2]: Rising trend
### Negative Keywords
[... see full documentation for more ...]

137
custom-skills/_ourdigital-shared/claude-ai-export/individual/08-trainer.md Normal file
View File

@@ -0,0 +1,137 @@
---
name: ourdigital-trainer
description: |
Training materials and workshop planning.
Triggers (ourdigital or our prefix):
- "our training", "our 워크샵", "our 교육"
---
# OurDigital Trainer
**Purpose**: Training materials
**Triggers**: Use "our" or "ourdigital" prefix
---
# OurDigital Trainer
Design training materials, plan workshops, and create evaluation frameworks for OurDigital education programs.
## Activation
Activate with "ourdigital" or "our" prefix:
- "ourdigital training" / "our training"
- "ourdigital 워크샵" / "our 워크샵"
- "our curriculum [subject]"
## Core Domains
OurDigital training expertise:
| Domain | Topics |
|--------|--------|
| **Data Literacy** | 데이터 리터러시, 분석 기초, 시각화 |
| **AI Literacy** | AI 활용, 프롬프트 엔지니어링, AI 윤리 |
| **Digital Marketing** | SEO, GTM, 마케팅 자동화 |
| **Brand Marketing** | 브랜드 전략, 콘텐츠 마케팅 |
## Workflow
### Phase 1: Training Needs Analysis
Gather requirements:
- **Target audience**: 직급, 경험 수준, 사전 지식
- **Learning objectives**: 교육 후 달성할 역량
- **Duration**: 시간 제약 (2시간/반일/전일/다회차)
- **Format**: 온라인/오프라인/하이브리드
- **Group size**: 참여 인원
### Phase 2: Curriculum Design
Structure the learning journey:
```
Module Structure:
├── 도입 (10-15%)
│ ├── Ice-breaker
│ ├── 학습 목표 공유
│ └── 사전 지식 확인
├── 핵심 학습 (60-70%)
│ ├── 개념 설명
│ ├── 사례 분석
│ ├── 실습 활동
│ └── 토론/질의응답
├── 심화/응용 (15-20%)
│ ├── 응용 과제
│ └── 그룹 활동
└── 마무리 (5-10%)
├── 핵심 정리
├── 평가
└── 후속 학습 안내
```
### Phase 3: Material Development
Create supporting materials:
| Material Type | Purpose |
|---------------|---------|
| 슬라이드 | 핵심 개념 전달 |
| 핸드아웃 | 참조 자료, 체크리스트 |
| 워크시트 | 실습 활동용 |
| 사례 연구 | 토론 및 분석용 |
| 퀴즈/평가지 | 학습 확인용 |
### Phase 4: Activity Design
Engagement techniques:
| Activity Type | Duration | Purpose |
|---------------|----------|---------|
| Think-Pair-Share | 5-10분 | 개별 사고 → 협력 |
| Case Study | 20-30분 | 실제 적용력 |
| Role Play | 15-20분 | 경험적 학습 |
| Gallery Walk | 15분 | 아이디어 공유 |
| Fishbowl | 20-30분 | 심층 토론 |
### Phase 5: Evaluation Design
Assessment framework:
| Level | What to Measure | Method |
|-------|-----------------|--------|
| 반응 | 만족도, 참여도 | 설문조사 |
| 학습 | 지식 습득 | 퀴즈, 테스트 |
| 행동 | 현업 적용 | 관찰, 피드백 |
| 결과 | 성과 개선 | KPI 측정 |
## Training Templates
### 2-Hour Workshop
```
00:00-00:10 도입 및 Ice-breaker
00:10-00:20 학습 목표 및 아젠다
00:20-00:50 핵심 개념 1
00:50-01:00 휴식
01:00-01:30 핵심 개념 2 + 실습
01:30-01:50 그룹 활동/토론
01:50-02:00 정리 및 Q&A
```
### Half-Day (4 Hours)
```
09:00-09:20 도입 및 네트워킹
09:20-10:20 모듈 1: 기초 개념
10:20-10:30 휴식
10:30-11:30 모듈 2: 심화 학습
11:30-12:00 실습 세션
12:00-12:30 사례 연구
12:30-13:00 정리, 평가, Q&A
```
### Full-Day (8 Hours)
[... see full documentation for more ...]

137
custom-skills/_ourdigital-shared/claude-ai-export/individual/09-backoffice.md Normal file
View File

@@ -0,0 +1,137 @@
---
name: ourdigital-backoffice
description: |
Business documents for consulting services.
Triggers (ourdigital or our prefix):
- "our 견적서", "our proposal", "our quote"
---
# OurDigital Backoffice
**Purpose**: Business documents
**Triggers**: Use "our" or "ourdigital" prefix
---
# OurDigital Backoffice
Create business documents for OurDigital consulting services.
## Activation
Activate with "ourdigital" or "our" prefix:
- "ourdigital 견적서" / "our 견적서"
- "ourdigital proposal" / "our proposal"
- "our cost analysis [project]"
## Important Notice
⚠️ **Legal Disclaimer**: Contract drafts require professional legal review before use. This skill provides templates and structure only.
## Document Types
### 1. Quote/Estimate (견적서)
**Purpose**: Service pricing and scope summary
**Structure:**
```
견적서 번호: OD-YYYY-NNN
발행일: YYYY-MM-DD
유효기간: 30일
1. 고객 정보
- 회사명, 담당자, 연락처
2. 서비스 개요
- 프로젝트명
- 서비스 범위 요약
3. 세부 항목
| 항목 | 상세 | 수량 | 단가 | 금액 |
|------|------|------|------|------|
4. 합계
- 소계, VAT, 총액
5. 결제 조건
- 선금/잔금 비율
- 결제 방법
6. 특이사항
- 포함/미포함 사항
```
### 2. Service Proposal (서비스 제안서)
**Purpose**: Detailed service offering and value proposition
**Structure:**
```
1. Executive Summary
- 핵심 제안 1-2문단
2. 고객 상황 이해
- 현재 과제
- 니즈 분석
3. 제안 서비스
- 서비스 범위
- 접근 방법
- 예상 산출물
4. 프로젝트 계획
- 일정표
- 마일스톤
- 체크포인트
5. 투입 리소스
- 담당자 프로필
- 역할 분담
6. 비용 및 조건
- 비용 구조
- 결제 조건
7. 기대 효과
- 예상 성과
- ROI 추정
8. 왜 OurDigital인가
- 차별점
- 관련 경험
```
### 3. Contract Draft (계약서 초안)
**Purpose**: Service agreement framework
⚠️ **반드시 법률 전문가 검토 필요**
**Structure:**
```
제1조 (목적)
제2조 (용어의 정의)
제3조 (계약 기간)
제4조 (서비스 범위)
제5조 (대금 및 지급 조건)
제6조 (권리와 의무)
제7조 (비밀유지)
제8조 (지적재산권)
제9조 (계약의 해지)
제10조 (손해배상)
제11조 (분쟁 해결)
제12조 (일반 조항)
```
### 4. Cost-Benefit Analysis (비용 분석)
**Purpose**: ROI and investment justification
**Structure:**
```
1. 프로젝트 개요
- 목적 및 범위
[... see full documentation for more ...]

137
custom-skills/_ourdigital-shared/claude-ai-export/individual/10-skill-creator.md Normal file
View File

@@ -0,0 +1,137 @@
---
name: ourdigital-skill-creator
description: |
Meta skill for creating and managing new skills.
Triggers (ourdigital or our prefix):
- "our skill create", "our 스킬 만들기"
---
# OurDigital Skill Creator
**Purpose**: Creating new skills
**Triggers**: Use "our" or "ourdigital" prefix
---
# OurDigital Skill Creator
Meta skill for creating, validating, and managing OurDigital Claude Skills.
## Activation
Activate with "ourdigital" or "our" prefix:
- "ourdigital 스킬 만들어줘" / "our 스킬 만들어줘"
- "ourdigital skill creator" / "our skill creator"
- "our skill create [name]"
Do NOT activate for generic "make a skill" requests (without our/ourdigital prefix).
## Interactive Workflow
### Phase 1: Need Assessment
When user requests a new skill:
1. **Acknowledge** the initial request
2. **Ask clarifying questions** (max 3 per turn):
- What is the core purpose?
- What triggers this skill?
- What outputs do you expect?
### Phase 2: Suitability Check
Evaluate against Claude Skill criteria:
| Criterion | Question to Ask |
|-----------|-----------------|
| Clear trigger | When exactly should this skill activate? |
| Focused scope | Can you describe 1-3 core functions? |
| Reusable resources | What scripts, templates, or references are needed? |
| Domain knowledge | What specialized knowledge does Claude lack? |
| Clear boundaries | How does this differ from existing skills? |
**Decision**: If ≥3 criteria pass → proceed. Otherwise, suggest alternatives.
### Phase 3: Requirements Definition
Guide user through structured Q&A:
```
Q1. 스킬 목적과 핵심 기능은 무엇인가요?
(What is the skill's purpose and core functions?)
Q2. 어떤 상황에서 이 스킬이 트리거되어야 하나요?
(When should this skill be triggered?)
Q3. 필요한 외부 도구나 API가 있나요?
(Any external tools or APIs needed?)
Q4. 기대하는 출력 형식은 무엇인가요?
(What output format do you expect?)
Q5. Desktop, Code, 또는 Both 환경이 필요한가요?
(Which environment: Desktop, Code, or Both?)
```
### Phase 4: Skill Generation
Generate skill structure following OurDigital standards:
```
XX-ourdigital-{skill-name}/
├── desktop/
│ └── SKILL.md # Desktop version
├── code/
│ └── SKILL.md # Code version (CLAUDE.md pattern)
├── shared/
│ ├── references/ # Common documentation
│ ├── templates/ # Shared templates
│ └── scripts/ # Utility scripts
├── docs/
│ ├── CHANGELOG.md # Version history
│ └── logs/ # Update logs
└── README.md # Overview
```
### Phase 5: Validation
Before finalizing, verify:
- [ ] YAML frontmatter includes "ourdigital" trigger keywords
- [ ] Description clearly states activation conditions
- [ ] Body content is 800-1,200 words
- [ ] shared/ resources are properly referenced
- [ ] No overlap with existing ourdigital skills
### Phase 6: Notion Sync
Record to Working with AI database:
- **Database**: f8f19ede-32bd-43ac-9f60-0651f6f40afe
- **Properties**:
- Name: `ourdigital-{skill-name} v{version}`
- Status: In progress → Done
- AI used: Claude Desktop
- AI summary: Brief skill description
## YAML Frontmatter Template
```yaml
---
name: ourdigital-{skill-name}
description: |
[Purpose summary]
Activated when user includes "ourdigital" keyword.
Triggers:
- "ourdigital {keyword1}", "ourdigital {keyword2}"
Features:
- Feature 1
- Feature 2
version: "1.0"
author: OurDigital
environment: Desktop | Code | Both
---
[... see full documentation for more ...]

336
custom-skills/_ourdigital-shared/claude-ai-export/ourdigital-skills-bundle.md Normal file
View File

@@ -0,0 +1,336 @@
---
name: ourdigital-skills-bundle
description: |
Complete OurDigital Skills package with 10 skills for brand, content, production, and business workflows.
Triggers (ourdigital or our prefix):
- "our brand", "our blog", "our journal", "our research"
- "our document", "our design", "our ad copy", "our training"
- "our 견적서", "our skill"
---
# OurDigital Skills Bundle for Claude.ai
This file contains all 10 OurDigital skills for use in Claude.ai Projects.
**Activation**: Use "ourdigital" or "our" prefix to trigger skills.
---
## 1. OurDigital Brand Guide
**Triggers**: `our brand guide`, `our 브랜드 가이드`, `our 톤앤매너`
### Brand Identity
- **Name**: OurDigital Clinic
- **Tagline**: 우리 디지털 클리닉 | Your Digital Health Partner
- **Mission**: 디지털 마케팅 클리닉 for SMBs
### Core Values
| 가치 | English | 메타포 |
|------|---------|--------|
| 데이터 중심 | Data-driven | 정밀 검사 |
| 실행 지향 | In-Action | 실행 가능한 처방 |
| 지속 성장 | Sustainable Growth | 정기 검진 |
### Writing Style
- **Korean**: 분석적 + 개인적, 철학-기술 융합
- **English**: Reflective, poetic, paradox as device
- **Fonts**: Poppins (headings), Lora (body)
- **Colors**: Primary #1a1a2e, Accent #4ecdc4
---
## 2. OurDigital Blog
**Triggers**: `our blog`, `our 블로그`, `our 한국어 포스트`
### Channel
- **URL**: blog.ourdigital.org
- **Language**: Korean (전문용어 영문 병기)
- **Tone**: Analytical & Personal, Educational
- **Length**: 1,500-3,000자
### Structure
```
제목 (SEO 키워드 포함)
├── 도입부 (hook + 핵심 질문)
├── 본문 (3-5 섹션)
│ ├── 소제목 + 본문
│ └── 데이터/인용 포함
├── 결론 (인사이트 + 열린 질문)
└── CTA (optional)
```
### Style Tips
- 역설(Paradox) 활용: "~하면서 동시에 ~하다"
- 수사적 질문으로 참여 유도
- 우울한 낙관주의: 불안 인정 + 희망 제시
---
## 3. OurDigital Journal
**Triggers**: `our journal`, `our English essay`, `our 영문 에세이`
### Channel
- **URL**: journal.ourdigital.org
- **Language**: English
- **Tone**: Conversational, Poetic, Reflective
- **Length**: 1,000-2,000 words
### Writing Characteristics
- **Philosophical-Technical Hybridization**: Tech + human implications
- **Paradox as Device**: Illuminate through tensions
- **Melancholic Optimism**: Clear-eyed hope
### Structure
```
Opening (hook with scene/question)
├── Body (weaving narrative + analysis)
│ ├── Personal observation
│ ├── Cultural/technical context
│ └── Philosophical reflection
└── Closing (open question, not conclusion)
```
---
## 4. OurDigital Research
**Triggers**: `our research`, `our 리서치`, `our deep research`
### Workflow
1. **Discovery**: Clarify topic, audience, depth
2. **Planning**: Generate research questions (3-5 primary)
3. **Research**: Multi-source investigation
4. **Synthesis**: Research paper with findings
5. **Archive**: Save to Notion "Working with AI"
6. **Output**: Optional blog draft
### Research Plan Template
```
Primary Questions:
1. [Core question about topic]
2. [Supporting question]
3. [Trend/future question]
Source Strategy:
- Web search: [keywords]
- Notion: [past research]
- Industry reports: [sources]
Deliverables:
- Research paper
- Notion archive
- Blog draft (optional)
```
---
## 5. OurDigital Document
**Triggers**: `our document`, `our 발표자료`, `our presentation`
### Workflow
1. Extract content from Notion
2. Synthesize key topics
3. Plan slide structure
4. Generate presentation
5. Apply OurDigital branding
### Presentation Types
| Type | Slides | Focus |
|------|--------|-------|
| Executive | 3-5 | High-level findings |
| Research | 10-20 | Detailed analysis |
| Meeting | 5-10 | Agenda-driven |
### Slide Structure
```
Title Slide → Agenda → Content (1-3 per topic) → Summary → Next Steps
```
---
## 6. OurDigital Designer
**Triggers**: `our design`, `our 썸네일`, `our image prompt`
### Philosophy
OurDigital images are visual philosophy—abstract metaphors over literal representations.
### Visual Approach
| Topic | Strategy | Colors |
|-------|----------|--------|
| Technology | Organic-digital hybrids | Cool blues |
| Social | Network patterns | Desaturated |
| Philosophy | Zen space | Monochrome + accent |
### Prompt Template
```
Create [style] featured image, 1200x630px.
Visual concept: [metaphor description].
Atmosphere: [mood].
Colors: [palette with accent].
Composition: Abstract, 20%+ negative space.
Avoid: Stock aesthetics, literal interpretation.
```
### Metaphor Shortcuts
- Algorithm → Constellation patterns
- Identity → Layered masks
- Network → Root systems
- Time → Spirals, sediment layers
---
## 7. OurDigital Ad Manager
**Triggers**: `our ad copy`, `our 광고 카피`, `our keyword`
### Google Ads Format
```
Headline 1: [30 chars] - Keyword + value
Headline 2: [30 chars] - Benefit
Headline 3: [30 chars] - Differentiator
Description 1: [90 chars] - Expand value
Description 2: [90 chars] - CTA + urgency
```
### Naver Format
```
제목: [25자] - 키워드 + 가치
설명: [45자] - 혜택 + 행동 유도
```
### Copy Formulas
- **PAS**: Problem → Agitate → Solution
- **FBP**: Feature → Benefit → Proof
- **QAA**: Question → Answer → Action
---
## 8. OurDigital Trainer
**Triggers**: `our training`, `our 워크샵`, `our 교육`
### Domains
- Data Literacy, AI Literacy
- Digital Marketing (SEO, GTM)
- Brand Marketing
### Workshop Templates
**2-Hour**
```
00:00-00:10 Ice-breaker
00:10-00:50 Module 1
00:50-01:00 Break
01:00-01:30 Module 2 + Practice
01:30-01:50 Activity
01:50-02:00 Wrap-up
```
**Half-Day (4 Hours)**
```
09:00-09:20 Opening
09:20-10:20 Module 1
10:20-10:30 Break
10:30-11:30 Module 2
11:30-12:00 Practice
12:00-12:30 Module 3
12:30-13:00 Closing
```
### Evaluation
- Level 1: Reaction (만족도)
- Level 2: Learning (지식 습득)
- Level 3: Behavior (현업 적용)
- Level 4: Results (성과 개선)
---
## 9. OurDigital Backoffice
**Triggers**: `our 견적서`, `our proposal`, `our quote`
### Document Types
1. **Quote (견적서)**: Pricing summary
2. **Proposal (제안서)**: Detailed offering
3. **Contract (계약서)**: Agreement framework ⚠️ Legal review required
4. **Cost Analysis**: ROI justification
### Quote Structure
```
문서번호: OD-QUOTE-YYYY-NNN
발행일: YYYY-MM-DD
서비스 항목 (표)
합계 (소계 + VAT)
결제 조건 (50/50)
프로젝트 일정
포함/미포함 사항
```
### Service Pricing Reference
| Service | Price Range |
|---------|-------------|
| SEO Audit | 300-500만원 |
| GTM Setup | 200-400만원 |
| Monthly SEO | 150-300만원/월 |
| Workshop | 100-200만원 |
---
## 10. OurDigital Skill Creator
**Triggers**: `our skill create`, `our 스킬 만들기`
### Suitability Criteria
- Clear trigger conditions
- Focused scope (1-3 functions)
- Reusable resources
- Domain-specific knowledge
- Clear boundaries
### Skill Structure
```
XX-ourdigital-skillname/
├── code/SKILL.md
├── desktop/SKILL.md
├── shared/references/
├── docs/CHANGELOG.md
└── README.md
```
### YAML Frontmatter Template
```yaml
---
name: ourdigital-skillname
description: |
[Purpose]
Triggers (ourdigital or our prefix):
- "our [keyword]", "ourdigital [keyword]"
version: "1.0"
author: OurDigital
---
```
---
## Quick Reference
| # | Skill | Trigger | Purpose |
|---|-------|---------|---------|
| 01 | brand-guide | `our brand` | Brand standards |
| 02 | blog | `our blog` | Korean posts |
| 03 | journal | `our journal` | English essays |
| 04 | research | `our research` | Research prompts |
| 05 | document | `our document` | Presentations |
| 06 | designer | `our design` | Image prompts |
| 07 | ad-manager | `our ad copy` | Ad copywriting |
| 08 | trainer | `our training` | Workshops |
| 09 | backoffice | `our 견적서` | Business docs |
| 10 | skill-creator | `our skill` | Create skills |
**Prefix**: Always use "our" or "ourdigital" to activate these skills.

415
custom-skills/_ourdigital-shared/install.sh Executable file
View File

@@ -0,0 +1,415 @@
#!/bin/bash
#
# OurDigital Skills Installer
# Portable installation tool for OurDigital Claude Skills package
#
# Usage:
# ./install.sh # Interactive install
# ./install.sh --update # Update existing installation
# ./install.sh --uninstall # Remove installation
# ./install.sh --help # Show help
#
set -e
# Colors for output
RED='\033[0;31m'
GREEN='\033[0;32m'
YELLOW='\033[1;33m'
BLUE='\033[0;34m'
CYAN='\033[0;36m'
NC='\033[0m' # No Color
# Configuration
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
SKILLS_DIR="$(dirname "$SCRIPT_DIR")"
ENV_FILE="$HOME/.env.ourdigital"
CONFIG_DIR="$HOME/.ourdigital"
VENV_DIR="$SKILLS_DIR/.venv-ourdigital"
# Print banner
print_banner() {
echo -e "${CYAN}"
echo "╔═══════════════════════════════════════════════════════════╗"
echo "║ ║"
echo "║ OurDigital Skills Installer ║"
echo "║ 사람, 디지털, 그리고 문화 ║"
echo "║ ║"
echo "╚═══════════════════════════════════════════════════════════╝"
echo -e "${NC}"
}
# Print colored messages
info() { echo -e "${BLUE}[INFO]${NC} $1"; }
success() { echo -e "${GREEN}[OK]${NC} $1"; }
warn() { echo -e "${YELLOW}[WARN]${NC} $1"; }
error() { echo -e "${RED}[ERROR]${NC} $1"; }
# Check prerequisites
check_prerequisites() {
info "Checking prerequisites..."
local missing=()
# Check Python 3.11+
if command -v python3 &> /dev/null; then
PYTHON_VERSION=$(python3 -c 'import sys; print(f"{sys.version_info.major}.{sys.version_info.minor}")')
if [[ $(echo "$PYTHON_VERSION >= 3.11" | bc -l) -eq 1 ]]; then
success "Python $PYTHON_VERSION"
else
warn "Python $PYTHON_VERSION (3.11+ recommended)"
fi
else
missing+=("python3")
fi
# Check git
if command -v git &> /dev/null; then
success "Git $(git --version | cut -d' ' -f3)"
else
missing+=("git")
fi
# Check 1Password CLI (optional)
if command -v op &> /dev/null; then
success "1Password CLI available"
HAS_1PASSWORD=true
else
warn "1Password CLI not found (credentials will need manual entry)"
HAS_1PASSWORD=false
fi
if [[ ${#missing[@]} -gt 0 ]]; then
error "Missing required tools: ${missing[*]}"
exit 1
fi
echo ""
}
# Create directory structure
setup_directories() {
info "Setting up directories..."
# Create config directory
mkdir -p "$CONFIG_DIR/credentials"
chmod 700 "$CONFIG_DIR"
chmod 700 "$CONFIG_DIR/credentials"
success "Created $CONFIG_DIR/"
# Create logs directory
mkdir -p "$CONFIG_DIR/logs"
success "Created $CONFIG_DIR/logs/"
echo ""
}
# Setup environment file
setup_environment() {
info "Setting up environment file..."
if [[ -f "$ENV_FILE" ]]; then
warn "$ENV_FILE already exists"
read -p "Overwrite? (y/N): " -n 1 -r
echo
if [[ ! $REPLY =~ ^[Yy]$ ]]; then
info "Keeping existing environment file"
return
fi
cp "$ENV_FILE" "$ENV_FILE.backup.$(date +%Y%m%d%H%M%S)"
success "Backed up existing file"
fi
cp "$SCRIPT_DIR/.env.ourdigital.template" "$ENV_FILE"
chmod 600 "$ENV_FILE"
success "Created $ENV_FILE"
echo ""
}
# Setup credentials from 1Password or manual
setup_credentials() {
info "Setting up credentials..."
if [[ "$HAS_1PASSWORD" == true ]]; then
read -p "Fetch credentials from 1Password? (Y/n): " -n 1 -r
echo
if [[ ! $REPLY =~ ^[Nn]$ ]]; then
fetch_from_1password
return
fi
fi
echo -e "${YELLOW}Manual credential setup required.${NC}"
echo "Edit $ENV_FILE with your API keys:"
echo " - NOTION_API_TOKEN"
echo " - GHOST_BLOG_ADMIN_KEY"
echo " - GHOST_JOURNAL_ADMIN_KEY"
echo " - FIGMA_ACCESS_TOKEN"
echo ""
}
# Fetch credentials from 1Password
fetch_from_1password() {
info "Fetching credentials from 1Password..."
# Check if signed in
if ! op account list &> /dev/null; then
warn "Please sign in to 1Password CLI first"
echo "Run: eval \$(op signin)"
return
fi
# Fetch each credential
local credentials=(
"NOTION_API_TOKEN:OurDigital Notion:api_token"
"GHOST_BLOG_ADMIN_KEY:OurDigital Ghost Blog:api_key"
"GHOST_JOURNAL_ADMIN_KEY:OurDigital Ghost Journal:api_key"
"FIGMA_ACCESS_TOKEN:OurDigital Figma:api_token"
)
for cred in "${credentials[@]}"; do
IFS=':' read -r env_var item_name field <<< "$cred"
if value=$(op item get "$item_name" --fields "$field" 2>/dev/null); then
sed -i '' "s|^$env_var=.*|$env_var=$value|" "$ENV_FILE" 2>/dev/null || \
sed -i "s|^$env_var=.*|$env_var=$value|" "$ENV_FILE"
success "Fetched $env_var"
else
warn "Could not fetch $env_var from 1Password"
fi
done
echo ""
}
# Setup Python virtual environment
setup_python_env() {
info "Setting up Python virtual environment..."
if [[ -d "$VENV_DIR" ]]; then
warn "Virtual environment already exists"
read -p "Recreate? (y/N): " -n 1 -r
echo
if [[ $REPLY =~ ^[Yy]$ ]]; then
rm -rf "$VENV_DIR"
else
info "Using existing virtual environment"
return
fi
fi
python3 -m venv "$VENV_DIR"
success "Created virtual environment"
# Activate and install dependencies
source "$VENV_DIR/bin/activate"
pip install --upgrade pip -q
pip install -r "$SCRIPT_DIR/requirements/base.txt" -q
success "Installed base dependencies"
# Install code-specific if requested
read -p "Install Claude Code dependencies? (Y/n): " -n 1 -r
echo
if [[ ! $REPLY =~ ^[Nn]$ ]]; then
pip install -r "$SCRIPT_DIR/requirements/code.txt" -q
success "Installed Code dependencies"
fi
deactivate
echo ""
}
# Copy config file
setup_config() {
info "Setting up configuration..."
if [[ ! -f "$CONFIG_DIR/config.yaml" ]]; then
cp "$SCRIPT_DIR/config/ourdigital.yaml" "$CONFIG_DIR/config.yaml"
success "Created $CONFIG_DIR/config.yaml"
else
info "Config file already exists, skipping"
fi
echo ""
}
# Validate installation
validate_installation() {
info "Validating installation..."
local checks_passed=0
local checks_total=6
# Check directories
[[ -d "$CONFIG_DIR" ]] && ((checks_passed++)) && success "Config directory exists" || warn "Config directory missing"
[[ -d "$CONFIG_DIR/credentials" ]] && ((checks_passed++)) && success "Credentials directory exists" || warn "Credentials directory missing"
# Check files
[[ -f "$ENV_FILE" ]] && ((checks_passed++)) && success "Environment file exists" || warn "Environment file missing"
[[ -f "$CONFIG_DIR/config.yaml" ]] && ((checks_passed++)) && success "Config file exists" || warn "Config file missing"
# Check virtual environment
[[ -d "$VENV_DIR" ]] && ((checks_passed++)) && success "Virtual environment exists" || warn "Virtual environment missing"
# Check skills directory
[[ -d "$SKILLS_DIR/01-ourdigital-brand-guide" ]] && ((checks_passed++)) && success "Skills directory valid" || warn "Skills not found"
echo ""
echo -e "${CYAN}Validation: $checks_passed/$checks_total checks passed${NC}"
echo ""
}
# Show installed skills
show_skills() {
info "Installed OurDigital Skills:"
echo ""
for dir in "$SKILLS_DIR"/0{1,2,3,4,5,6,7,8,9}-ourdigital-* "$SKILLS_DIR"/10-ourdigital-*; do
if [[ -d "$dir" ]]; then
name=$(basename "$dir")
desc=$(grep -m1 "^name:" "$dir/desktop/SKILL.md" 2>/dev/null | cut -d':' -f2 | xargs || echo "")
echo -e " ${GREEN}✓${NC} $name"
fi
done
echo ""
}
# Print usage instructions
print_usage() {
echo -e "${CYAN}Usage Instructions:${NC}"
echo ""
echo "1. Activate the virtual environment:"
echo " source $VENV_DIR/bin/activate"
echo ""
echo "2. Edit credentials if needed:"
echo " nano $ENV_FILE"
echo ""
echo "3. Use skills with 'our' or 'ourdigital' prefix:"
echo " - our blog [topic]"
echo " - our research [topic]"
echo " - our 견적서"
echo ""
echo "4. Documentation:"
echo " $SKILLS_DIR/OUR_SKILL_PROJECT_PLAN_v1.1.md"
echo ""
}
# Uninstall
uninstall() {
warn "This will remove OurDigital configuration (not skills)."
read -p "Continue? (y/N): " -n 1 -r
echo
if [[ ! $REPLY =~ ^[Yy]$ ]]; then
info "Cancelled"
exit 0
fi
# Backup before removing
if [[ -f "$ENV_FILE" ]]; then
cp "$ENV_FILE" "$ENV_FILE.uninstall.backup"
rm "$ENV_FILE"
success "Removed $ENV_FILE (backup saved)"
fi
if [[ -d "$VENV_DIR" ]]; then
rm -rf "$VENV_DIR"
success "Removed virtual environment"
fi
info "Config directory preserved at $CONFIG_DIR"
info "To fully remove: rm -rf $CONFIG_DIR"
success "Uninstall complete"
}
# Show help
show_help() {
echo "OurDigital Skills Installer"
echo ""
echo "Usage: ./install.sh [OPTIONS]"
echo ""
echo "Options:"
echo " --help, -h Show this help message"
echo " --update, -u Update existing installation"
echo " --uninstall Remove installation (preserves skills)"
echo " --validate Only run validation checks"
echo " --skip-creds Skip credentials setup"
echo " --skip-venv Skip virtual environment setup"
echo ""
echo "Examples:"
echo " ./install.sh # Full interactive install"
echo " ./install.sh --update # Update existing setup"
echo " ./install.sh --skip-creds # Install without credentials"
echo ""
}
# Main installation flow
main_install() {
print_banner
check_prerequisites
setup_directories
setup_environment
if [[ "$SKIP_CREDS" != true ]]; then
setup_credentials
fi
if [[ "$SKIP_VENV" != true ]]; then
setup_python_env
fi
setup_config
validate_installation
show_skills
print_usage
echo -e "${GREEN}╔═══════════════════════════════════════════════════════════╗${NC}"
echo -e "${GREEN}║ Installation Complete! ║${NC}"
echo -e "${GREEN}╚═══════════════════════════════════════════════════════════╝${NC}"
}
# Parse arguments
SKIP_CREDS=false
SKIP_VENV=false
while [[ $# -gt 0 ]]; do
case $1 in
--help|-h)
show_help
exit 0
;;
--uninstall)
uninstall
exit 0
;;
--validate)
validate_installation
exit 0
;;
--update|-u)
info "Updating installation..."
setup_python_env
validate_installation
exit 0
;;
--skip-creds)
SKIP_CREDS=true
shift
;;
--skip-venv)
SKIP_VENV=true
shift
;;
*)
error "Unknown option: $1"
show_help
exit 1
;;
esac
done
# Run main install
main_install

158
custom-skills/_ourdigital-shared/scripts/export_for_claude_ai.py Executable file
View File

@@ -0,0 +1,158 @@
#!/usr/bin/env python3
"""
Export OurDigital Skills for Claude.ai Projects
Generates simplified skill files suitable for uploading to Claude.ai.
Usage:
python export_for_claude_ai.py # Export all skills
python export_for_claude_ai.py --bundle # Generate bundle only
python export_for_claude_ai.py --individual # Generate individual files only
"""
import os
import re
import argparse
from pathlib import Path
from typing import Optional
SCRIPT_DIR = Path(__file__).parent.parent
SKILLS_DIR = SCRIPT_DIR.parent
EXPORT_DIR = SCRIPT_DIR / "claude-ai-export"
INDIVIDUAL_DIR = EXPORT_DIR / "individual"
# (dir, name, desc, triggers)
SKILLS = [
("01-ourdigital-brand-guide", "Brand Guide", "brand standards and style",
'"our brand guide", "our 브랜드 가이드", "our 톤앤매너"'),
("02-ourdigital-blog", "Blog", "Korean blog drafts",
'"our blog", "our 블로그", "our 한국어 포스트"'),
("03-ourdigital-journal", "Journal", "English essays",
'"our journal", "our English essay", "our 영문 에세이"'),
("04-ourdigital-research", "Research", "research prompts",
'"our research", "our 리서치", "our deep research"'),
("05-ourdigital-document", "Document", "presentations",
'"our document", "our 발표자료", "our presentation"'),
("06-ourdigital-designer", "Designer", "image prompts",
'"our design", "our 썸네일", "our image prompt"'),
("07-ourdigital-ad-manager", "Ad Manager", "ad copywriting",
'"our ad copy", "our 광고 카피", "our keyword"'),
("08-ourdigital-trainer", "Trainer", "training materials",
'"our training", "our 워크샵", "our 교육"'),
("09-ourdigital-backoffice", "Backoffice", "business documents",
'"our 견적서", "our proposal", "our quote"'),
("10-ourdigital-skill-creator", "Skill Creator", "creating new skills",
'"our skill create", "our 스킬 만들기"'),
]
def extract_skill_content(skill_dir: str) -> Optional[str]:
"""Extract and simplify content from a skill's SKILL.md."""
desktop_path = SKILLS_DIR / skill_dir / "desktop" / "SKILL.md"
if not desktop_path.exists():
print(f" Warning: {desktop_path} not found")
return None
content = desktop_path.read_text()
# Remove YAML frontmatter
if content.startswith("---"):
parts = content.split("---", 2)
if len(parts) >= 3:
content = parts[2].strip()
# Extract key sections (first 150 lines or so)
lines = content.split("\n")
# Find main heading and take content
simplified = []
in_content = False
line_count = 0
max_lines = 120
for line in lines:
if line.startswith("# "):
in_content = True
if in_content:
simplified.append(line)
line_count += 1
if line_count >= max_lines:
simplified.append("\n[... see full documentation for more ...]")
break
return "\n".join(simplified)
def generate_individual_files():
"""Generate individual skill files for Claude.ai."""
INDIVIDUAL_DIR.mkdir(parents=True, exist_ok=True)
print("Generating individual skill files...")
for skill_dir, name, desc, triggers in SKILLS:
content = extract_skill_content(skill_dir)
if content:
# Create simplified header with YAML frontmatter
num = skill_dir.split("-")[0]
skill_name = name.lower().replace(' ', '-')
filename = f"{num}-{skill_name}.md"
header = f"""---
name: ourdigital-{skill_name}
description: |
{desc.capitalize()}.
Triggers (ourdigital or our prefix):
- {triggers}
---
# OurDigital {name}
**Purpose**: {desc.capitalize()}
**Triggers**: Use "our" or "ourdigital" prefix
---
"""
output_path = INDIVIDUAL_DIR / filename
output_path.write_text(header + content)
print(f" Created: {filename}")
def generate_bundle():
"""Generate combined bundle file."""
print("Generating bundle file...")
# Read existing bundle (already created manually with full content)
bundle_path = EXPORT_DIR / "ourdigital-skills-bundle.md"
if bundle_path.exists():
print(f" Bundle exists: {bundle_path}")
else:
print(f" Warning: Bundle not found at {bundle_path}")
def main():
parser = argparse.ArgumentParser(description="Export skills for Claude.ai")
parser.add_argument("--bundle", action="store_true", help="Generate bundle only")
parser.add_argument("--individual", action="store_true", help="Generate individual files only")
args = parser.parse_args()
print(f"Export directory: {EXPORT_DIR}\n")
if args.bundle:
generate_bundle()
elif args.individual:
generate_individual_files()
else:
generate_bundle()
generate_individual_files()
print("\nDone! Files ready for upload to Claude.ai Projects.")
print(f" Bundle: {EXPORT_DIR / 'ourdigital-skills-bundle.md'}")
print(f" Individual: {INDIVIDUAL_DIR}/")
if __name__ == "__main__":
main()

284
custom-skills/_ourdigital-shared/scripts/validate_install.py Executable file
View File

@@ -0,0 +1,284 @@
#!/usr/bin/env python3
"""
OurDigital Skills Installation Validator
Checks that all components are properly installed and configured.
Usage:
python validate_install.py
python validate_install.py --verbose
python validate_install.py --fix # Attempt to fix issues
"""
import os
import sys
import json
import argparse
from pathlib import Path
from typing import List, Tuple, Dict
# Colors for terminal output
class Colors:
GREEN = '\033[92m'
YELLOW = '\033[93m'
RED = '\033[91m'
CYAN = '\033[96m'
BOLD = '\033[1m'
END = '\033[0m'
def ok(msg: str) -> None:
print(f"{Colors.GREEN}[✓]{Colors.END} {msg}")
def warn(msg: str) -> None:
print(f"{Colors.YELLOW}[!]{Colors.END} {msg}")
def fail(msg: str) -> None:
print(f"{Colors.RED}[✗]{Colors.END} {msg}")
def info(msg: str) -> None:
print(f"{Colors.CYAN}[i]{Colors.END} {msg}")
class InstallationValidator:
def __init__(self, verbose: bool = False):
self.verbose = verbose
self.home = Path.home()
self.script_dir = Path(__file__).parent.parent
self.skills_dir = self.script_dir.parent
self.env_file = self.home / ".env.ourdigital"
self.config_dir = self.home / ".ourdigital"
self.venv_dir = self.skills_dir / ".venv-ourdigital"
self.results: List[Tuple[str, bool, str]] = []
def check(self, name: str, condition: bool, fix_hint: str = "") -> bool:
"""Record a check result."""
self.results.append((name, condition, fix_hint))
return condition
def validate_directories(self) -> int:
"""Check required directories exist."""
info("Checking directories...")
passed = 0
checks = [
("Config directory", self.config_dir.exists(),
f"mkdir -p {self.config_dir}"),
("Credentials directory", (self.config_dir / "credentials").exists(),
f"mkdir -p {self.config_dir}/credentials"),
("Logs directory", (self.config_dir / "logs").exists(),
f"mkdir -p {self.config_dir}/logs"),
]
for name, condition, fix in checks:
if self.check(name, condition, fix):
ok(name)
passed += 1
else:
fail(name)
if self.verbose:
print(f" Fix: {fix}")
return passed
def validate_files(self) -> int:
"""Check required files exist."""
info("Checking files...")
passed = 0
checks = [
("Environment file (.env.ourdigital)", self.env_file.exists(),
"cp _ourdigital-shared/.env.ourdigital.template ~/.env.ourdigital"),
("Config file (config.yaml)", (self.config_dir / "config.yaml").exists(),
"cp _ourdigital-shared/config/ourdigital.yaml ~/.ourdigital/config.yaml"),
]
for name, condition, fix in checks:
if self.check(name, condition, fix):
ok(name)
passed += 1
else:
fail(name)
if self.verbose:
print(f" Fix: {fix}")
return passed
def validate_env_variables(self) -> int:
"""Check environment variables are set."""
info("Checking environment variables...")
passed = 0
required_vars = [
"NOTION_API_TOKEN",
"GHOST_BLOG_ADMIN_KEY",
"GHOST_JOURNAL_ADMIN_KEY",
]
optional_vars = [
"FIGMA_ACCESS_TOKEN",
"N8N_API_KEY",
]
if self.env_file.exists():
env_content = self.env_file.read_text()
for var in required_vars:
has_value = f"{var}=" in env_content and \
f"{var}=<" not in env_content and \
f"{var}=$" not in env_content
if self.check(f"Required: {var}", has_value, f"Set {var} in {self.env_file}"):
ok(f"{var}")
passed += 1
else:
fail(f"{var} (required)")
for var in optional_vars:
has_value = f"{var}=" in env_content and \
f"{var}=<" not in env_content
if has_value:
ok(f"{var} (optional)")
passed += 1
else:
warn(f"{var} (optional, not set)")
else:
fail("Environment file not found")
return passed
def validate_python_env(self) -> int:
"""Check Python virtual environment."""
info("Checking Python environment...")
passed = 0
if self.check("Virtual environment", self.venv_dir.exists(),
f"python3 -m venv {self.venv_dir}"):
ok("Virtual environment exists")
passed += 1
# Check for key packages
pip_path = self.venv_dir / "bin" / "pip"
if pip_path.exists():
ok("pip available")
passed += 1
else:
fail("Virtual environment not found")
return passed
def validate_skills(self) -> int:
"""Check skills are properly structured."""
info("Checking skills...")
passed = 0
expected_skills = [
"01-ourdigital-brand-guide",
"02-ourdigital-blog",
"03-ourdigital-journal",
"04-ourdigital-research",
"05-ourdigital-document",
"06-ourdigital-designer",
"07-ourdigital-ad-manager",
"08-ourdigital-trainer",
"09-ourdigital-backoffice",
"10-ourdigital-skill-creator",
]
for skill in expected_skills:
skill_dir = self.skills_dir / skill
has_desktop = (skill_dir / "desktop" / "SKILL.md").exists()
has_code = (skill_dir / "code" / "SKILL.md").exists()
if has_desktop and has_code:
ok(f"{skill}")
passed += 1
elif has_desktop or has_code:
warn(f"{skill} (incomplete)")
else:
fail(f"{skill} (missing)")
return passed
def validate_permissions(self) -> int:
"""Check file permissions are secure."""
info("Checking permissions...")
passed = 0
if self.env_file.exists():
mode = oct(self.env_file.stat().st_mode)[-3:]
if mode in ('600', '400'):
ok(f".env.ourdigital permissions ({mode})")
passed += 1
else:
warn(f".env.ourdigital permissions ({mode}, should be 600)")
creds_dir = self.config_dir / "credentials"
if creds_dir.exists():
mode = oct(creds_dir.stat().st_mode)[-3:]
if mode in ('700', '500'):
ok(f"credentials/ permissions ({mode})")
passed += 1
else:
warn(f"credentials/ permissions ({mode}, should be 700)")
return passed
def run(self) -> Dict[str, int]:
"""Run all validation checks."""
print(f"\n{Colors.CYAN}{Colors.BOLD}OurDigital Skills Installation Validator{Colors.END}\n")
results = {
"directories": self.validate_directories(),
"files": self.validate_files(),
"env_variables": self.validate_env_variables(),
"python_env": self.validate_python_env(),
"skills": self.validate_skills(),
"permissions": self.validate_permissions(),
}
# Summary
total_passed = sum(results.values())
total_checks = len(self.results)
print(f"\n{Colors.CYAN}{'='*50}{Colors.END}")
print(f"{Colors.BOLD}Summary:{Colors.END} {total_passed}/{total_checks} checks passed")
if total_passed == total_checks:
print(f"{Colors.GREEN}All checks passed! Installation is complete.{Colors.END}")
else:
failed = [r for r in self.results if not r[1]]
print(f"{Colors.YELLOW}Some checks failed. Review above for details.{Colors.END}")
if self.verbose:
print(f"\n{Colors.BOLD}Failed checks:{Colors.END}")
for name, _, fix in failed:
print(f" - {name}")
if fix:
print(f" Fix: {fix}")
return results
def main():
parser = argparse.ArgumentParser(description="Validate OurDigital Skills installation")
parser.add_argument("--verbose", "-v", action="store_true",
help="Show detailed output with fix suggestions")
parser.add_argument("--json", action="store_true",
help="Output results as JSON")
args = parser.parse_args()
validator = InstallationValidator(verbose=args.verbose)
results = validator.run()
if args.json:
print(json.dumps(results, indent=2))
# Exit with error if any checks failed
total_passed = sum(results.values())
total_checks = len(validator.results)
sys.exit(0 if total_passed == total_checks else 1)
if __name__ == "__main__":
main()

0
settings-audit-report.json → docs/settings-audit-report.json
View File

0
settings-audit-report.md → docs/settings-audit-report.md
View File

80
reference/SKILL-FORMAT-REQUIREMENTS.md
View File

@@ -4,15 +4,15 @@
This document describes the format requirements for Claude Skills in this repository. Skills support dual-platform development (Claude Code and Claude Desktop) with separated concerns. This document describes the format requirements for Claude Skills in this repository. Skills support dual-platform development (Claude Code and Claude Desktop) with separated concerns.
## Desktop Skill Structure (Recommended) ## Desktop Skill Structure
For Claude Desktop skills, metadata is stored in a separate `skill.yaml` file: For Claude Desktop skills:
``` ```
skill-name/ skill-name/
└── desktop/ └── desktop/
├── skill.yaml # Metadata (name, description, allowed-tools, license) ├── SKILL.md # MUST have YAML frontmatter (name, description)
├── SKILL.md # Content only (no frontmatter) ├── skill.yaml # Optional extended metadata
├── tools/ # MCP tool documentation ├── tools/ # MCP tool documentation
│ ├── firecrawl.md # Tool-specific docs │ ├── firecrawl.md # Tool-specific docs
│ └── notion.md │ └── notion.md
@@ -20,10 +20,35 @@ skill-name/
└── examples/ # Usage examples └── examples/ # Usage examples
``` ```
### skill.yaml Format ### SKILL.md Format (REQUIRED)
**Claude Desktop REQUIRES YAML frontmatter** with at least `name` and `description`.
```markdown
---
name: skill-name-here
description: |
Brief description of what the skill does.
Include trigger keywords in the description.
Triggers: keyword1, keyword2.
---
# Skill Name
Purpose and overview...
## Workflow
Step-by-step instructions...
## MCP Tool Usage
Tool-specific guidance...
```
### skill.yaml (Optional, for extended metadata)
```yaml ```yaml
# Required fields
name: skill-name-here name: skill-name-here
description: Brief description of what the skill does and trigger keywords description: Brief description of what the skill does and trigger keywords
@@ -46,24 +71,6 @@ triggers:
- keyword2 - keyword2
``` ```
### SKILL.md Content
With metadata separated into skill.yaml, SKILL.md contains only the skill directive:
```markdown
# Skill Name
Purpose and overview...
## Workflow
Step-by-step instructions...
## MCP Tool Usage
Tool-specific guidance...
```
### tools/ Directory ### tools/ Directory
Document MCP tools used by the skill: Document MCP tools used by the skill:
@@ -145,18 +152,21 @@ The script:
3. Creates `tools/` directory 3. Creates `tools/` directory
4. Generates tool stub files based on `allowed-tools` 4. Generates tool stub files based on `allowed-tools`
## Legacy Format (Deprecated) ## Required vs Optional Fields
The old format with frontmatter embedded in SKILL.md is deprecated: ### SKILL.md Frontmatter (Required)
```yaml | Field | Required | Description |
--- |-------|----------|-------------|
name: skill-name | `name` | **Yes** | Skill identifier in kebab-case |
description: Description | `description` | **Yes** | Multi-line, include trigger keywords |
allowed-tools: mcp__firecrawl__*, Read, Write
---
# Skill content... ### skill.yaml (Optional)
```
Use the migration script to convert to the new format. | Field | Description |
|-------|-------------|
| `name` | Same as SKILL.md |
| `description` | Same or extended |
| `allowed-tools` | List of permitted tools |
| `license` | MIT, Internal-use Only |
| `triggers` | Explicit trigger list |