Files
our-claude-skills/README.md
Andrew Yim b85dead216
Some checks failed
Verify Skills / verify-skills (push) Has been cancelled
Verify Skills / verify-skills (pull_request) Has been cancelled
chore(marketplace): add ourdigital-skills local marketplace + fix README install docs
Add .claude-plugin/marketplace.json defining the ourdigital-skills local directory marketplace: 8 themed skill plugins (core/seo/notion/jamie/notebooklm/gtm/dintel/utils, 66 skills) + 3 standalone command plugins (mac-optimizer, multi-agent-guide, dintel-bootstrap). Every skill path resolves to a root SKILL.md.

Fix README install instructions: clarify Quick Install scope (commands + venv + creds, not skills); correct the Claude Code skill symlink target to the skill root (was desktop/, which would not load); fix the Claude Desktop import step.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-09 00:25:21 +09:00

255 lines
11 KiB
Markdown

# Our Claude Skills
> **Internal R&D Repository** - This repository is restricted for internal use only.
A collection of **65 custom Claude Skills** for OurDigital workflows, D.intelligence Agent Corps (9-agent business operations suite), Jamie Plastic Surgery Clinic brand management, SEO/GTM tools, NotebookLM automation, Notion integrations, reference documentation curation, macOS system optimization, TUI wizard design, and multi-agent collaboration.
## Quick Install
```bash
git clone https://github.com/ourdigital/our-claude-skills.git
cd our-claude-skills/custom-skills/_ourdigital-shared
./install.sh
```
This symlinks the global slash commands into `~/.claude/commands/`, sets up the
Python virtual environment, and configures credentials. It does **not** register
skills natively — to load a skill as a Claude Code skill, also symlink it into
`~/.claude/skills/` (see [Usage → Claude Code](#claude-code)).
## Custom Skills Overview
### OurDigital Core (01-10)
| # | Skill | Purpose |
|---|-------|---------|
| 01 | `ourdigital-brand-guide` | Brand standards, writing style, visual identity reference |
| 02 | `ourdigital-blog` | Korean blog draft creation for blog.ourdigital.org |
| 03 | `ourdigital-journal` | English essay/article creation for journal.ourdigital.org |
| 04 | `ourdigital-research` | Research → Blog workflow |
| 05 | `ourdigital-document` | Notion → Presentation workflow |
| 06 | `ourdigital-designer` | Visual storytelling, image prompts |
| 07 | `ourdigital-ad-manager` | Ad copywriting & keyword research |
| 08 | `ourdigital-trainer` | Training material creation |
| 09 | `ourdigital-backoffice` | Business document creation |
| 10 | `ourdigital-skill-creator` | Meta skill for creating/managing skills |
### SEO Tools (11-34)
| # | Skill | Purpose |
|---|-------|---------|
| 11 | `seo-comprehensive-audit` | Unified 6-stage SEO audit orchestrator |
| 12 | `seo-technical-audit` | Robots.txt, sitemap, crawlability |
| 13 | `seo-on-page-audit` | Meta tags, headings, links analysis |
| 14 | `seo-core-web-vitals` | LCP, CLS, FID, INP metrics |
| 15 | `seo-search-console` | GSC data analysis |
| 16 | `seo-schema-validator` | Structured data validation |
| 17 | `seo-schema-generator` | Schema markup creation |
| 18 | `seo-local-audit` | NAP consistency, GBP, Naver Smart Place, citations |
| 19 | `seo-keyword-strategy` | Keyword expansion, intent classification, clustering, gaps |
| 20 | `seo-serp-analysis` | Google/Naver SERP features, competitor positions |
| 21 | `seo-position-tracking` | Rank monitoring, visibility scores, alerts |
| 22 | `seo-link-building` | Backlink audit, toxic links, link gaps |
| 23 | `seo-content-strategy` | Content audit, decay detection, briefs, clusters |
| 24 | `seo-ecommerce` | Product page audit, product schema, Naver Smart Store |
| 25 | `seo-kpi-framework` | Unified KPIs, health scores, ROI estimation |
| 26 | `seo-international` | Hreflang validation, content parity, multi-language |
| 27 | `seo-ai-visibility` | AI search citations, brand radar, share of voice |
| 28 | `seo-knowledge-graph` | Entity SEO, Knowledge Panel, PAA, FAQ |
| 29 | `seo-gateway-architect` | Gateway page strategy (Naver/Google) |
| 30 | `seo-gateway-builder` | Gateway page content generation |
| 31 | `seo-competitor-intel` | Competitor profiling, benchmarking, threat scoring |
| 32 | `seo-crawl-budget` | Log analysis, bot profiling, crawl waste detection |
| 33 | `seo-migration-planner` | Site migration planning, redirect mapping, monitoring |
| 34 | `seo-reporting-dashboard` | Executive reports, HTML dashboards, data aggregation |
### Notion Tools (31-39)
| # | Skill | Purpose |
|---|-------|---------|
| 31 | `notion-organizer` | Notion workspace management |
| 32 | `notion-writer` | Content writing to Notion |
### Jamie Clinic (40-49)
| # | Skill | Purpose |
|---|-------|---------|
| 40 | `jamie-brand-editor` | Branded content generation |
| 41 | `jamie-brand-audit` | Content review/compliance |
| 42 | `jamie-faq-entry` | KakaoTalk Kanana chatbot Q&A entries |
| 43 | `jamie-youtube-manager` | YouTube SEO audit & management |
| 44 | `jamie-youtube-subtitle-checker` | YouTube subtitle validation |
| 45 | `jamie-instagram-manager` | Instagram account management |
| 46 | `jamie-journal-editor` | Journal/blog content for journal.jamie.clinic |
| 47 | `jamie-marketing-editor` | Multi-channel marketing content & ad copy |
### NotebookLM Tools (50-59)
| # | Skill | Purpose |
|---|-------|---------|
| 50 | `notebooklm-agent` | Q&A from notebooks with source citations |
| 51 | `notebooklm-automation` | Notebook/source/artifact management |
| 52 | `notebooklm-studio` | Content generation (podcasts, videos, quizzes) |
| 53 | `notebooklm-research` | Web/Drive research & source discovery |
**Prerequisites:** `pip install notebooklm-py && playwright install chromium && notebooklm login`
### GTM/GA Tools (60-62)
| # | Skill | Purpose |
|---|-------|---------|
| 60 | `gtm-audit` | GTM container audit — page scan, site audit, gap analysis, tag design (DTM Agent + Chrome DevTools MCP) |
| 61 | `gtm-editor` | GTM tag/trigger/variable creation via API, ES5 Custom HTML, dataLayer generation, workspace lifecycle |
| 62 | `gtm-validator` | GTM QA — tag firing verification, trigger testing, dataLayer schema, naming conventions, cross-platform mapping |
### D.intelligence Agent Corps (70-79)
| # | Skill | Purpose | Autonomy |
|---|-------|---------|----------|
| 70 | `dintel-brand-guardian` | Brand compliance review (100pt checklist) | Auto |
| 71 | `dintel-brand-editor` | Brand-compliant copywriting & style evaluation | Auto + Ask |
| 72 | `dintel-doc-secretary` | Document formatting, meeting notes, reports | Draft & Wait |
| 73 | `dintel-quotation-mgr` | Quotation generation (4 sub-agents) | Draft & Wait |
| 74 | `dintel-service-architect` | Service scope design & module recommendation | Inquiry-driven |
| 75 | `dintel-marketing-mgr` | Content pipeline (Magazine D., newsletter, LinkedIn) | Draft & Wait |
| 76 | `dintel-backoffice-mgr` | Invoicing, contracts, NDA, HR operations | Draft & Wait |
| 77 | `dintel-account-mgr` | Client relationship management & Notion monitoring | Mixed |
| 79 | `dintel-skill-update` | Cross-skill consistency management (meta-agent) | Triggered |
**Shared infrastructure:** `_dintel-shared/` (Python package + reference docs)
**Install:** `cd custom-skills/_dintel-shared && ./install.sh --all`
**User Guide:** `custom-skills/_dintel-shared/USER-GUIDE.md`
### System & Utility Tools (80-82)
| # | Skill | Purpose |
|---|-------|---------|
| 80 | `claude-settings-optimizer` | Claude settings optimization & token efficiency audit |
| 81 | `mac-optimizer` | macOS system health audit & optimization (Claude Code only) |
| 82 | `tui-design-template` | TUI wizard interface design (Norton Commander / Gopher style, Rich) |
### Reference Curator & Multi-Agent (90-91)
| # | Skill | Purpose |
|---|-------|---------|
| 90 | `reference-curator` | Modular reference documentation suite (6 sub-skills + pipeline orchestrator) |
| 91 | `multi-agent-guide` | Multi-agent collaboration setup & guardrails |
**Reference Curator Sub-skills:**
| Sub-skill | Purpose |
|-----------|---------|
| `reference-discovery` | Search & validate authoritative sources |
| `web-crawler-orchestrator` | Multi-backend crawling (Firecrawl/Node/aiohttp/Scrapy) |
| `content-repository` | MySQL storage with version tracking |
| `content-distiller` | Summarization & key concept extraction |
| `quality-reviewer` | QA loop with approve/refactor/research routing |
| `markdown-exporter` | Export to markdown or JSONL for fine-tuning |
**Pipeline Command:** `/reference-curator "topic" --max-sources 5`
## Dual-Platform Architecture
Each skill supports both Claude Code and Claude Desktop:
```
XX-skill-name/
├── code/ # Claude Code version
│ ├── CLAUDE.md # Action-oriented directive
│ ├── scripts/ # Executable Python/Bash
│ └── docs/ # Documentation
├── desktop/ # Claude Desktop version
│ ├── SKILL.md # Skill directive with YAML frontmatter
│ ├── skill.yaml # Extended metadata (optional)
│ └── tools/ # MCP tool documentation
├── shared/ # Shared resources (optional)
└── README.md # Overview
```
## Repository Structure
```
our-claude-skills/
├── custom-skills/
│ ├── _ourdigital-shared/ # Shared config, installer, dependencies
│ ├── _dintel-shared/ # D.intelligence shared infra (Python pkg, refs)
│ │
│ ├── 01-10 (OurDigital core)
│ ├── 11-34 (SEO tools)
│ ├── 31-32 (Notion tools)
│ ├── 40-47 (Jamie clinic)
│ ├── 50-53 (NotebookLM tools)
│ ├── 60-62 (GTM/GA tools)
│ ├── 70-79 (D.intelligence Agent Corps)
│ ├── 80-82 (System & utility tools)
│ ├── 90-reference-curator/
│ └── 91-multi-agent-guide/
├── example-skills/ # Anthropic reference examples
├── official-skills/ # 3rd party skills (Notion)
├── reference/ # Skill format documentation
├── .claude/commands/ # Slash command definitions
├── CLAUDE.md # Development guidelines
├── AGENTS.md # Agent routing guide
└── README.md # This file
```
## Shared Environment
The `_ourdigital-shared/` directory provides:
- **install.sh** - Cross-machine installer
- **.env.ourdigital.template** - Environment variables template
- **requirements/** - Python dependencies (base, code)
- **scripts/** - Validation utilities
### Required Credentials
| Service | Variable | Purpose |
|---------|----------|---------|
| Notion | `NOTION_API_TOKEN` | Notion API access |
| Ghost Blog | `GHOST_BLOG_ADMIN_KEY` | blog.ourdigital.org |
| Ghost Journal | `GHOST_JOURNAL_ADMIN_KEY` | journal.ourdigital.org |
| Figma | `FIGMA_ACCESS_TOKEN` | Design integration |
## Usage
### Claude Code
The Quick Install symlinks the **slash commands** into `~/.claude/commands/`. To
also load a skill natively, symlink its **root** directory (which holds the
loadable `SKILL.md`) into `~/.claude/skills/`, using the clean name without the
`NN-` prefix:
```bash
# From the repo root — symlink a skill into Claude Code
ln -sf "$PWD/custom-skills/16-seo-schema-validator" ~/.claude/skills/seo-schema-validator
```
> Legacy skills that don't yet have a root `SKILL.md` expose it under
> `code/SKILL.md` instead — symlink `.../<skill>/code` for those.
### Claude Desktop
Import the skill's `desktop/` folder (containing `SKILL.md` + `skill.yaml`) via
your Claude Desktop skills settings.
## Development
See `CLAUDE.md` for detailed skill development guidelines and `AGENTS.md` for agent routing recommendations.
### Creating New Skills
```bash
# Use the skill creator
python example-skills/skills-main/skill-creator/scripts/init_skill.py <name> --path custom-skills/
```
---
**OurDigital** | Internal Use Only