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

Fix SEO skills 19-34 bugs, add slash commands, enhance reference-curator (#3)

Browse Source 
* Fix SEO skill 34 bugs, Korean labels, and transition Ahrefs refs to our-seo-agent

P0: Fix report_aggregator.py — wrong SKILL_REGISTRY[33] mapping, missing
CATEGORY_WEIGHTS for 7 categories, and break bug in health score parsing
that exited loop even on parse failure.

P1: Remove VIEW tab references from skill 20, expand skill 32 docs,
replace Ahrefs MCP references across all 16 skills (19-28, 31-34)
with our-seo-agent CLI data source references.

P2: Fix Korean labels in executive_report.py and dashboard_generator.py,
add tenacity to base requirements, sync skill 34 base_client.py with
canonical version from skill 12.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* Add Claude Code slash commands for SEO skills 19-34 and fix stale paths

Create 14 new slash command files for skills 19-28, 31-34 so they
appear as /seo-* commands in Claude Code. Also fix stale directory
paths in 8 existing commands (skills 12-18, 29-30) that referenced
pre-renumbering skill directories.

Update .gitignore to track .claude/commands/ while keeping other
.claude/ files ignored.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* Add 8 slash commands, enhance reference-curator with depth/output options

- Add slash commands: ourdigital-brand-guide, notion-writer, notebooklm-agent,
  notebooklm-automation, notebooklm-studio, notebooklm-research,
  reference-curator, multi-agent-guide
- Add --depth (light/standard/deep/full) with Firecrawl parameter mapping
- Add --output with ~/Documents/reference-library/ default and user confirmation
- Increase --max-sources default from 10 to 100
- Rename /reference-curator-pipeline to /reference-curator
- Simplify web-crawler-orchestrator label to web-crawler in docs

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Andrew Yim
2026-02-24 14:12:57 +09:00
committed by GitHub
parent 59e5c519f5
commit 397fa2aa5d
33 changed files with 1699 additions and 48 deletions
Download Patch File Download Diff File Expand all files Collapse all files

233
.claude/commands/reference-curator.md Normal file
View File

@@ -0,0 +1,233 @@
---
description: Full reference curation pipeline - discovery, crawl, store, distill, review, export with configurable depth
argument-hint: <topic|urls|manifest> [--depth light|standard|deep|full] [--output ~/Documents/reference-library/] [--max-sources 100] [--auto-approve] [--export-format project_files]
allowed-tools: WebSearch, WebFetch, Read, Write, Bash, Grep, Glob, Task
---
# Reference Curator Pipeline
Full-stack orchestration of the 6-skill reference curation workflow.
## Input Modes
| Mode | Input Example | Pipeline Start |
|------|---------------|----------------|
| **Topic** | `"Claude system prompts"` | reference-discovery |
| **URLs** | `https://docs.anthropic.com/...` | web-crawler (skip discovery) |
| **Manifest** | `./manifest.json` | web-crawler (resume) |
## Arguments
- `<input>`: Required. Topic string, URL(s), or manifest file path
- `--depth`: Crawl depth level (default: `standard`). See Depth Levels below
- `--output`: Output directory path (default: `~/Documents/reference-library/`)
- `--max-sources`: Max sources to discover (default: 100)
- `--max-pages`: Max pages per source to crawl (default varies by depth)
- `--auto-approve`: Auto-approve scores above threshold
- `--threshold`: Approval threshold (default: 0.85)
- `--max-iterations`: Max QA loop iterations per document (default: 3)
- `--export-format`: `project_files`, `fine_tuning`, `jsonl` (default: project_files)
- `--include-subdomains`: Include subdomains in site mapping (default: false)
- `--follow-external`: Follow external links found in content (default: false)
## Output Directory
**IMPORTANT: Never store output in any claude-skills, `.claude/`, or skill-related directory.**
The `--output` argument sets the base path for all pipeline output. If omitted, the default is `~/Documents/reference-library/`.
### Directory Structure
```
{output}/
├── {topic-slug}/ # One folder per pipeline run
│ ├── README.md # Index with table of contents
│ ├── 00-page-name.md # Individual page files
│ ├── 01-page-name.md
│ ├── ...
│ ├── {topic-slug}-complete.md # Combined bundle (all pages)
│ └── manifest.json # Crawl metadata
├── pipeline_state/ # Resume state (auto-managed)
│ └── run_XXX/state.json
└── exports/ # Fine-tuning / JSONL exports
```
### Resolution Rules
1. If `--output` is provided, use that path exactly
2. If not provided, use `~/Documents/reference-library/`
3. **Before writing any files**, check if the output directory exists
4. If the directory does NOT exist, **ask the user for permission** before creating it:
- Show the full resolved path that will be created
- Wait for explicit user approval
- Only then run `mkdir -p <path>`
5. The topic slug is derived from the input (URL domain+path or topic string)
### Examples
```bash
# Uses default: ~/Documents/reference-library/glossary-for-wordpress/
/reference-curator https://docs.codeat.co/glossary/
# Custom path: /tmp/research/mcp-docs/
/reference-curator "MCP servers" --output /tmp/research
# Explicit home subfolder: ~/Projects/client-docs/api-reference/
/reference-curator https://api.example.com/docs --output ~/Projects/client-docs
```
## Depth Levels
### `--depth light`
Fast scan for quick reference. Main content only, minimal crawling.
| Parameter | Value |
|-----------|-------|
| `onlyMainContent` | `true` |
| `formats` | `["markdown"]` |
| `maxDiscoveryDepth` | 1 |
| `max-pages` default | 20 |
| Map limit | 50 |
| `deduplicateSimilarURLs` | `true` |
| Follow sub-links | No |
| JS rendering wait | None |
**Best for:** Quick lookups, single-page references, API docs you already know.
### `--depth standard` (default)
Balanced crawl. Main content with links for cross-referencing.
| Parameter | Value |
|-----------|-------|
| `onlyMainContent` | `true` |
| `formats` | `["markdown", "links"]` |
| `maxDiscoveryDepth` | 2 |
| `max-pages` default | 50 |
| Map limit | 100 |
| `deduplicateSimilarURLs` | `true` |
| Follow sub-links | Same-domain only |
| JS rendering wait | None |
**Best for:** Documentation sites, plugin guides, knowledge bases.
### `--depth deep`
Thorough crawl. Full page content including sidebars, nav, and related pages.
| Parameter | Value |
|-----------|-------|
| `onlyMainContent` | `false` |
| `formats` | `["markdown", "links", "html"]` |
| `maxDiscoveryDepth` | 3 |
| `max-pages` default | 150 |
| Map limit | 300 |
| `deduplicateSimilarURLs` | `true` |
| Follow sub-links | Same-domain + linked resources |
| JS rendering wait | `waitFor: 3000` |
| `includeSubdomains` | `true` |
**Best for:** Complete product documentation, research material, sites with sidebars/code samples hidden behind tabs.
### `--depth full`
Exhaustive crawl. Everything captured including raw HTML, screenshots, and external references.
| Parameter | Value |
|-----------|-------|
| `onlyMainContent` | `false` |
| `formats` | `["markdown", "html", "rawHtml", "links"]` |
| `maxDiscoveryDepth` | 5 |
| `max-pages` default | 500 |
| Map limit | 1000 |
| `deduplicateSimilarURLs` | `false` |
| Follow sub-links | All (same-domain + external references) |
| JS rendering wait | `waitFor: 5000` |
| `includeSubdomains` | `true` |
| Screenshots | Capture for JS-heavy pages |
**Best for:** Archival, migration references, preserving sites, training data collection.
## Depth Comparison
```
light ████░░░░░░░░░░░░ Speed: fastest Pages: ~20 Content: main only
standard ████████░░░░░░░░ Speed: fast Pages: ~50 Content: main + links
deep ████████████░░░░ Speed: moderate Pages: ~150 Content: full page + HTML
full ████████████████ Speed: slow Pages: ~500 Content: everything + raw
```
## Pipeline Stages
```
1. reference-discovery (topic mode only)
2. web-crawler ← depth controls this stage
3. content-repository
4. content-distiller <--------+
5. quality-reviewer |
+-- APPROVE -> export |
+-- REFACTOR -----------------+
+-- DEEP_RESEARCH -> crawler -+
+-- REJECT -> archive
6. markdown-exporter
```
## Crawl Execution by Depth
When executing the crawl (Stage 2), apply the depth settings to the Firecrawl tools:
### Site Mapping (`firecrawl_map`)
```
firecrawl_map:
url: <target>
limit: {depth.map_limit}
includeSubdomains: {depth.includeSubdomains}
```
### Page Scraping (`firecrawl_scrape`)
```
firecrawl_scrape:
url: <page>
formats: {depth.formats}
onlyMainContent: {depth.onlyMainContent}
waitFor: {depth.waitFor} # deep/full only
excludeTags: ["nav", "footer"] # light/standard only
```
### Batch Crawling (`firecrawl_crawl`) - for deep/full only
```
firecrawl_crawl:
url: <target>
maxDiscoveryDepth: {depth.maxDiscoveryDepth}
limit: {depth.max_pages}
deduplicateSimilarURLs: {depth.dedup}
scrapeOptions:
formats: {depth.formats}
onlyMainContent: {depth.onlyMainContent}
waitFor: {depth.waitFor}
```
## Example Usage
```bash
# Quick scan of a single doc page
/reference-curator https://docs.example.com/api --depth light
# Standard documentation crawl (default)
/reference-curator "Glossary for WordPress" --max-sources 5
# Deep crawl capturing full page content and HTML
/reference-curator https://docs.codeat.co/glossary/ --depth deep
# Full archival crawl with all formats
/reference-curator https://docs.anthropic.com --depth full --max-pages 300
# Deep crawl with auto-approval and fine-tuning export
/reference-curator "MCP servers" --depth deep --auto-approve --export-format fine_tuning
```
## Related Sub-commands
Individual stages available at: `custom-skills/90-reference-curator/commands/`
- `/reference-discovery`, `/web-crawler`, `/content-repository`
- `/content-distiller`, `/quality-reviewer`, `/markdown-exporter`
## Source
Full details: `custom-skills/90-reference-curator/README.md`