Skillsbench auto-skill-generator
install
source · Clone the upstream repo
git clone https://github.com/benchflow-ai/skillsbench
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/benchflow-ai/skillsbench "$T" && mkdir -p ~/.claude/skills && cp -r "$T/.claude/skills/docs-to-skill" ~/.claude/skills/benchflow-ai-skillsbench-auto-skill-generator && rm -rf "$T"
manifest:
.claude/skills/docs-to-skill/SKILL.mdsource content
Auto Skill Generator
Generate skills by researching and crawling authoritative documentation.
Tool: fetch_docs.py
# Search - returns all URLs with snippets python scripts/fetch_docs.py search "Modal GPU Python documentation" # Crawl - with domain/path filtering to stay focused python scripts/fetch_docs.py crawl \ --url https://modal.com/docs/guide/gpu \ --no-external \ --select-paths "/docs/.*" \ --instructions "Focus on GPU setup and code examples" \ --limit 30
Workflow
1. Search for Documentation
python scripts/fetch_docs.py search "{topic} documentation"
Returns JSON with all URLs, titles, scores, and content snippets.
2. Select Best URL
Review search results and select based on:
- Official docs:
,*.com/docs/
,docs.*.com*.readthedocs.io - Content relevance: Check snippets for API docs, code examples
- Avoid: Blog posts, changelogs, marketing, glossaries
3. Crawl with Filtering
python scripts/fetch_docs.py crawl \ --url {selected_url} \ --no-external \ --select-paths "/docs/.*" "/guide/.*" \ --instructions "Focus on API methods and code examples"
Core Parameters:
| Parameter | Description |
|---|---|
| Required. URL to crawl |
| Natural language guidance for crawler |
| Total pages (default: 50) |
| Link depth (default: 2) |
Domain/Path Filtering (Critical):
| Parameter | Description |
|---|---|
| Block external domains |
| Regex patterns to include (e.g., ) |
| Regex patterns to exclude (e.g., ) |
| Regex for allowed domains |
| Regex for blocked domains |
Quality Options:
| Parameter | Description |
|---|---|
| (1 credit/5 URLs) or (2 credits/5 URLs) |
| or |
| Seconds (10-150, default: 150) |
4. Generate Skill File
From crawled content, create:
--- name: {topic-slug}ß description: > {What the skill does}. Use when: {specific triggers}. --- # {Topic Name} ## Quick Start ## Core API ## Common Patterns
Output
- Location:
~/.claude/skills/{topic-slug}/SKILL.md - Extract ALL code blocks from crawled content
- Keep SKILL.md under 500 lines; split to
if longerreferences/