docs-fetcher
Skill2 starsChanged 11 months agoMITView on GitHub
Fetch up-to-date library documentation directly into context to prevent hallucinated APIs and outdated code examples. Use when user says "use docs", "fetch docs for [library]", "check [library] docs", or asks about a library's API, methods, or usage patterns and current documentation would be helpful. Also use proactively when generating code for libraries where version-specific accuracy matters.
In this repository5 other files it gives its agents.
- fastapi-code-reviewSkill
- hpe-copyrightSkill
- jira-workflowSkill
- multi-agent-debate-reviewSkill
- skill-creatorSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 46
Add entry following the existing format
- Distinctive: line 53
No version pinning — fetches current docs
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Docs Fetcher
Fetch current documentation for libraries to ensure accurate, up-to-date code generation.
Workflow
Trigger Detection
Activate this skill when:
- User explicitly requests: "use docs", "fetch docs for X", "check X documentation"
- User asks about specific API methods, parameters, or patterns for a supported library
- Generating code where version-specific accuracy is critical
Execution Steps
- Identify the library from user request or code context
- Look up documentation URLs in references/libraries.md
- Fetch relevant pages using
fetch_webpagetool with appropriate URLs - Use fetched content to inform code generation or answer
Fetching Strategy
For comprehensive coverage, fetch multiple pages:
fetch_webpage(urls: [
"https://fastapi.tiangolo.com/tutorial/dependencies/",
"https://fastapi.tiangolo.com/advanced/advanced-dependencies/"
])For quick lookups, fetch the most relevant single page.
Adding Libraries
To add a new library, edit references/libraries.md:
- Find the official documentation URL
- Identify key pages: quickstart, API reference, common patterns
- Add entry following the existing format
Limitations
- Fetches only explicitly listed URLs (no recursive crawling)
- Some documentation sites may block or limit fetches
- Very large pages may be truncated
- No version pinning — fetches current docs
When NOT to Use
- General programming questions not library-specific
- Libraries not in the mapping (inform user, suggest they provide URLs)
- Simple questions where training knowledge is sufficient
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

