agentleFS
sammcjsammcj/agentic-coding/Skills/find-docs/SKILL.md

find-docs

Skill167 starsChanged 10 days agoApache-2.0View on GitHub

Retrieves up-to-date documentation, API references and code examples for any developer technology. Use when the user asks about, or you need docs for, a specific library, framework, SDK, CLI tool or cloud service - even well-known ones, as training data may be outdated. Prefer this over web search for library docs and API details.

  • Reads credentials

We split this skill into the rules it gives an agent

12 rules. 7 are common, 1 is distinctive, and 4 are very specific to this project.

  • 7

    Common

    Most of the 25 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run the context7 CLI directly like so:

    line 15
  2. Very specific:

    Use the official library name with its punctuation ("Next.js" not nextjs, "Three.js" not threejs).

    line 47
  3. Common:

    If multiple good matches exist, acknowledge this but proceed with the most relevant one

    line 72
  4. Common:

    If no good matches exist, clearly state this and suggest query refinements

    line 73
  5. Common:

    If the user mentions a specific version, use a version-specific library ID:

    line 78
  6. Very specific:

    If you know the user's programming language, add --language so examples in that language rank first:

    line 100
  7. Common:

    If a command fails with a quota error ("Monthly quota reached" or "quota exceeded"):

    line 133
  8. Common:

    If they cannot or choose not to authenticate, answer from training knowledge and clearly note it may be outdated

    line 136
  9. Common:

    Do not silently fall back to training data - always tell the user why Context7 was not used.

    line 138
  10. Very specific:

    Always run ctx7 library first - ctx7 docs react "hooks" will fail without a valid ID

    line 143
  11. Very specific:

    Use descriptive queries, not single words - "React useEffect cleanup function" not "hooks"

    line 144
  12. Common:

    Do not include sensitive information (API keys, passwords, credentials) in queries

    line 146

“Common” is measured: kept by at least 6 in 10 of the 25 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Documentation Lookup

Retrieve current documentation and code examples for any library using the Context7 CLI.

Run the context7 CLI directly like so:

pnpx ctx7@latest <command>

Workflow

Two-step process: resolve the library name to an ID, then query docs with that ID.

# Step 1: Resolve library ID
ctx7 library <name> <query>

# Step 2: Query documentation
ctx7 docs <libraryId> <query>

You MUST call ctx7 library first to obtain a valid library ID UNLESS the user explicitly provides a library ID in the format /org/project or /org/project/version.

IMPORTANT: Do not run these commands more than 3 times per question. If you cannot find what you need after 3 attempts, use the best result you have.

Step 1: Resolve a Library

Resolves a package/product name to a Context7-compatible library ID and returns matching libraries.

ctx7 library React "How to clean up useEffect with async operations"
ctx7 library "Next.js" "How to set up app router with a proxy"
ctx7 library Prisma "How to define one-to-many relations with cascade delete"

Use the official library name with its punctuation ("Next.js" not nextjs, "Three.js" not threejs). If results look wrong, try an alternate spelling such as next.js before changing the query.

Always pass a query argument - it is required and directly affects result ranking. Use the user's intent to form the query, which helps disambiguate when multiple libraries share a similar name. Do not include any sensitive or confidential information such as API keys, passwords, credentials, personal data, or proprietary code in your query.

Result fields

Each result includes:

  • Library ID - Context7-compatible identifier (format: /org/project)
  • Name - Library or package name
  • Description - Short summary
  • Code Snippets - Number of available code examples
  • Source Reputation - Authority indicator (High, Medium, Low, or Unknown)
  • Benchmark Score - Quality indicator (100 is the highest score)
  • Versions - List of versions if available. Use one of those versions if the user provides a version in their query. The format is /org/project/version.

Selection process

  1. Analyse the query to understand what library/package the user is looking for
  2. Select the most relevant match based on:
    • Name similarity to the query (exact matches prioritised)
    • Description relevance to the query's intent
    • Documentation coverage (prioritise libraries with higher Code Snippet counts)
    • Source reputation (consider libraries with High or Medium reputation more authoritative)
    • Benchmark score (higher is better, 100 is the maximum)
  3. If multiple good matches exist, acknowledge this but proceed with the most relevant one
  4. If no good matches exist, clearly state this and suggest query refinements
  5. For ambiguous queries, request clarification before proceeding with a best-guess match

Version-specific IDs

If the user mentions a specific version, use a version-specific library ID:

# General (latest indexed)
ctx7 docs /vercel/next.js "How to set up app router"

# Version-specific
ctx7 docs /vercel/next.js/v16.2.9 "How to set up app router"

The available versions are listed in the ctx7 library output. Use the closest match to what the user specified.

Step 2: Query Documentation

Retrieves up-to-date documentation and code examples for the resolved library.

ctx7 docs /facebook/react "How to clean up useEffect with async operations"
ctx7 docs /vercel/next.js "How to add an authentication proxy to app router"
ctx7 docs /prisma/prisma "How to define one-to-many relations with cascade delete"

If you know the user's programming language, add --language so examples in that language rank first:

ctx7 docs /websites/twilio "How to send an SMS" --language Ruby

Writing good queries

The query directly affects the quality of results. Be specific and keep each query to one topic. For a question spanning distinct concepts, run a separate docs command per concept, unless the question is about how they interact. Do not include any sensitive or confidential information such as API keys, passwords, credentials, personal data, or proprietary code in your query.

  • Good: "How to set up authentication with JWT in Express.js"
  • Good: "React useEffect cleanup function with async operations"
  • Bad (vague): "auth", "hooks"
  • Bad (multi-topic): "routing and auth and caching in Next.js"

Describe what to look up in the docs rather than the task to complete. One-word queries return generic results. Multi-topic queries return shallow results for each topic.

The output contains two types of content: code snippets (titled, with language-tagged blocks) and info snippets (prose explanations with breadcrumb context).

Authentication

Works without authentication. For higher rate limits:

# Option A: environment variable
export CONTEXT7_API_KEY=your_key

# Option B: OAuth login
ctx7 login

Error Handling

If a command fails with a quota error ("Monthly quota reached" or "quota exceeded"):

  1. Inform the user their Context7 quota is exhausted
  2. Suggest they authenticate for higher limits: ctx7 login
  3. If they cannot or choose not to authenticate, answer from training knowledge and clearly note it may be outdated

Do not silently fall back to training data - always tell the user why Context7 was not used.

Common Mistakes

  • Library IDs require a / prefix - /facebook/react not facebook/react
  • Always run ctx7 library first - ctx7 docs react "hooks" will fail without a valid ID
  • Use descriptive queries, not single words - "React useEffect cleanup function" not "hooks"
  • One topic per query - split "routing and auth and caching" into one docs command per concept
  • Do not include sensitive information (API keys, passwords, credentials) in queries

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.