agentleFS
m2ai-mcp-serversm2ai-mcp-servers/claude-skills/skills/get-api-docs/SKILL.md

get-api-docs

Skill0 starsChanged 7 months agoMITView on GitHub

Use the chub CLI to fetch curated, versioned API documentation before writing code against external APIs. This prevents hallucinated API calls and ensures correct SDK usage. 20 entries including: airtable, amplitude, anthropic/claude-api, asana, assemblyai, atlassian/confluence, auth0, aws/s3, binance, braintree, chromadb, clerk, cloudflare/workers, cockroachdb, cohere, datadog, deepgram, deepl, deepseek, directus. Run chub search to get the current full list.

4 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

10 rules. 0 are common, 4 are distinctive, and 6 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 6

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use the chub CLI to fetch curated, versioned API documentation before writing code against external APIs.

    line 7
  2. Distinctive:

    Before implementing code that calls an external API or SDK

    line 11
  3. Distinctive:

    When unsure about correct API parameters, methods, or patterns

    line 12
  4. Distinctive:

    When the user asks about how to use a specific service's API

    line 13
  5. Very specific:

    Annotate: if you discover gaps: chub annotate stripe/api "webhook needs raw body"

    line 48
  6. Very specific:

    Rate: after use: chub feedback stripe/api up

    line 49
  7. Very specific:

    Run chub search to get the current full list.

    line 55
  8. Distinctive:

    Always fetch docs BEFORE writing API integration code, not after

    line 59
  9. Very specific:

    Use --lang py or --lang js to get language-specific examples

    line 60
  10. Very specific:

    Use --full sparingly — it returns all reference files and uses more tokens

    line 61

“Common” is measured: kept by at least 6 in 10 of the 4 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

Skill: Get API Documentation via Context Hub

Use the chub CLI to fetch curated, versioned API documentation before writing code against external APIs. This prevents hallucinated API calls and ensures correct SDK usage.

When to Use

  • Before implementing code that calls an external API or SDK
  • When unsure about correct API parameters, methods, or patterns
  • When the user asks about how to use a specific service's API

Commands

# Search for available docs (no query lists all)
chub search [query]

# Fetch documentation by ID (with language variant)
chub get <id> --lang py    # Python docs
chub get <id> --lang js    # JavaScript/TypeScript docs
chub get <id>              # Default (usually JS)

# Fetch full docs (all reference files)
chub get <id> --lang py --full

# Fetch specific reference file (token-efficient)
chub get <id> --file <filename>

# Add persistent annotation when you discover a gap or workaround
chub annotate <id> "note about what you learned"

# View existing annotations
chub annotate --list

# Rate documentation quality
chub feedback <id> up      # Helpful
chub feedback <id> down    # Needs improvement

Workflow

  1. Search for the relevant API: chub search "stripe"
  2. Fetch language-specific docs: chub get stripe/api --lang js
  3. Read the output and use it as the source of truth for API calls
  4. Annotate if you discover gaps: chub annotate stripe/api "webhook needs raw body"
  5. Rate after use: chub feedback stripe/api up

Available Docs (as of 2026-03-07)

20 entries including: airtable, amplitude, anthropic/claude-api, asana, assemblyai, atlassian/confluence, auth0, aws/s3, binance, braintree, chromadb, clerk, cloudflare/workers, cockroachdb, cohere, datadog, deepgram, deepl, deepseek, directus.

Run chub search to get the current full list.

Important

  • Always fetch docs BEFORE writing API integration code, not after
  • Use --lang py or --lang js to get language-specific examples
  • Use --full sparingly — it returns all reference files and uses more tokens
  • Annotations persist locally across sessions — use them to build knowledge

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.