agentleFS
quochuydevquochuydev/kit/skills/research-apis/SKILL.md

research-apis

Skill0 starsChanged 8 months agoMITView on GitHub

Use when the user wants to research a third-party API, learn how to set up a developer account, get API keys, or see example requests. Triggers on requests to explore, integrate, or understand external APIs.

  • Reads credentials

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    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
  1. Distinctive:

    If the user does NOT specify which API or service to research, ASK:

    line 13
  2. Distinctive:

    Use WebSearch and WebFetch to find official API documentation

    line 79
  3. Distinctive:

    Always show curl first, then a library example (pick the most popular SDK/library for that API)

    line 80
  4. Distinctive:

    If the API has a sandbox/test mode, note it in the authentication section

    line 83
  5. Distinctive:

    If official docs are unclear, state what is uncertain rather than guessing

    line 84

≈ “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.

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

Research APIs

Research third-party APIs and produce a ready-to-use integration guide with working examples.

Process

If the user does NOT specify which API or service to research, ASK:

What API or service would you like to research? (e.g., Stripe, AccessTrade, Shopify, Twilio)

Once the API is known, research and produce the output below.

Output Format

Generate a markdown file saved to docs/api-research/{api-name}.md with this structure:

# {API Name} — API Research

## 1. Developer Account Setup

| Step | Action |
|------|--------|
| 1 | Go to `{signup-url}` |
| 2 | {Registration steps} |
| 3 | {Verification or approval process} |
| ... | ... |

**Approval time:** {instant / X days / manual review}

## 2. API Key / Authentication

| Item | Detail |
|------|--------|
| **Auth type** | {API key / OAuth2 / Bearer token / etc.} |
| **Where to find** | {Dashboard path to get credentials} |
| **Header format** | `{e.g., Authorization: Bearer <token>}` |
| **Rate limits** | {requests per second/minute if known} |

## 3. API Examples

### {Endpoint name} — {short description}

**curl**

\`\`\`bash
curl -X {METHOD} '{full-url}' \
  -H 'Authorization: Bearer <YOUR_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{request-body}'
\`\`\`

**Sample Response**

\`\`\`json
{
  "status": 200,
  "data": { ... }
}
\`\`\`

**{Library name}** ({language})

\`\`\`{language}
{library code example}
\`\`\`

(Repeat for each relevant endpoint)

Rules

  • Use WebSearch and WebFetch to find official API documentation
  • Always show curl first, then a library example (pick the most popular SDK/library for that API)
  • Include real endpoint URLs from official docs — do not fabricate URLs
  • Include sample request bodies and sample responses based on official docs
  • If the API has a sandbox/test mode, note it in the authentication section
  • If official docs are unclear, state what is uncertain rather than guessing
  • Group endpoints by the user's use case, not by the full API surface — only cover what the user needs

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.