agentleFS
wangyendtwangyendt/wayne-skills/alapi/SKILL.md

alapi

Skill9 starsChanged 9 months agoMITView on GitHub

Comprehensive ALAPI skill covering the full bundled ALAPI OpenAPI catalog. Use when the user mentions ALAPI, alapi, ALAPI_TOKEN, openapi.json, or an ALAPI path like /api/..., or asks to find which ALAPI API matches a business need, choose between similar ALAPI endpoints, explain request fields, prepare or execute a request, or troubleshoot an ALAPI response. Covers inspirational content, articles, news and hotlists, AI chat/translation/NLP, OCR and document recognition, weather and calendar data, IP/phone/ID/domain/ICP/enterprise lookup and verification, finance/exchange/gold/oil/crypto market data, music/media/video/TTS, URL/QR tools, and related utility APIs.

The file

Show its rules and text

We split this skill into the rules it gives an agent

14 rules. About 0 are common, 7 are distinctive, and 7 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 7

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill to work against the full ALAPI OpenAPI catalog without hand-parsing the schema each time.

    line 10
  2. Very specific:

    If the token is missing, tell the user to request one from https://apifox.com/apihub/, then ask them to send it back.

    line 15
  3. Distinctive:

    After the user sends the token, persist it to the active shell profile, export it in the current session, and avoid echoing it back in logs.

    line 16
  4. Very specific:

    Use references/intent-router.md first to map a user request to the most likely endpoint with minimal context cost.

    line 17
  5. Very specific:

    Use scripts/alapi_request.py for real calls instead of rewriting HTTP boilerplate.

    line 19
  6. Very specific:

    If the OpenAPI source changes, replace references/openapi-source.json and rerun scripts/generate_references.py.

    line 20
  7. Very specific:

    All endpoints in the bundled OpenAPI spec use POST

    line 25
  8. Very specific:

    All endpoints use application/json request bodies

    line 26
  9. Distinctive:

    If the token is missing:

    line 33
  10. Distinctive:

    Ask the user to send the token

    line 36
  11. Distinctive:

    After receiving it, persist it based on the active shell:

    line 37
  12. Distinctive:

    Do not invent or reuse placeholder tokens for real requests.

    line 42
  13. Very specific:

    Use rg '^### /api/' references/api-catalog.md to jump to a path quickly.

    line 51
  14. Distinctive:

    When answering a user with this skill:

    line 60

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

ALAPI

Overview

Use this skill to work against the full ALAPI OpenAPI catalog without hand-parsing the schema each time. The skill bundles the raw OpenAPI source, a generated endpoint catalog, an auth guide, and a reusable request script.

Workflow

  1. Confirm whether ALAPI_TOKEN is available.
  2. If the token is missing, tell the user to request one from https://apifox.com/apihub/, then ask them to send it back.
  3. After the user sends the token, persist it to the active shell profile, export it in the current session, and avoid echoing it back in logs.
  4. Use references/intent-router.md first to map a user request to the most likely endpoint with minimal context cost.
  5. Open references/api-catalog.md only for the exact endpoint you selected.
  6. Use scripts/alapi_request.py for real calls instead of rewriting HTTP boilerplate.
  7. If the OpenAPI source changes, replace references/openapi-source.json and rerun scripts/generate_references.py.

Authentication

  • ALAPI uses header auth: token: $ALAPI_TOKEN
  • All endpoints in the bundled OpenAPI spec use POST
  • All endpoints use application/json request bodies
  • Base URL: https://v3.alapi.cn

Token Handling

Run printenv ALAPI_TOKEN first.

If the token is missing:

  • Tell the user to申请或管理 ALAPI token at https://apifox.com/apihub/
  • Ask the user to send the token
  • After receiving it, persist it based on the active shell:
    • zsh: append export ALAPI_TOKEN='...' to ~/.zshrc
    • bash: append export ALAPI_TOKEN='...' to ~/.bashrc
  • Also export it in the current shell before making API calls

Do not invent or reuse placeholder tokens for real requests.

References

  • references/auth-and-usage.md: auth model, calling conventions, error-handling checklist
  • references/intent-router.md: lowest-cost full routing table from common intent to endpoint
  • references/api-catalog.md: endpoint-by-endpoint reference including purpose and request schema
  • references/openapi-source.json: bundled ALAPI OpenAPI source of truth

Use rg '^### /api/' references/api-catalog.md to jump to a path quickly.

Scripts

  • scripts/alapi_request.py: send authenticated ALAPI requests with JSON bodies
  • scripts/generate_references.py: regenerate the reference markdown files from references/openapi-source.json

Response Discipline

When answering a user with this skill:

  • State the selected endpoint path explicitly
  • Explain why that endpoint matches the request
  • Show the required JSON body fields
  • Mention that auth is via ALAPI_TOKEN
  • Summarize the API response instead of dumping raw JSON unless the user asks for the full payload

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.