agentleFS
XakkiXakki/ai-agents-skills/skills/api-docs-sync/SKILL.md

api-docs-sync

Skill6 starsChanged 3 months agoMITView on GitHub

Reconcile API documentation, OpenAPI artifacts, documentation UIs and public capability catalogs (llms.txt, indexes) with the shipped implementation. Use when API docs may have drifted from routes or schemas. RU: документация API, openapi, llms.txt.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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:

    Use implementation, route and schema declarations as evidence for public claims.

    line 9

≈ “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

API documentation

Use implementation, route and schema declarations as evidence for public claims. Identify the canonical source, generated artifacts, public surfaces, supported tools and authorized scope before editing. Preserve unrelated work and follow the project's conventions.

Reconcile documentation with shipped routes, request and response shapes, authorization, entitlements and limitations. Change canonical inputs first, then regenerate only affected derived artifacts with the project's supported commands. Verify source and generated output for drift and stale claims; never assume a specific build target exists or hand-edit generated output as a substitute for fixing its source. Runtime-generated specifications need runtime verification.

For public API indexes, llms.txt, sitemaps and similar capability catalogs, use the public capability catalog checklist: verify claims against the implementation, reconcile counts and localized entries and boundaries against evidence, and document the actual protocol, authentication and freshness limits. A catalog-only change does not by itself require OpenAPI generation, container builds or a commit.

For self-hosted documentation UIs, use the UI asset checklist. A page with no third-party startup requests, a build that does not download UI assets, and an entirely offline rebuild are separate claims.

For operation-level authentication metadata or a generator that cannot write to its default output, use schema verification. Run proportionate project checks for the changed contract, including relevant authentication behavior and documentation drift. Report commands, actual outcomes and skipped checks, and distinguish unchanged artifacts from regenerated changes. Preserve existing staged work and commit only when authorized under the project policy.

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.