agentsclimarketplace

Api doc to tool spec

Skill alexzhu0/agent-ready-skills/skills/api-doc-to-tool-spec

Ten practical AI-agent skills for turning messy work into clear context, evals, reviews, and launch-ready artifacts.

Install
npx -y skills add alexzhu0/agent-ready-skills --skill api-doc-to-tool-spec

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Use when converting API documentation, endpoint notes, OpenAPI snippets, or integration docs into an agent-ready tool specification with capabilities, inputs, auth, examples, and operational risks.

SKILL.md

1.6 KB, as published. Nobody here has run it

API Doc To Tool Spec

Purpose

Turn API documentation into a compact tool specification an agent can safely use or hand to an implementer.

Fit

  • Use when source docs describe API behavior but an agent needs a safer tool contract before implementation or automation.
  • Do not use when the source is only product intent with no endpoint, auth, or data-shape evidence.

Inputs

  • Endpoint docs, OpenAPI snippets, SDK examples, or integration notes.
  • Auth requirements, rate limits, scopes, and sample requests if available.
  • The intended agent workflow or user task.

Workflow

  1. Identify each capability the API exposes in plain language.
  2. Extract required inputs, optional inputs, output shape, auth scopes, and errors.
  3. Mark unclear fields as assumptions instead of guessing.
  4. Separate read-only operations from write or destructive operations.
  5. Add one minimal example request and one expected response shape per core operation.

Output

Produce Markdown with:

  • Tool Summary
  • Capability Table
  • Inputs And Outputs
  • Auth And Rate Limits
  • Example Calls
  • Risks And Approval Gates
  • Open Questions

Validation

  • Every capability maps back to evidence in the source docs.
  • Required inputs are not mixed with optional inputs.
  • Auth scopes and write operations are explicit.
  • Unknown behavior is listed under open questions.
  • Examples are small and do not include real secrets or private data.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.