agentleFS
srikanth-manivannansrikanth-manivannan/claude-agent-factory/skills/backend/openapi-designer/SKILL.md

openapi-designer

Skill1 starsChanged 5 months agoMITView on GitHub

Use this to design and lint an OpenAPI specification from requirements before any code is written.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Design status codes + errors: Use correct HTTP semantics.

    line 49
  2. Very specific:

    Specify auth + security: Add securitySchemes and apply them.

    line 51

≈ “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

OpenAPI Designer

Use this to design and lint an OpenAPI specification from requirements before any code is written.

Tech profile — Technology: REST API · Language: n/a · Stack: OpenAPI 3.1 · Toolchain: any · Domain: backend (Contract-first: produces a portable OpenAPI spec, independent of server language.)

When to use this skill

  • Designing a new REST API contract-first, before implementation.
  • Formalizing an existing/implicit API into a reviewable OpenAPI spec.
  • Producing the contract that backend/rest-endpoint-scaffold and consumers build against.

When NOT to use this skill

  • GraphQL/gRPC — use backend/graphql-schema-builder (or the gRPC equivalent).
  • Implementing endpoints — use backend/rest-endpoint-scaffold.
  • Generating reference docs from a spec — use documentation/api-reference-generator.

Prerequisites

  • The API's purpose, its resources, and the operations clients need.

Inputs

InputRequiredDescription
requirementsyesWhat the API must let clients do
resourcesnoDomain resources/entities, if known
auth_modelnoAuth scheme (e.g. bearer/OAuth); flagged if unspecified

Instructions

  1. Model resources + operations. Derive resources and their CRUD/actions from the requirements; map to REST paths and methods.
  2. Define schemas. Specify request/response schemas as reusable components (DRY); include types, required fields, formats, and constraints.
  3. Design status codes + errors. Use correct HTTP semantics; define a consistent error response schema; cover success, client-error, and server-error cases.
  4. Specify auth + security. Add securitySchemes and apply them; if auth_model is unspecified, flag it (don't leave the API open by omission — /standards/security.md).
  5. Add pagination/filtering for collection endpoints; be consistent across the API.
  6. Lint the spec. Validate OpenAPI 3.1 correctness; check naming consistency, missing descriptions, and unused components.
  7. Document each operation with a summary + example; produce an example request/response.

Output

A valid OpenAPI 3.1 document: paths + operations, reusable component schemas, consistent error model, security schemes, pagination, and per-operation descriptions/examples — plus a lint summary. Ready for backend/rest-endpoint-scaffold and documentation/api-reference-generator.

Constraints & safety

  • Correct HTTP semantics (status codes, idempotency, methods).
  • Security explicit, never implicit — unspecified auth is flagged.
  • DRY schemas via components; consistent naming (/standards/naming.md).

Examples

Minimal below; full examples in EXAMPLES.md.

Given: "Clients manage tasks (list, create, get, complete)." Produces: an OpenAPI 3.1 spec with /tasks + /tasks/{id} operations, a Task component schema, a shared Error schema, bearer auth, and paginated list responses.

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.