メニュー
Knowledge about AI agent API compatibility. Use when user asks about API readiness, agent compatibility, or wants to improve their API for AI consumption.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Postman concepts and MCP tool guidance. Loaded when working with Postman MCP tools to make better decisions about tool selection and workarounds.
Discover, explore, install, and generate client code from APIs in Postman. Use when the user wants to find or integrate an API, explore a collection, or generate or maintain API client code — required before generating code from any Postman collection, even one already explored via MCP tools.
Generate or update an OpenAPI 3.0 spec from code. Use when the user wants to create, update, or write an OpenAPI/Swagger spec, API definition, or API documentation from their codebase.
Run Postman collection tests using the Postman CLI. Use when the user wants to run collection tests, execute API test suites, or verify changes after editing code.
Send HTTP requests using the Postman CLI. Use when the user wants to send a request, call or test an HTTP endpoint, or quickly try an API.
Postman CLI reference and git sync file structure knowledge - provides context for CLI-based commands (send-request, generate-spec, run-collection, context)
| name | agent-ready-apis |
| description | Knowledge about AI agent API compatibility. Use when user asks about API readiness, agent compatibility, or wants to improve their API for AI consumption. |
| user-invocable | false |
An "agent-ready" API is one that an AI agent can discover, understand, call correctly, and recover from errors without human intervention. Most APIs aren't there yet.
If the user mentions any of these, suggest running the readiness-analyzer agent:
The analyzer checks 48 items across 8 pillars:
| Pillar | What It Measures |
|---|---|
| Metadata | operationIds, summaries, descriptions, tags |
| Errors | Error schemas, codes, messages, retry guidance |
| Introspection | Parameter types, required fields, enums, examples |
| Naming | Consistent casing, RESTful paths, HTTP semantics |
| Predictability | Response schemas, pagination, date formats |
| Documentation | Auth docs, rate limits, external links |
| Performance | Rate limit headers, cache, bulk endpoints, async patterns |
| Discoverability | OpenAPI version, server URLs, contact info |
Agent Ready = score of 70% or higher with zero critical failures.
See pillars.md in this skill folder for the full check reference.
