More screenshots
Works with the AI Agents you already use
API Design Review: REST Best Practices & OpenAPI
Design or review REST APIs: naming, status codes, errors, pagination, idempotency, security, plus an OpenAPI 3.1 skeleton.
$12
API Design Review: REST Best Practices & OpenAPI
Example session with this skill installed
Review these endpoints: GET /getOrders, POST /createOrder, DELETE /orders/delete?id=5
- Read your context and instructions
- Compiled the api design review
Summary: naming and method misuse across all 3 endpoints; biggest risk is DELETE with the id in the query string and no ownership check.\n\nIMPORTANT DELETE /orders/delete?id=5 - verb in the path, and no object-level authorization mentioned - use DELETE /orders/{orderId} and verify the caller owns the order (404 otherwise).\nIMPORTANT POST /createOrder - retries can create duplicates - POST /orders with an Idempotency-Key header, return 201 + Location.\nMINOR GET /getOrders - verb in the path - GET /orders with limit and cursor.
Connects securely to your tools. The creator never sees your data.
About this skill
Ship APIs your consumers will not curse at. Use it in two modes: Design a new API from requirements, or Review an existing one from code, an OpenAPI file or a list of endpoints.
What it checks (with a 9-area checklist)
- Resource naming and stable ids
- HTTP methods and status codes (201 with Location, 409 vs 422, 401 vs 403...)
- One consistent error format (Problem Details style) with codes, field errors and a trace id, and no stack traces
- Pagination (cursor vs offset), filtering, sorting, max page size
- Idempotency keys and ETag / If-Match to avoid double charges and lost updates
- Versioning and safe, additive evolution with deprecation signals
- Security: authentication on every route, object-level authorization, response field filtering, mass assignment, rate limits
- Caching, N+1 round trips, and documentation completeness
What you get
- Design mode: resource table, shared conventions and an OpenAPI 3.1 skeleton
- Review mode: Critical / Important / Minor findings with method + path and the fix, consistency notes and what is missing from the spec
- Breaking changes come with a rollout plan so current clients keep working
Security findings are never rated below Important. It never invents endpoints it did not see.
En español: diseña o revisa APIs REST y genera el esqueleto OpenAPI. Responde en tu idioma.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Security.
Focused on REST/JSON over HTTP (not GraphQL, gRPC or event APIs). It does not call or load-test your API, and it reviews only the endpoints and code it is shown.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 6 days ago
Requires
Nothing to install.
Permissions
No special permissions declared or detected