- Home
- Skills
- APIs & Backend
- API Design Pack
API Design Pack
Multi-protocol API auditor for REST, GraphQL, tRPC, and OpenAPI design patterns.
$5
Works with the AI Agents you already use
API Design Pack
Example session with this skill installed
Review this Express route
app.post('/item', (req, res) => {
const item = db.items.create(req.body);
res.status(200).send(item);
});
- Read your context and instructions
- Compiled the api design
Stack
Express.js, JavaScript
Audit
- REST: Wrong status code. POST /item returns 200, but should be 201 Created.
- REST: Resource naming. Route is singular '/item', should be plural '/items'.
- Rate Limiting: No middleware detected for this write operation.
Fixes
res.status(201).send(item);
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
API inconsistencies and anti-patterns often go unnoticed until production, leading to brittle integrations, N+1 performance bottlenecks, and poor developer experiences. Manually checking every route for proper status codes, pagination, and rate limiting is tedious and error-prone.
What it does
- Audits REST, GraphQL, and tRPC code for architectural anti-patterns using a multi-skill detection engine.
- Identifies specific violations like missing pagination, incorrect HTTP status codes, and N+1 resolver loops with line-level citations.
- Generates concrete code fixes using detected frameworks like FastAPI, Express, or Apollo.
- Validates OpenAPI/Swagger schemas for completeness, documentation quality, and security definitions.
- Analyzes rate limiting strategies, suggesting token bucket or sliding window implementations based on your stack.
Frameworks & tools
REST (Express, FastAPI), GraphQL (Apollo, DataLoader), tRPC, OpenAPI 3.0/3.1, Swagger, Zod, and Pydantic.
Why this beats prompting it yourself
Generic prompts often miss the nuances of specific protocols, such as RFC 7807 error formats or GraphQL forward compatibility rules. This skill uses a structured matrix to apply deep domain rules specific to your detected stack, ensuring you don't just get "cleaner code" but technically compliant API design.
Use cases
- Reviewing legacy REST controllers for missing idempotency and pagination.
- Fixing N+1 query issues in complex GraphQL resolver chains.
- Converting flat tRPC routers into scalable sub-router architectures.
- Hardening endpoints with RFC-compliant rate limit headers and 429 error handling.
Known limitations
Operates only on provided code and schemas. Does not execute, test, or deploy APIs.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for APIs & Backend.
Does not execute code, perform live network tests, or deploy infrastructure. Reviews are limited to the code snippets pasted by the user.
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 3 months ago