API design reviewer
Give it your API spec. Get a scorecard, flagged breaking changes and fixes for naming and errors.
API design reviewer is a free AI skill for the job "Test and fix code". Give the instructions to an AI assistant that supports the required files and tools, then review its output.
Free · No account · MIT licence · Made by Alireza Rezvani · Level: advanced
Made by Alireza Rezvani. See the original on GitHub; we copied it as it is, with its licence.
What it does
A scorecard for your API design, with a list of breaking changes and fixes for naming, errors and structure. It works best before an API ships, or before you plan a second version. The skill runs three scripts and reports what they find. A linter checks resource names, how requests and statuses are used, URL shape, error format and missing docs. A change detector compares two versions of your spec and flags removed endpoints and changed responses. A scoring tool grades the whole design. You fix the issues, then run them again until the linter is clean, nothing breaks without a version bump, and the grade meets your target. It will not sign off on words alone.
You give it
- Your OpenAPI or Swagger file
- An older version to compare (optional)
- Your target grade (optional)
- Team naming rules (optional)
You get
- A graded scorecard
- A list of convention problems
- Flagged breaking changes
- Fixes for naming and error format
Use it when
- A pull request adds or changes endpoints and you want a proper review.
- You are planning a second version and need to know what would break.
- Your team has no shared API standards.
- Names and errors differ from route to route.
How to use it
- Add it to your AI once: download it and add the folder to Claude, ChatGPT or Codex as a skill.
- Ask for the job in your own words. Your AI opens the skill when it fits.
- It works best when your AI can run code and read your project files.