Pull request risk scorer
Point it at a pull request. Get complexity and risk scored, code smells flagged and review comments written.
Pull request risk scorer 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
Made by Alireza Rezvani. See the original on GitHub; we copied it as it is, with its licence.
What it does
A quick score for how risky and complex a pull request is, with code smells flagged and review comments already written. You know where to look before reading line by line. The skill runs analysis tools on the change and rates complexity and risk. It checks code against universal rules for security, async code, resources, error handling and performance, then against rules for the language in use, from Python and TypeScript to Go, Rust, Java, Swift and more. It looks for design problems like SOLID breaks and common smells. The output is a review report with a checklist and suggested comments.
You give it
- The pull request or code diff
- Language or languages used
- Team coding rules (optional)
You get
- Complexity and risk score
- Code smell and design issue list
- Language-specific findings
- Review checklist and written comments
Use it when
- You must review many pull requests and need to triage them.
- A change looks large and you want to know where the danger is.
- You want consistent review standards across languages.
- You need a checklist to support your review notes.
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.