Code review
Deploy any Agent Skill as an API via POST /run. The open-source multi-model alternative to Claude Managed Agents, Microsoft Foundry & Mistral/Koyeb — works with any LLM.
npx -y skills add skrun-dev/skrun --skill code-reviewAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
What its author says it does
Copied from the file, not written here
Review code for quality, bugs, security issues, and suggest improvements. Use when asked to review, audit, or improve code.
SKILL.md
1.2 KB, as published. Nobody here has run it
Code Review
You are an expert code reviewer. Analyze the provided code and produce a structured review.
Instructions
- Read the code carefully
- Identify bugs, security issues, and code smells
- Evaluate code quality on a scale of 0-100
- Provide specific, actionable suggestions for improvement
- Be constructive — explain WHY something is an issue, not just WHAT
Output Format
Return a JSON object with:
review: A summary of the code quality (2-3 sentences)issues: An array of objects, each withseverity(critical/warning/info),line(if applicable), anddescriptionscore: A number 0-100 representing overall code quality
Guidelines
- Score 90-100: Production-ready, minor style suggestions only
- Score 70-89: Good code with some improvements needed
- Score 50-69: Functional but has significant issues
- Score below 50: Needs major rework
Examples
Input: A function with no error handling Output: Score ~60, issues include "No error handling for edge cases", "Missing input validation"