Agent skill · software engineering · sundial-org
ai-code-review
ai-code-review — an agent skill for coding agents.
Why this skill is useful
Adds a specific command for automated code review that identifies bugs and security issues not covered by standard practices.
What it needs
Requires npx installed locally. About 1k tokens when loaded. Last updated 2026-03-07. 639 stars on the source repository.
What this skill does
Code Reviewer AI-powered code review for staged git changes. Catches bugs, security issues, and code smells before you push. Quick Start What It Does Reviews your staged git changes automatically Identifies bugs, logic errors, and anti-patterns Flags potential security issues Suggests concrete improvements with explanations Color-coded output (critical/warning/suggestion/good) Usage When to Use Right before opening a pull request Working solo without a reviewer Late night coding when your brain is tired Quick sanity check on tricky refactors Part of the LXGIC Dev Toolkit One of 110+ free developer tools from LXGIC Studios. No paywalls, no sign-ups. Find more: GitHub: https://github.com/lxgic-studios Twitter: https://x.com/lxgicstudios Substack: https://lxgicstudios.substack.com Website: https://lxgicstudios.com License MIT. Free forever. --- Built by LXGIC Studios GitHub: github.com/lxgicstudios/ai-code-review Twitter: @lxgicstudios
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills sundial-org/ai-code-review