# Code Review > Perform a structured code review with emphasis on correctness, regressions, and test gaps. Use when this capability is needed. - Skill: `tomevault-io/code-review-311` (Agent Skill, multi-file: 2 files) - Install (CLI): `npx skillmds@latest add tomevault-io/code-review-311` - Raw SKILL.md: https://api.skillmd.com/api/skills/tomevault-io/code-review-311/raw - Safety review: pending - Works with: Claude Code, Claude.ai, OpenAI Codex - Category: Coding & Dev Tools - Author: tomevault-io (https://skillmd.com/u/tomevault-io) - Updated: 2026-09-17 - Page: https://skillmd.com/skills/tomevault-io/code-review-311 --- ## Steps 1. Identify the files and behaviors affected by the change. 2. Compare the implementation against local conventions and surrounding patterns. 3. Check whether edge cases, failure paths, and permissions are covered. 4. Note any test gaps or unclear assumptions. 5. Summarize the highest-signal findings first. ## Guardrails - Do not suggest broad refactors unless they are required to make the change safe. - Prefer comments tied to observable behavior. - Distinguish clearly between bugs, risks, and polish. --- > Source: [jackby03/agentic-collaboration-standard](https://github.com/jackby03/agentic-collaboration-standard) — distributed by [TomeVault](https://tomevault.io).