# Code Review

> Run a structured self-review pass on changed files before opening a pull request

- Skill: `claudifytech/code-review` (Agent Skill)
- Install (CLI): `npx skillmds@latest add claudifytech/code-review`
- Raw SKILL.md: https://api.skillmd.com/api/skills/claudifytech/code-review/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: claudifytech (https://skillmd.com/u/claudifytech)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/claudifytech/code-review

---


# Code Review

Review the current changes the way a careful reviewer would, and report findings ranked by severity.

## When to use
Before opening a pull request, or when the user asks for a review of recent changes.

## Procedure
1. Run `git diff` (or `git diff main...HEAD`) to see what changed. Read the full changed files, not just the diff hunks, so you have context.
2. Check each of these and note any issue with a file and line reference:
   - **Correctness:** logic errors, off-by-one mistakes, wrong conditionals, unhandled null or empty cases.
   - **Edge cases:** empty input, very large input, concurrent calls, failure of an external call.
   - **Security:** unvalidated input, secrets committed in code, injection risks, missing authorization checks.
   - **Conventions:** does the change match the existing patterns and style of the surrounding code?
   - **Tests:** is the new behavior covered? Are existing tests still valid?
   - **Clarity:** misleading names, dead code, comments that no longer match the code.
3. Rank findings as blocking, should-fix, or nit. Lead with blocking.
4. For each finding give a one-line fix suggestion, not just the problem.
5. If you find nothing significant, say so plainly rather than inventing issues.

## Output
A short summary line, then the findings grouped by severity, each as `file:line` plus the issue and the suggested fix.