# Reviewing Code

> Provides concise, focused code reviews matching exact task complexity requirements. Use when reviewing code quality, security, or when the user asks for code review.

- Skill: `qte77/reviewing-code` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add qte77/reviewing-code`
- Raw SKILL.md: https://api.skillmd.com/api/skills/qte77/reviewing-code/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Security
- Author: qte77 (https://skillmd.com/u/qte77)
- Updated: 2026-09-10
- Page: https://skillmd.com/skills/qte77/reviewing-code

---


# Review Context

- Changed files: !`git diff --name-only HEAD~1 2>/dev/null || echo "No recent commits"`
- Staged files: !`git diff --staged --name-only`

## Code Review

**Scope**: $ARGUMENTS

Delivers **focused, streamlined** code reviews matching stated task
requirements exactly. No over-analysis.

## Python Standards

See `docs/best-practices/python-best-practices.md` for comprehensive Python guidelines.

## Workflow

1. **Read task requirements** to understand expected scope
2. **Check `make validate`** passes before detailed review
3. **Match review depth** to task complexity (simple vs complex)
4. **Validate requirements** - does implementation match task scope exactly?
5. **Issue focused feedback** with specific file paths and line numbers

## Review Strategy

**Simple Tasks (100-200 lines)**: Security, compliance, requirements match,
basic quality

**Complex Tasks (500+ lines)**: Above plus architecture, performance,
comprehensive testing

**Always**: Use existing project patterns, immediate use after implementation

## Review Checklist

**Security & Compliance**:

- [ ] No security vulnerabilities (injection, XSS, etc.)
- [ ] Follows @AGENTS.md mandatory requirements
- [ ] Passes `make validate`

**Requirements Match**:

- [ ] Implements exactly what was requested
- [ ] No over-engineering or scope creep
- [ ] Appropriate complexity level

**Code Quality**:

- [ ] Follows project patterns in `src/`
- [ ] Proper type hints and docstrings
- [ ] Tests cover stated functionality

**Structural Health**:

- [ ] No function exceeds cognitive complexity threshold (suggested default: 15 per function, overridable per-project)
- [ ] No copy-paste duplication across methods (watch for repeated dispatch chains)
- [ ] File aggregate complexity — flag if trending above project norms (suggested default: 50 per file, overridable per-project)

## Output Standards

**Simple Tasks**: CRITICAL issues only, clear approval when requirements met
**Complex Tasks**: CRITICAL/WARNINGS/SUGGESTIONS with specific fixes
**All reviews**: Concise, streamlined, no unnecessary complexity analysis