unrealandychan/clean-code-skill/code-review
Claude Code and agent skill by unrealandychan/clean-code-skill
- community
Checking that the SKILL.md file is still in the repository.
Performs rigorous 5-axis code reviews across Correctness, Readability, Architecture, Security, and Performance. Use when reviewing pull requests, inspecting git diffs, checking code health, or when the user invokes /code-review, /review-diff, /review-security, /review-perf, or /quality-gate.
Install
npx vskill@latest install unrealandychan/clean-code-skill/code-reviewSKILL.md
The same SKILL.md was published earlier as unrealandychan/clean-code-skill/code-review.
Code Review & Quality Skill
Inspired by Addy Osmani'sagent-skills(addyosmani/agent-skills/skills/code-review-and-quality/SKILL.md).
Overview
Performs rigorous, multi-dimensional code reviews across Correctness, Readability, Architecture, Security, and Performance.
When to Invoke This Skill
Use this skill when:
- The user requests a code review, pull request review, or quality check (
/code-review,/review-diff,/review-security,/review-perf). - Reviewing new code or refactoring changes before merging.
- Evaluating code health across the 5 axes of quality.
- Checking merge readiness against automated quality gates (
/quality-gate).
The 5-Axis Quality Framework
- Correctness: Spec/acceptance criteria alignment, edge cases, error handling, race conditions.
- Readability: Clear naming, small functions, self-documenting structure, _why_-focused comments.
- Architecture: Separation of concerns, bounded context boundaries, Ponytail anti-overengineering ladder.
- Security: OWASP top risks, input sanitization, secret protection, least privilege.
- Performance: Query batching, memory leak prevention, async efficiency, resource bounding.
Review Benchmark
Approve a change when it definitely improves overall code health, even if it isn't perfect. Perfect code doesn't exist — continuous improvement is the goal.
Execution Procedure
- Scope the Diff: Identify changed files, target branch, and relevant tests using
git diffor PR metadata. - Scan Invariants: Verify that business invariants, types, and contract tests pass before aesthetic feedback.
- Evaluate 5 Axes: Assess each axis sequentially; flag blocking bugs immediately.
- Deliver Structured Findings:
- Severity:
BLOCK,WARN,NIT. - Category: One of the 5 axes.
- Evidence: Exact file link and line range.
- Proposed Fix: Minimal, drop-in code snippet.
Quick Shortcuts
| Command | Action | |
|---|---|---|
/code-review | Full 5-axis code review on target files or git diff | |
/review-diff | Review git diff against HEAD / main branch | |
/review-security | Focused security audit (injection, secrets, OWASP) | |
/review-perf | Focused performance & memory leak audit | |
/quality-gate | Evaluate whether code passes merge readiness criteria |
References
- Canonical Rules: skills/shared/code-review-quality-rules.md
- Workflows & Prompts: skills/code-review/WORKFLOWS.md
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/code-review/SKILL.md
Popularity
- Repository stars
- 10
- Repository forks
- 1
- 7-day trend score
- 17
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/unrealandychan/clean-code-skill/code-review)