Code Review
Three-stage code review that actually stops you from skipping steps. First pass checks spec compliance requirement by requirement, second pass evaluates code quality and domain types, third pass audits domain boundaries and type system opportunities. Each stage can block the next, which sounds rigid but prevents the common problem of diving into code style before you've verified the thing actually meets requirements. Checks for primitive obsession, validates against architecture docs if they exist, and enforces vertical slice coverage so you're not just unit testing isolated functions. Writes findings to `.reviews/` files because chat messages don't survive context compaction. Built for agents but the structure works fine for human reviews too.
- skills.sh installs
- 163
- GitHub stars
- 5
- last updated
- Aug 21, 2026
Install
$ npx -y skills add jwilger/agent-skills --skill code-review --agent claude-codeInstalls into .claude/skills of the current project.
Files
Code Review
Value: Feedback and communication -- structured review catches defects that the author cannot see, and separating review into stages prevents thoroughness in one area from crowding out another.
Purpose
Teaches a systematic three-stage code review that evaluates spec compliance, code quality, and domain integrity as separate passes. Prevents combined reviews from letting issues slip through by ensuring each dimension gets focused attention.
Practices
Three Stages, In Order
Review code in three sequential stages. Do not combine them. Each stage has a single focus. A failure in an earlier stage blocks later stages -- there is no point reviewing code quality on code that does not meet the spec.
Stage 1: Spec Compliance. Does the code do what was asked? Not more, not less.
For each acceptance criterion or requirement:
- Find the code that implements it
- Find the test that verifies it
- Confirm the implementation matches the spec exactly
Mark each criterion: PASS, FAIL (missing/incomplete/divergent), or CONCERN (implemented but potentially incorrect). Flag anything built beyond requirements as OVER-BUILT.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/jwilger/agent-skills
- Categories
- Testing & QA, Security, Git & Pull Requests, Documentation, Code Review & Quality, AI & Agent Building, Debugging, Automation & Workflows
- First seen
- Jun 3, 2026
More from jwilger/agent-skills
All 4Recommended
More Testing & QA
agent-browserm1heng/clawdbot-feishuAutomates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web 156skills.sh installs
alicloud-observability-ptscinience/alicloud-skillsManage Alibaba Cloud Performance Testing Service (PTS) via OpenAPI/SDK. Use for scene lifecycle operations, test start/stop control, report retrieval, and metad126skills.sh installs
journey-templatesbutterbase-ai/butterbase-skillsUse as the optional template-publishing stage of the Butterbase journey, after deploy (and substrate, if used). Walks the user through authoring a clone-ready R0skills.sh installs
dogfoodcallstackincubator/agent-skillsSystematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "e0skills.sh installs
Browser Automationclaude-office-skills/skillsAutomate web browser interactions, scraping, testing, and workflow automation with Puppeteer/Playwright0skills.sh installs
security-analyzerCornjebus/security-analyzerComprehensive security vulnerability analysis for codebases and infrastructure. Scans dependencies (npm, pip, gem, go, cargo), containers (Docker, Kubernetes), 0skills.sh installs