superpowers-review
Reviews code changes against a checklist including security, edge cases, and maintainability standards.
Install
mkdir -p .claude/skills/superpowers-review && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/6431" && unzip -o skill.zip -d .claude/skills/superpowers-review && rm skill.zipInstalls to .claude/skills/superpowers-review
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Reviews changes for correctness, edge cases, style, security, and maintainability with severity levels (Blocker/Major/Minor/Nit). Use before finalizing changes.Key capabilities
- →Categorize issues by severity levels
- →Evaluate code against security and performance criteria
- →Provide summary and next actions
- →Check for edge cases and error handling
How it works
The skill performs a structured checklist review of code changes, classifying findings into Blocker, Major, Minor, and Nit categories.
Inputs & outputs
When to use superpowers-review
- →Reviewing code before pull requests
- →Checking for security vulnerabilities
- →Validating edge cases in new logic
About this skill
Review Skill
When to use this skill
- before delivering final code changes
- after implementing a planned set of steps
- before merging or shipping
Severity levels
- Blocker: wrong behavior, security issue, data loss risk, broken tests/build
- Major: likely bug, missing edge cases, poor reliability
- Minor: style, clarity, small maintainability issues
- Nit: optional polish
Checklist
- Correctness vs requirements
- Edge cases & error handling
- Tests (adequate coverage, meaningful assertions)
- Security (secrets, auth, injection, unsafe defaults)
- Performance (obvious hotspots, N+1, unnecessary work)
- Readability & maintainability
- Docs / comments updated if needed
Output format
- Blockers
- Majors
- Minors
- Nits
- Overall summary + next actions
When not to use it
- →During early development phases before logic is implemented
Limitations
- →Requires manual review of the generated summary
How it compares
It enforces a standardized severity-based reporting structure compared to informal or ad-hoc code reviews.
Compared to similar skills
superpowers-review side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| superpowers-review (this skill) | 6 | 6mo | No flags | Intermediate |
| contrib-pr-review | 1 | 27d | Review | Intermediate |
| verifier | 0 | 2mo | Caution | Intermediate |
| feature-flags | 6 | 6mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by anthonylee991
View all by anthonylee991 →You might also like
contrib-pr-review
homeassistant-ai
Review a contribution PR for safety, quality, and readiness. Checks for security concerns, test coverage, size appropriateness, and intent alignment. Use when reviewing external contributions.
verifier
oleyna80
Pre-merge quality gate. Use to verify code is ready to ship: route contracts (status, Content-Type, body), TypeScript, tests, CSP/CSRF headers, schema alignment, secret leak scan. Issues structured READY or BLOCKED verdict with file:line evidence. Read-only. Для верификации, проверки перед мержем, и
feature-flags
Use when feature flag tests fail, flags need updating, understanding @gate pragmas, debugging channel-specific test failures, or adding new flags to React.
production-code-audit
davila7
Autonomously deep-scan entire codebase line-by-line, understand architecture and patterns, then systematically transform it to production-grade, corporate-level professional quality with optimizations
check-code-quality
r3bl-org
Run comprehensive Rust code quality checks including compilation, linting, documentation, and tests. Use after completing code changes and before creating commits.
tech-debt
vm0-ai
Technical debt management - scan codebase for bad smells and create tracking issues