Browse skills

Run an independent peer review of an implementation plan. Returns structured findings without applying fixes. Use when the user asks to "peer review my plan", "get a second opinion on my plan", or "review my plan independently".

Run an independent peer review of a prompt plan. Returns structured findings without applying fixes. Use when the user asks to "peer review my prompt plan", "get a second opinion on my prompts", or "review my prompts independently".

Run an independent peer review of a specification document. Returns structured findings without applying fixes. Use when the user asks to "peer review my spec", "get a second opinion on my spec", or "review my spec independently".

Fetch and rank open GitHub issues by community engagement, present the top 3 candidates, and plan implementation for the selected issue. Use when the user asks to "pick next issue", "next issue", "which issue should I work on", "top issues", "most popular issues", "prioritize issues", or "what should I work on next".

Pick the next prompt from .turbo/prompts.md and plan its implementation. Use when the user asks to "pick next prompt", "next prompt", "continue prompt plan", "what's next", "next implementation step", or "continue with the plan".

Planning conventions for task tracking, skill loading, and finalization. Use when writing implementation plans, or when the user asks to "load plan style", "plan conventions", or "how should I structure a plan".

Stage, format, lint, test, simplify, review, smoke test, and re-run itself until stable. Use when the user asks to "polish code", "refine code", "iterate on code quality", "simplify and review loop", "clean up, test, and review loop", or "run the polish loop".

Evaluate, fix, and reply to GitHub pull request review comments. Use when the user asks to "resolve PR comments", "fix review comments", "address PR feedback", "handle review comments", "address review feedback", "respond to PR comments", or "address code review".

Check API, library, and framework usage in code against official documentation and installed skill knowledge. Flags deprecated APIs, incorrect method signatures, wrong parameter types, version-incompatible patterns, and best-practice violations. Use when the user asks to "review API usage", "check API usage", "verify against docs", "check library usage", "validate API calls", "check against documentation", or "check for deprecated APIs".

Full code review: launches `/review-test-coverage`, `/review-correctness`, `/review-security`, `/review-quality`, `/review-api-usage`, and `/peer-review-code` in parallel and returns combined findings. Use when the user asks to "review my code", "full code review", "review my changes", or wants a comprehensive code review.

Analyze code for bugs and correctness problems using strict determination criteria. Returns structured findings without applying fixes. Use when the user asks to "review correctness", "scan my code for bugs", "find bugs in my changes", "look for bugs", "check for bugs", or "run a correctness review".

Detect package managers and discover outdated or vulnerable dependencies. Returns structured findings without upgrading. Use when the user asks to "review dependencies", "check for outdated packages", "check dependencies", "scan dependencies", or "dependency review".

Review an implementation plan: launches an internal plan review and `/peer-review-plan` in parallel and returns combined findings. Use when the user asks to "review my plan", "review this plan", "check my plan", "critique my plan", or wants plan feedback before implementation.

Review a pull request by fetching PR comments and running a comprehensive code review with evaluation. Use when the user asks to "review PR", "review pull request", "review this PR", "check PR before merging", or "full PR review".

Review a prompt plan against its source spec: launches an internal prompt plan review and `/peer-review-prompt-plan` in parallel and returns combined findings. Use when the user asks to "review my prompt plan", "review my prompts", "check my prompt plan", "critique my prompts", or wants prompt plan feedback before implementation.

Analyze code for cross-file quality issues: duplicated logic, architectural inconsistencies, and abstraction opportunities. Returns structured findings without applying fixes. Use when the user asks to "review quality", "check for duplication across files", "find architectural inconsistencies", "cross-file quality review", or "review code quality".

Analyze code for security vulnerabilities, insecure patterns, and security regressions using strict determination criteria. References the project threat model when available. Returns structured findings without applying fixes. Use when the user asks to "review security", "check for security issues", "find vulnerabilities in my changes", "run a security review", "analyze my code for security", "security audit", or "security scan".

Review a specification document: launches an internal spec review and `/peer-review-spec` in parallel and returns combined findings. Use when the user asks to "review my spec", "review this spec", "check my spec", "critique my spec", or wants spec feedback before planning.

Analyze code for test coverage gaps, untested functions, and missing edge cases. Returns structured findings without writing tests. Use when the user asks to "review test coverage", "check test coverage", "find untested code", "analyze coverage gaps", or "what needs tests".

Detect what dev tooling infrastructure a project has and flag gaps across linters, formatters, pre-commit hooks, test runners, and CI/CD pipelines. Returns structured findings without applying changes. Use when the user asks to "review tooling", "check project tooling", "what tooling is missing", "review dev infrastructure", or "tooling audit".