skills/reviewing-code/SKILL.md
Use when reviewing code changes for correctness, maintainability, readability, security, performance, test coverage, and integration risk; especially when the user asks to inspect a diff, pull request, merge request, commit, patch, or source files.
npx skillsauth add narumiruna/agent-skills reviewing-codeInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Review the requested change, not the entire codebase. Prioritize correctness and production risk over surface style. Treat the review as read-only unless the user asks you to address findings.
main.Report findings introduced by the reviewed change or made materially worse or newly reachable by it. Keep unrelated pre-existing problems out of the main findings unless the user requested a broader audit; mention a directly relevant pre-existing problem separately and label it clearly.
Lead with findings, ordered by severity:
Each finding must include the file and line when available, the concrete triggering scenario, its impact, and an actionable fix. Do not invent context or report speculative risks without a plausible path to failure. Omit preference-only comments and nits unless the user explicitly asks for style or clarity feedback.
If there are no findings, say so directly and note any meaningful residual risk or verification gap. Add a short summary only when it helps explain a complex change. Discuss tests separately only when there is a specific coverage gap.
Give a merge recommendation only for a pull request, merge request, or explicit mergeability question. Use one conclusion: Approve, Approve with minor comments, Request changes, or Needs more context.
development
Score or compare one or more agent skills across trigger clarity, workflow actionability, safety boundaries, verification rigor, incremental knowledge value, and leanness. Use only when the user explicitly asks for ratings, numerical quality scores, rubric-based scorecards, or scored comparisons; use creating-agent-skills for unscored reviews or revisions.
development
Assess or improve an existing codebase's architecture when the user asks about module boundaries, coupling, scattered ownership, testability, change locality, deep modules, seams, or behavior-preserving structural refactoring. Use for cross-module design rather than ordinary diff review or a confirmed edge-case bug fix.
development
Perform read-only security audits, vulnerability assessments, or threat-focused reviews of diffs, pull requests, code paths, or explicitly scoped repositories when security is the primary objective or acceptance criterion. Use reviewing-code for ordinary review with baseline security coverage and hardening-code-paths for fixing confirmed findings.
development
Run iterative multi-reviewer panels over a code diff, verify their findings, apply explicitly authorized fixes, and re-review the updated change until it passes or reaches a stopping condition. Use when the user asks for a panel loop, multi-model code-review consensus, or a review-fix-re-review cycle.