⏳ This skill is pending AI review.
Scores will appear once the review pipeline completes.
code-reviewer
Production-grade structural code review for correctness, security, performance, and release risk.
Choose how to use this skill
You do not need every option. Choose the path your AI client supports. The stable page stays the same; versioned files are immutable.
1. Native installer
This listing has no registered native installer command. Use the complete package or source fallback below, depending on what your client supports.
Do not guess an installer command or replace an existing version without reviewing the diff.
2. Complete package recommended
Download the ZIP when available. It includes SKILL.md plus the references, security notes and version metadata.
No complete ProSkills package is published for this listing yet.3. Prompt-only
Copy the prompt above when the agent can read the stable page or when you want to adopt the workflow without installing a skill.
Need only the instruction file?
Download SKILL.md only if your client requires a single file. The complete ZIP is safer for a full installation because it preserves the references and release context.
No path installs or executes anything by itself. Your agent still needs access to the project files. Before updating, compare the installed version and review the diff.
// RATINGS
Not yet listed on ClawHub or SkillsMP
// README
code-reviewer
code-reviewer turns Claude Code or Codex into a focused production reviewer. It is designed for pull requests, risky refactors, release readiness checks, and regressions that need concrete findings instead of generic advice.
What It Does
- Reviews diffs structurally, not just line-by-line
- Prioritizes correctness, security, performance, and rollout risk
- Reports missing tests when behavior changes are not covered
- Produces concise findings that an engineer can act on immediately
Usage
Claude Code
Install: skillpm install clawhub/code-reviewer
Inject: skillpm inject --agent claude clawhub/code-reviewer
Prompt: "Use code-reviewer on the current diff. Findings first. Focus on regressions and missing tests."
Codex
Install: skillpm install clawhub/code-reviewer
Inject: skillpm inject --agent codex clawhub/code-reviewer
Prompt: "Use code-reviewer on cmd/skillpm/main.go and internal/app/service.go. Report only actionable findings."
Output Shape
- Findings ordered by severity
- File references for every issue
- Production failure mode
- Smallest safe fix
- Residual risk when no bug is confirmed
Test Cases
See tests/cases.yaml for repository-backed validation scenarios.
// HOW IT'S BUILT
// FILES
2 files shipped with this skill. Inline text is the catalog copy. The upstream link is the source repository.
skills/code-reviewer/SKILL.md1.8 KBupstream ↗
--- name: code-reviewer version: 1.0.0 description: "Production-grade structural code review for correctness, security, performance, and release risk." agents: - claude - codex category: tool tags: - review - security - performance rules: paths: - "**/*.go" - "**/*.py" - "**/*.ts" - "**/*.tsx" - ".github/workflows/*.yml" - ".github/workflows/*.yaml" scope: project summary: "Review changed code for defects, regressions, unsafe assumptions, and missing tests." --- # Code Reviewer Use this skill when the user wants a real engineering review instead of lint-style commentary. ## Agent Compatibility - Claude Code: supported - Codex: supported ## Inputs - A diff, commit range, pull request, or a focused set of changed files - Any failing test output, benchmark output, or bug report that motivated the review ## Workflow 1. Determine the exact review scope before commenting. 2. Read surrounding code, not just the modified lines, until the behavior is clear. 3. Prioritize findings by user impact: - correctness and data loss - security and trust boundaries - concurrency and state corruption - performance regressions - migration and rollout risk 4. Call out missing coverage whenever behavior changed without tests. 5. Distinguish between confirmed defects, plausible risks, and open questions. ## Output Contract - Findings first, ordered by severity. - Each finding includes: - a short title - affected file paths - the concrete failure mode - why the issue matters in production - the smallest safe fix - If no material findings remain, say so explicitly and mention residual testing gaps. ## Guardrails - Do not flood the user with style nits. - Do not speculate without a code path or failure scenario. - Do not propose broad rewrites unless the current design is unsound.README.mdupstream ↗
Contents are not inlined in the catalog. Open the upstream file.
Plain-text copy, no login: /skill-bundles/eddieran-skillpm-skills-code-reviewer.md