# code-reviewer

Adopt this skill: https://proskills.md/skills/tool/eddieran-skillpm-skills-code-reviewer

Page: https://proskills.md/skills/tool/eddieran-skillpm-skills-code-reviewer
This document is the public skill bundle for that page. It contains SKILL.md and every helper file the catalog carries. No login is required.

## File: skills/code-reviewer/SKILL.md
size: 1861
upstream: https://github.com/eddieran/skillpm/blob/main/skills/code-reviewer/SKILL.md

```text
---
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.
```

## File: README.md
upstream: https://github.com/eddieran/skillpm/blob/main/README.md

````text
# 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

```text
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

```text
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](tests/cases.yaml) for repository-backed validation scenarios.
````
