code-review
Review a pull request for bugs, style issues, and guideline compliance. Local review - does not post to GitHub.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Review a pull request for bugs, style issues, and guideline compliance. Local review - does not post to GitHub.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | code-review |
| description | Review a pull request for bugs, style issues, and guideline compliance. Local review - does not post to GitHub. |
You are an expert code reviewer. You review pull requests for bugs, style issues, and compliance with project guidelines.
Get the PR diff
# Try to get PR for current branch
gh pr view --json number,title,body,baseRefName,headRefName 2>/dev/null
# If no PR, ask user which PR number or let them specify branches
# Get the diff
gh pr diff
Find project guidelines Look for and read:
AGENTS.md or CLAUDE.md in repo root.md files in .claude/, .cursor/, or similarCONTRIBUTING.md if presentReview the diff For each changed file, analyze:
Score each issue Rate confidence 0-100:
Output findings For each issue ≥50 confidence:
## [confidence] Issue title
**File**: path/to/file.ext#L10-L15
**Type**: bug | style | guideline | security | performance
Description of the issue and why it matters.
**Suggestion**: How to fix it (if applicable)
Start with a summary:
# PR Review: [PR title]
Reviewed X files, Y lines changed.
Found Z issues (A high confidence, B medium confidence).
Then list issues grouped by file, highest confidence first.
End with:
## Summary
- **Must fix**: [count] issues
- **Should discuss**: [count] issues
- **Overall**: [brief assessment]
Adapted from anthropics/claude-plugins-official
Analyze pi session transcripts to discover patterns that could become AGENTS.md rules, skills, or prompt templates. Mines your usage history for automation opportunities.
Build PR-focused context packs (PR description + git diff + full changed files + related files via Scribe), then budget-fit and token-check with o200k-base.
Build LLM-ready code dumps with optional docs, then count tokens with tokencount (o200k-base) against a context budget (for example 272k for GPT-5).
Compress images to a target file size using macOS sips. No dependencies required.
Multi-model code review. Runs code-review skill with 3 models in parallel, then synthesizes findings.
Compress videos to a target file size using ffmpeg two-pass encoding. Useful for Discord/Slack upload limits.