メニュー
This skill should be used when performing exhaustive code reviews using multi-agent analysis, ultra-thinking, and Git worktrees for deep local inspection. It applies to PR reviews, branch comparisons, and comprehensive code quality assessments.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
This skill should be used when transforming feature descriptions, bug reports, or improvement ideas into well-structured project plans following project conventions and best practices.
This skill should be used when building AI agents using prompt-native architecture where features are defined in prompts, not code. Use it when creating autonomous agents, designing MCP servers, implementing self-modifying systems, or adopting the "trust the agent's intelligence" philosophy.
Capture solved problems as categorized documentation with YAML frontmatter for fast lookup
This skill provides expert guidance for creating, writing, building, and refining Claude Code Skills. It should be used when working with SKILL.md files, authoring new skills, improving existing skills, or understanding skill structure and best practices.
This skill should be used when executing work plans, specifications, or todo files systematically while maintaining quality and shipping complete features.
| name | workflows-review |
| description | This skill should be used when performing exhaustive code reviews using multi-agent analysis, ultra-thinking, and Git worktrees for deep local inspection. It applies to PR reviews, branch comparisons, and comprehensive code quality assessments. |
Perform exhaustive code reviews using multi-agent analysis, ultra-thinking, and Git worktrees for deep local inspection.
Senior Code Review Architect with expertise in security, performance, architecture, and quality assurance.
gh) installed and authenticatedFirst, determine the review target type and set up the code for analysis.
Immediate Actions:
gh pr view --json for title, body, files, linked issuesgh pr checkout if needed)Ensure the code is ready for analysis before proceeding.
Spawn sub-agents in parallel for comprehensive review. Each sub-agent should focus on a specific aspect of the code.
Core Review Agents (run all in parallel):
Run these agents ONLY when the PR matches specific criteria:
If PR contains database migrations (db/migrate/*.rb) or data backfills:
Trigger conditions:
db/migrate/*.rbFor each phase, spend maximum cognitive effort. Think step by step. Consider all angles. Question assumptions.
Developer Perspective
Operations Perspective
End User Perspective
Security Team Perspective
Business Perspective
Technical Excellence:
Business Value:
Risk Management:
Team Dynamics:
Spawn a sub-agent using @guidance/review/code-simplicity-reviewer to identify simplification opportunities.
ALL findings MUST be stored in the .opencode/todos/ directory. Create todo files immediately after synthesis.
Use @skill/file-todos for structured todo management. Create todo files for ALL findings immediately.
For large PRs with 15+ findings: Spawn sub-agents in parallel to create finding files simultaneously.
File naming convention:
{issue_id}-{status}-{priority}-{description}.md
Examples:
- 001-pending-p1-security-vulnerability.md
- 002-pending-p2-performance-optimization.md
- 003-pending-p3-code-cleanup.md
Status values:
pending - New findings, needs triage/decisionready - Approved, ready to workcomplete - Work finishedPriority values:
p1 - Critical (blocks merge, security/data issues)p2 - Important (should fix, architectural/performance)p3 - Nice-to-have (enhancements, cleanup)Tagging: Always add code-review tag, plus: security, performance, architecture, rails, quality, etc.
After creating all todo files, present:
## ✅ Code Review Complete
**Review Target:** PR #XXXX - [PR Title]
**Branch:** [branch-name]
### Findings Summary:
- **Total Findings:** [X]
- **🔴 CRITICAL (P1):** [count] - BLOCKS MERGE
- **🟡 IMPORTANT (P2):** [count] - Should Fix
- **🔵 NICE-TO-HAVE (P3):** [count] - Enhancements
### Created Todo Files:
**P1 - Critical (BLOCKS MERGE):**
- `001-pending-p1-{finding}.md` - {description}
**P2 - Important:**
- `003-pending-p2-{finding}.md` - {description}
**P3 - Nice-to-Have:**
- `005-pending-p3-{finding}.md` - {description}
### Next Steps:
1. Address P1 Findings: CRITICAL - must be fixed before merge
2. Triage all todos in `.opencode/todos/`
3. Work on approved todos using @workflows/work
4. Track progress by updating todo status
After presenting the Summary Report, offer appropriate testing based on project type:
Detect project type from PR files:
*.xcodeproj, *.xcworkspace, Package.swiftGemfile, package.json, app/views/*, *.html.*For Web Projects: Offer to spawn a sub-agent for Playwright browser tests on affected pages.
For iOS Projects: Offer to spawn a sub-agent for Xcode simulator tests.
For Hybrid Projects: Offer web only, iOS only, or both.
Any 🔴 P1 (CRITICAL) findings must be addressed before merging the PR. Present these prominently and ensure resolution before accepting the PR.