メニュー
Reference for how the built-in /simplify command integrates with blueprint-dev workflows — when it runs, what it checks, and how it complements review agents.
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
Production A/B testing lifecycle for design variants. Covers hypothesis formation, feature flags, variant comparison, analytics tracking, statistical significance analysis, experiment setup, and cleanup.
Browser automation using Vercel's agent-browser CLI. Use when you need to interact with web pages, fill forms, take screenshots, or scrape data. Uses Bash commands with ref-based element selection. Triggers on "browse website", "fill form", "click button", "take screenshot", "scrape page", "web automation".
Multi-agent architecture review combining core architecture design with parallel security, performance, and data integrity assessments. Produces ADRs in MADR format. Covers ADR, architecture decision, system design, scalability assessment. Not for code review or implementation — for architectural decisions only.
Reference for how the built-in /batch command integrates with blueprint-dev workflows — parallel codebase-wide changes using worktrees with project context.
Analyzes detected stack profiles and suggests targeted CLAUDE.md improvements. Covers CLAUDE.md improvement, project configuration, AI instructions. Never auto-writes to CLAUDE.md — stages suggestions for user review.
Problem documentation methodology for compounding team knowledge. Captures solved problems with structured metadata for searchability, pattern detection, and prevention. Covers postmortem, lessons learned, debugging documentation, solved problem capture. Not for general documentation — specifically for post-debugging problem capture.
| name | simplify-integration |
| description | Reference for how the built-in /simplify command integrates with blueprint-dev workflows — when it runs, what it checks, and how it complements review agents. |
| user-invocable | false |
| disable-model-invocation | true |
How the built-in /simplify command fits into blueprint-dev workflows.
/simplify is a built-in Claude Code command that runs 3 specialized agents on your code:
| Agent | Focus | Examples |
|---|---|---|
| Reuse | Finds existing utilities you could use instead of new code | Project already has formatDate() but you wrote a new one |
| Quality | Spots hacky patterns, redundant state, copy-paste code | Duplicated validation logic, unnecessary wrapper functions |
| Efficiency | Identifies unnecessary work, missed concurrency, hot-path bloat | Sequential awaits that could be parallel, unused computations |
After analysis, /simplify auto-fixes the issues it finds. It modifies your code directly.
/bp:build — Step 5.5 runs /simplify after implementation, before presenting results. This catches reuse opportunities and quality issues while the code is fresh.
/bp:go — Step 7 suggests running /simplify after implementation completes.
/bp:review — Step 5 offers /simplify as a next step for auto-fixing P2/P3 quality and efficiency findings.
/bp:lfg — Phase 5 (Build) runs /simplify after implementation. Phase 6 (Review) suggests it for remaining findings.
/simplify and blueprint-dev's review agents serve different purposes:
| Aspect | /simplify | /bp:review agents |
|---|---|---|
| Action | Auto-fixes code | Reports findings |
| Scope | Reuse, quality, efficiency | Quality, tests, TBD, patterns |
| Output | Modified source files | P1/P2/P3 review report |
| When | During/after build | After build, before ship |
| Overlap | DRY violations, redundant code | Same issues + architecture, conventions |
They are complementary, not redundant:
/simplify handles the mechanical fixes (DRY, efficiency, reuse)/simplify first reduces noise in the review report — fewer P2/P3 findings for reviewers to wade through/bp:build
│
├── Step 3: Implement (trunk-implementor)
├── Step 5: Self-Review (checklist)
├── Step 5.5: /simplify ◄── auto-fixes reuse, quality, efficiency
├── Re-verify tests + linting
└── Step 6: Present results
/bp:review
│
├── Step 2: 4 parallel review agents
├── Step 4: Present P1/P2/P3 findings
└── Step 5: Offer next steps
└── "Run /simplify to auto-fix P2/P3 findings" ◄──
/simplify after implementation, before marking complete/simplify in the present step/simplify"/simplify"