メニュー
Engineering Manager review of any feature plan. Architecture diagrams, data flow, state machines, edge cases, test matrix. Forces hidden assumptions into the open.
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
Builds production-grade Claude Projects and CustomGPTs, improves AI output quality using meta-thinking prompts, and architects self-improving AI systems. Use proactively when a founder wants to build a reliable AI workflow, automate a repeatable task with AI, improve the quality of AI outputs they're getting, feels stuck with generic AI responses, or wants to build internal tools powered by Claude. Trigger for "build a Claude project", "my AI outputs are generic", "how do I make Claude more specific", "build an AI workflow", "automate this with AI", or "my prompts aren't working".
One-command review pipeline. Chains CEO review → design review → eng review automatically. Surfaces only taste decisions for PD approval. Everything else runs autonomously.
Performance baseline measurement. Captures page load times, Core Web Vitals, and resource sizes. Compare before/after on every PR.
Playbook for bootstrapped and early-stage SaaS founders based on proven case studies ($0 to $5M ARR with 6 people, and creator-to-business flywheel models). Use proactively when a founder is bootstrapped or capital-efficient, needs to grow without paid acquisition, is facing a churn crisis, wants to build a freemium or usage-based model, or asks "how do I grow without VC money". Also trigger for "PLG", "inbound-led outbound", "creator-led growth", "build in public", or "how did [bootstrapped company] grow".
Real browser automation for testing, QA, and demo verification. Provides Playwright-based browser control for navigating the live app, clicking elements, filling forms, taking screenshots, and verifying visual state.
Post-deploy monitoring. After release-engineer pushes to production, canary watches the live site for errors, performance regressions, and page failures.
| name | plan-eng-review |
| description | Engineering Manager review of any feature plan. Architecture diagrams, data flow, state machines, edge cases, test matrix. Forces hidden assumptions into the open. |
| used_by | ["workflow-architect","backend-dev"] |
After CEO approves a plan, the engineering lead runs this review before any code is written.
Draw the data flow for this feature:
[User Action] → [Frontend Component] → [API Call] → [Backend Route] → [Database Table]
↓
[Response] ← [Business Logic] ← [Result]
Include: which existing components are touched, which are new.
[Initial] --action--> [State A] --action--> [State B]
|
+--error--> [Error State]
Reference docs/STATE_MACHINES.md for existing state machines. Flag conflicts.
| # | Edge Case | What happens | Handled? |
|---|---|---|---|
| 1 | User has no profile yet | ||
| 2 | Concurrent requests | ||
| 3 | Network timeout mid-operation | ||
| 4 | Invalid/expired auth token | ||
| 5 | Feature-specific edge case |
| Test Type | What to test | Owner |
|---|---|---|
| Unit | Component renders, service logic | frontend-dev / backend-dev |
| Integration | API endpoint contract | backend-dev |
| Browser | User flow end-to-end | qa-engineer (qa-browser skill) |
| Security | Auth, input sanitisation | security-auditor |
What happens when each dependency fails?
ENG APPROVED / ENG NEEDS REVISION — [specific items]
Write to docs/plan-reviews/[feature]-eng-review-[date].md
Post to Slack STRATEGY: "ENG REVIEW: [feature] — [APPROVED/NEEDS REVISION]"
Hand off to build team for implementation via handoff envelope.