メニュー
Systematic root-cause debugging. Iron Law — no fixes without investigation. Traces data flow, tests hypotheses, stops after 3 failed fix attempts.
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 | investigate |
| description | Systematic root-cause debugging. Iron Law — no fixes without investigation. Traces data flow, tests hypotheses, stops after 3 failed fix attempts. |
| used_by | ["frontend-dev","backend-dev","qa-engineer"] |
When a bug is reported or a test fails, DO NOT JUMP TO FIXING. Investigate first.
No fix without investigation. If you can't explain WHY the bug happens, you can't fix it reliably.
Step 1 — Reproduce:
Step 2 — Trace the data flow: Starting from the user action that triggers the bug, trace through:
[User clicks X] → [Event handler in Component.tsx:L42]
→ [Service call: featureService.doThing()]
→ [API: POST /api/feature/thing]
→ [Backend handler: routes/feature.ts:L18]
→ [Database query: SELECT ... WHERE ...]
→ [Response: {data}]
→ [State update: setState(data)]
→ [Re-render: Component shows wrong value]
At each step: is the data correct? Where does it first go wrong?
Step 3 — Form hypothesis: "I believe the bug is caused by [X] because [evidence]."
Step 4 — Test hypothesis:
Step 5 — Fix (only after hypothesis confirmed):
If your fix doesn't resolve the bug after 3 attempts:
docs/agent-notes/[agent]-notes.mdWhen investigating, restrict your edits to the module under investigation.
src/components/matching/, do NOT edit src/components/profile/Append investigation to docs/agent-notes/[agent]-notes.md:
Investigation: [Bug/Issue]
Date: [date]
Data flow trace: [the trace above]
Hypothesis: [what you think]
Hypothesis verified: YES/NO
Fix applied: [file:line — what changed]
Regression test: [test file path]
Result: RESOLVED / ESCALATED