메뉴
Use after /office-hours when the problem is defined but the plan and scope are not yet ready. Judges readiness through discovery, product, and engineering lenses. Returns a readiness verdict (ready / revise / park) + concrete gaps to close before implementation starts.
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
Explicit GPT-5.6 native-first router for auditing, designing, installing, or validating Codex skill combinations, global skill setup, routing fixtures, and harness behavior. Use when the user explicitly invokes $codex-skill-router or asks to change or inspect Codex skills, routing, AGENTS guidance, or global harness configuration. Do not use for ordinary coding, review, debugging, research, or UI work merely because the task is complex.
Use when work introduces or changes shared nouns, states, IDs, ownership, authority, or customer-facing vocabulary.
Use when changing harness gates, routing rules, skills, or automation behavior and benchmark/eval evidence is needed to avoid slowing normal coding performance. Do not use for ordinary app code changes.
Use when a request is early, ambiguous, or lacks a codebase-backed shared language; interview the user to expose assumptions before planning.
Use when a codebase, docs, ADRs, tests, prior reviews, or team traces exist; align new work with existing shared language before implementation.
Use first for normal or high-risk natural-language work to choose task mode, tier, grill path, spec layers, team-rule scan, and required gates before implementation.
| name | product-planner |
| description | Use after /office-hours when the problem is defined but the plan and scope are not yet ready. Judges readiness through discovery, product, and engineering lenses. Returns a readiness verdict (ready / revise / park) + concrete gaps to close before implementation starts. |
문제 정의는 끝났는데 (office-hours 이후) 아직 PRD / Plan 이 불안한 단계를 잠그는 skill.
/office-hours 이후 "이 문제는 풀 가치가 있다" 가 결정됨PRD.md 초안이 있지만 acceptance criteria 가 모호Plan.md 쓰기 전, 또는 쓴 뒤 "이 정도면 scope_lock 해도 될까?" 판단 필요/office-hours 로 돌아가기runtime.json → gates.plan_reviewed == truegstack/Manta 의 다면 렌즈를 솔로 환경에 맞게 3개로 단순화:
size_check.py 기준) 와 Plan 의 self-assessment 가 일치하나?# Product Planner Verdict — <date>
## Readiness: ready | revise | park
## Discovery lens
- 사용자 관찰 증거: <구체>
- 현재 우회법: <구체>
- Gaps: <있으면 list, 없으면 "none">
## Product lens
- 10x claim: <왜 10x 인지 또는 "1.1x, park 권장">
- Acceptance criteria 구체성: high / medium / low
- Gaps: <list>
## Engineering lens
- In/Out scope 명시: yes / no
- Milestone 쪼개기: good / weak
- Rollback 계획: yes / no / n/a
- Tier 정확성: <match / mismatch>
- Gaps: <list>
## Close-before-scope-lock list
구현 시작 전에 반드시 해결할 것:
1. ...
2. ...
## Next gate
- If ready → `runtime_gate.py lock-scope` + `runtime_gate.py review-plan`
- If revise → 위 close list 를 PRD.md / Plan.md 에 반영 후 재평가
- If park → Documentation.md 에 "parked: <reason>" 기록 후 다른 작업으로
/office-hours 와 /plan-eng-review 사이의 자연스러운 연결고리Prompt.md, PRD.md, (있으면) Plan.md 초안ETHOS.md — 무너지지 않는 철학CLAUDE.md — 운영 헌법templates/PRD.md, templates/Plan.md — 양식 기준