메뉴
Daily session startup scan — assess pipeline state and determine next actions.
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
Multi-expert AI/ML specification review with scoring gate — model architecture, evaluation rigor, safety/alignment, and production readiness for AI systems and LLM apps
Multi-expert architecture review — boundaries, integration patterns, failure modes, evolvability
Multi-expert business analysis with advisory recommendations (no scoring gate)
Multi-expert intelligence pipeline review — discovery quality, ingestion resilience, scoring validity, platform compliance, taxonomy coherence, cost efficiency
Multi-expert mobile/native app specification review with scoring gate — Android, iOS, Swift, SwiftUI
Multi-expert personal-development review with scoring gate — learnability, adoption, human-centeredness, and capability impact for talent/learning/AI-augmentation designs
| name | sh-kickoff |
| description | Daily session startup scan — assess pipeline state and determine next actions. |
| disable-model-invocation | true |
Run at the start of each working session to understand pipeline state and determine next actions.
Read INBOX.md for untriaged items. If any exist, offer to run /sh:triage.
Read BACKLOG.md#Ready for items waiting to be queued. If any exist, offer to run /sh:workflow.
Read TODO-Today.md for unchecked [ ] items. If any exist, offer to resume /sh:autopilot.
Read ROADMAP.md and suggest what to refine next. Surface any items approaching staleness.
Next: action, no owner, no linked spec/sh:retro before starting work.claude/memory.md for context from previous sessionsReport the pipeline state concisely:
## Kickoff -- [date]
- INBOX: N untriaged items
- BACKLOG: N in Ideation, N in Refining, N Ready
- TODO-Today: N queued, N done
- Retro counter: N/10
- Stale items: [list or "none"]
- Recommendation: [next action with /sh: command]