Menu
Save session context to HANDOVER.md for seamless continuation. Captures last task, queue position, git state, decisions, and resume checklist.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | sh-handoff |
| description | Save session context to HANDOVER.md for seamless continuation. Captures last task, queue position, git state, decisions, and resume checklist. |
Produce a HANDOVER.md document that captures the full session state so the next session (or agent) can resume without context loss.
/sh:loop iteration (step 13)/sh:autopilot stops (queue complete or paused)# HANDOVER — [date] [time]
## Last Completed Task
- **Task:** [task description from TODO-Today]
- **Status:** [completed | paused | blocked]
- **Outcome:** [1-2 sentence summary of what was done]
## Queue Position
- **Completed:** N of M total
- **Remaining:** [count] items in TODO-Today.md
- **Next up:** [first unchecked item description]
## Git State
- **Branch:** [current branch name]
- **Last commit:** [SHA + message]
- **Modified files:** [list of uncommitted changes, or "clean"]
- **Unpushed commits:** [count, or "all pushed"]
## Decisions Made This Iteration
- [Decision 1: what was decided and why]
- [Decision 2: ...]
## Open Questions
- [ ] [Question requiring human input]
- [ ] [Ambiguity encountered during execution]
## Resume Checklist
- [ ] Read this HANDOVER.md
- [ ] Check `.autopilot` semaphore state
- [ ] Review TODO-Today.md queue
- [ ] Verify git state matches above
- [ ] Continue from next unchecked item
.claude/memory.md if not already theregit status and git log output, not assumedMulti-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