session-handoff
Synthesizes the current session into a structured HANDOFF block for context transfer between sessions. Captures what was built, decisions made, and unresolved items.
- License 许可
- MIT
- 最近更新
- 2026-11-13
- Stars
- ★ 930
- Forks
- 84
01 前言 Front Matter
- name
- session-handoff
- license
- MIT
- description
- Synthesizes the current session into a structured HANDOFF block for context transfer between sessions. Captures what was built, decisions made, and unresolved items.
- auto-trigger
- false
- last-updated
- 1792022400000
- user-invocable
- true
- trigger_keywords
- [ "handoff", "session summary" ]
02 资源文件 2
- 参考文档__benchmarks__/mid-campaign.md802 B
- 参考文档__benchmarks__/no-active-work.md806 B
03 SKILL.md 正文
/session-handoff — Context Transfer
Identity
You summarize the current task accurately and economically so another session can continue it.
Orientation
Use when ending a session and wanting to preserve context for the next one. Also used automatically by orchestrators (Archon, Fleet) at session boundaries.
Don't use when: You want to extract reusable patterns from a completed campaign (use /learn), write a structured postmortem for a failed campaign (use /postmortem), or produce documentation rather than a context transfer.
Protocol
-
Reuse current evidence first:
- Start with the task, edits, verification results, decisions, and blockers already established in this session. If they are sufficient for a truthful handoff, make no tool calls.
- Do not repeat Git inspections, scan campaign/fleet directories, or read unrelated history merely to fill the format. A handoff summarizes work; it does not start a new audit.
- If a material fact is missing or may have changed since it was checked, perform one targeted read. Batch related checks into that call and limit them to the task's files or known campaign. If no budget remains, state the uncertainty rather than delaying or inventing a verification result.
-
Identify the primary thread: Use the current task and its known campaign, if any, as the anchor. Mention other campaigns only when they are already known and affect the handoff. Do not discover unrelated work to create a frame.
-
Map data to HANDOFF fields:
- What changed: actual task output and files changed; distinguish committed, uncommitted, and proposed work when known
- Key decisions: the decisions and reasons established while doing the task
- Unresolved items: failed or missing verification, known blockers, and explicitly deferred work
- Next steps: the next actionable step, or "none" when the task is complete
-
Output the HANDOFF block.
Output Format
---HANDOFF---
- {what was built or changed — be specific}
- {key decisions and tradeoffs — include reasoning}
- {unresolved items — what's blocking}
- {next steps — what the next session should do first}
---
Keep it to 3-5 bullets, under 150 words. This is a context transfer, not a report.
Quality Gates
- Every bullet must be actionable or informative
- No vague statements ("made progress on X")
- Specific file references where relevant
- Decisions include reasoning, not just the choice
Fringe Cases
.planning/ does not exist or was not inspected: Summarize the current task from session evidence. Do not inspect Git or infer campaign status merely to fill the handoff.
A relevant campaign file was found to be corrupted or unparseable: State that its status is unknown and name the file. Do not treat unreadable state as inactive or scan for other campaigns.
No active campaign and no git changes: If there is nothing to summarize, say so explicitly: "No active campaign or session changes found. Nothing to hand off." Do not fabricate a handoff.
No context to summarize (fresh session with no edits): Output a minimal handoff noting the session start state. At minimum, include what the user asked about and what was found.
Campaign is in a blocked/parked state: Include the block reason and the recommended next action in the handoff so the next session can resume immediately.
Contextual Gates
Reversibility: Green — this skill writes nothing to disk; the HANDOFF block is display-only. Cost: No cost actions — synthesis only; no agents spawned, no confirmation needed. Trust: No gates — safe at all trust levels.
Exit Protocol
Output the HANDOFF block and then wait for the next command. This skill does not write to disk — the HANDOFF block is the deliverable, for the user to copy into the next session or save manually.
04 同仓库更多 Skills
workspace
Multi-repo campaign coordinator. Same lifecycle as fleet -- scope claims, discovery relay, wave-based execution -- but the unit of work is a repo, not a file. Coordinates campaigns across repositories with shared context.
wiki
Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to ~400K words.
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for one-off inspection or tasks needing human judgment per file.
verify
Self-test the Citadel hook pipeline from within a live session. Exercises real tool calls (Write, Edit, Bash, Read) and checks that hooks fired, telemetry accumulated, and no errors occurred. Reports HOOK HEALTH: PASS or HOOK HEALTH: FAIL with a per-hook breakdown.
unharness
Safely leave Citadel using the active adoption receipt. Produces a no-write, reviewable plan, preserves a portable archive, removes only exact owned material, and reports modified or externally registered surfaces as retained or unknown. Legacy installs must be imported before exact leave is claimed.
triage
GitHub issue and PR investigator. Pulls open issues/PRs, classifies them, searches the codebase for root cause or reviews contributed code, proposes fixes with file:line references, and optionally implements fixes. Use for investigating GitHub issues and reviewing PRs; do NOT use for general code review unrelated to GitHub issues.