handoff
Compact the current conversation into a handoff document for another agent to pick up.
- License 许可
- GPL-3.0
- 最近更新
- 2026-11-14
- Stars
- ★ 6
- Forks
- 2
01 前言 Front Matter
- name
- handoff
- description
- Compact the current conversation into a handoff document for another agent to pick up.
- argument-hint
- What will the next session be used for?
- disable-model-invocation
- true
02 资源文件 1
- 其他.gh-get-source252 B
03 SKILL.md 正文
Write a handoff document summarising the current conversation so a fresh agent can continue the work. Save to the temporary directory of the user's OS - not the current workspace.
Include a "suggested skills" section in the document, which suggests skills that the agent should invoke.
Do not duplicate content already captured in other artifacts (PRDs, plans, ADRs, issues, commits, diffs). Reference them by path or URL instead.
Redact any sensitive information, such as API keys, passwords, or personally identifiable information.
If the user passed arguments, treat them as a description of what the next session will focus on and tailor the doc accordingly.
04 同仓库更多 Skills
staged-plan
Design a self-contained multi-stage plan whose markdown is the operational contract — every execution detail (Execution model, Hand-off conventions, retry rule, working-tree policy, reviewer gate, pre-execution placeholder gate) is encoded in the plan file itself. This is a PLANNING skill — it produces a plan and stops. Use when the user wants to design, scaffold, or decompose work into a staged subagent track. Typical invocations - "design a staged plan", "decompose this into stages", "scaffold a multi-stage plan", "plan in stages", "create a staged execution plan". Do NOT invoke during Phase 2 execution — the plan markdown is self-sufficient and re-invoking the skill is redundant.
setup-pocock
Sets up an `## Agent skills` block in AGENTS.md/CLAUDE.md and `docs/agents/` so the engineering skills know this repo's issue tracker (GitHub or local markdown), triage label vocabulary, domain doc layout, and — optionally — a PRD/roadmap track model. Run before first use of `to-issues`, `to-prd`, `triage`, `diagnose`, `tdd`, `improve-codebase-architecture`, or `zoom-out` — or if those skills appear to be missing context about the issue tracker, triage labels, or domain docs.
reviewer
Use ONLY when the user explicitly invokes /reviewer (literal slash command). Performs a native, findings-first review with a deterministic coverage audit run by the reviewer before emission (`scripts/fact_pack.py` + `scripts/audit.py`). Three evidence lanes (defect-hunter, test-auditor, verifier) run delegated or in-context depending on host capability; scout is discretionary. During validation this skill must NOT match generic "code review" requests.
to-prd
Turn the current conversation into a PRD and publish it to the project issue tracker — no interview, just synthesis of what you've already discussed.
to-issues
Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices.
prototype
Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.