handover
Skill0 starsChanged 3 months agoMITView on GitHub
Write a handover that lets a zero-context agent resume the work in one read. Use when a session may end, context is running long, before major fan-out, when switching major tasks, or when the user says handover, continue tomorrow, or pick this up later. Written too late is written badly — be early.
53 other projects use a version of this.
Adopted by
Most recently taken up by
- Kealman/cland-v0their own version, first seen Nov 15, 2026
- gjoranv/claude-plan-skillstheir own version, first seen Nov 15, 2026
- yagizdo/quivertheir own version, first seen Nov 15, 2026
- thiagobluhm/o1memtheir own version, first seen Nov 8, 2026
- randommonicle/claude-skillstheir own version, first seen Nov 5, 2026
- hmislk/hmistheir own version, first seen Nov 2, 2026
Used with
Projects with it also use harness-init, incident and 9 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
steptianSkillharness-init
初始化 .harness 开发框架,集成代码修改影响范围评估和测试覆盖建议功能。触发词:'初始化新项目'、'harness init'、'更新 harness'、'分析影响范围'、'评估修改影响'
Also in 3 projects that use this
JkudjoSkillincident
Production incident response — structured triage, hypothesis tree, safe remediation, incident record
Also in 3 projects that use this
GoogleSkillto-tickets
Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker — edges as text in one file per ticket locally, or native blocking links on a real tracker.
Also in 4 projects that use this
BlockSkillplan
Draft a TDD, PRD, or lightweight plan in the conversation without committing it.
Also in 4 projects that use this
GoogleSkillgrilling
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
Also in 4 projects that use this
Microsoft AzureSkilldesign
Design rules and conventions for the API Center Portal. Use when editing detail pages, card components, badges, layout, navigation, sidebars, or headers. Covers badge styling, metadata placement, page navigation patterns, and layout alignment.
Also in 3 projects that use this
- +2 more from google
Other versions53 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 53
- me2resh/apexyard★ 542same name
- hmislk/hmis★ 245same name
- chenklein26-maker/Harness-Starter★ 119same name
- k1ein-chen/Harness-Starter★ 119same name
- eai-org/agent-toolkit★ 94same name
- manusco/resonance★ 38same name
- chacosoldier/compabob★ 34same name
- randommonicle/claude-skills★ 27same name
- yagizdo/quiver★ 16same name
- L-X-T/ng-agentic-skills★ 13same name
43 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository20 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- brainstormSkill
- cleanupSkill
- context-managementSkill
- critiqueSkill
- debuggingSkill
- design-decisionsSkill
- diff-managementSkill
- fan-outSkill
- final-checkSkill
- loopsSkill
- memorySkill
- orientSkill
- planningSkill
- researchSkill
- roadmapSkill
- verificationSkill
- web-testingSkill
- writing-reviewSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 40 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 31
Before finishing, re-read the handover pretending you know nothing.
- Distinctive: line 34
Read newest handover → read linked plan → verify claimed state (re-run the passing checks.
“Common” is measured: kept by at least 6 in 10 of the 40 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Handover
A handover succeeds if a fresh agent with ZERO context — no conversation history, no memory of this session — can resume the work after one read. Write against that standard and nothing weaker.
Triggers (write one without being asked)
- Session likely ending, or context getting long (be proactive — a handover written too late is written badly).
- About to fan out major parallel work (the handover doubles as orchestrator state).
- Switching to a different major task.
- User says "handover", "pick this up later", "continue tomorrow".
Location
docs/handovers/YYYY-MM-DD-HHMM-<slug>.md using templates/handover.md. Newest file = current state. Never overwrite an old handover; supersede it.
Required content (all sections, no exceptions)
- Mission — the original request, verbatim or near-verbatim, plus current interpretation.
- State — what is DONE (with evidence: paths, passing checks), what is IN PROGRESS (exactly where it stopped, mid-loop iteration count if looping), what is NOT STARTED.
- Next action — the single concrete step the successor should take first. Not a theme; a step ("run X, it currently fails with Y, the fix is likely in Z").
- Live plan — link to the plan file + any amendments since.
- Landmines — everything that will waste the successor's time: failed approaches and WHY they failed, misleading file names, flaky checks, things that look done but aren't.
- Decisions since last handover — links to ADRs.
- Open questions for the user — anything blocked on user input.
- Verification state — which checks pass right now, which fail, exact commands to re-run them.
Quality test
Before finishing, re-read the handover pretending you know nothing. Every "as discussed", "the usual place", "continue the approach" is a failure — replace with explicit content. Paths absolute or repo-relative, commands copy-pasteable, no references to conversation context.
On resume (successor protocol)
Read newest handover → read linked plan → verify claimed state (re-run the passing checks; trust nothing) → take the Next action. If claimed state doesn't verify, write that discrepancy down before proceeding.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

