handoff
Skill2 starsChanged 4 months agoMITView on GitHub
跨 AI agent（Claude Code、Codex 等）的工作交接协议。当用户准备从一个 agent 切到另一个、 说"准备交接 / 交接工作 / handoff / 整理一下进度好切换 / 我要换成 codex 来做 / 把现在的进度交代清楚"时， 整理进度写入本地 HANDOFF.md、提议原子 commit（用户确认后才提交）、留下干净工作区； 当用户说"接手 / pickup / 继续上一个 agent 的活 / 读一下交接进度再开始"时， 读取 HANDOFF.md 并与 git 真实状态对账后承接。即使没说"交接"二字，只要在表达 "换一个 agent 继续这个项目"或"把当前进度交代清楚以便切换"，都应使用本 skill。
- Reads credentials
191 other projects use a version of this.
Adopted by
Most recently taken up by
- xiaoxiaosrm/dsh-mattpocock-skillstheir own version, first seen Nov 8, 2026
- ethosagent/ethostheir own version, first seen Nov 8, 2026
- dsifry/metaswarmtheir own version, first seen Nov 8, 2026
- glebis/claude-skillstheir own version, first seen Nov 8, 2026
- domengabrovsek/agent-configtheir own version, first seen Nov 8, 2026
- domengabrovsek/claudetheir own version, first seen Nov 8, 2026
Used with
Projects with it also use decision-mapping, setup-ts-deep-modules and 10 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.
FabienDehopreSkilldecision-mapping
Turn a loose idea into a sequenced map of investigation tickets, then drive them to resolution one at a time.
Also in 8 projects that use this
liufeng1976Skillsetup-ts-deep-modules
Wire dependency-cruiser into a TypeScript repo so each package is a deep module — implementation hidden in subfolders, reachable only through its entry-point files. User-invoked.
Also in 42 projects that use this
AWSSkillto-questionnaire
Turn a decision you can't fully answer into a questionnaire for someone else to fill in.
Also in 93 projects that use this
GoogleSkillask-matt
Ask which skill or flow fits your situation. A router over the skills in this repo.
Also in 87 projects that use this
RoentekSkillloop-me
Grill me about specs for the workflows I want to build, within this workspace.
Also in 51 projects that use this
LesaniSkillwriting-beats
Shape an article as a journey of beats, choose-your-own-adventure style. The user picks a starting beat from the raw material, you write only that beat, then offer options for where to pivot next, beat by beat, until the article reaches a natural end. Use when the user has raw material and wants to assemble it as a narrative rather than an argument.
Also in 54 projects that use this
Other versions191 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 191
- mattpocock/skills★ 309ksame name
- QuivrHQ/quivr★ 40ksame name
- The-Vibe-Company/quivr★ 40ksame name
- GreyDGL/PentestGPT★ 16ksame name
- ykdojo/claude-code-tips★ 10ksame name
- ArcReel/ArcReel★ 6.3ksame name
- vinvcn/mattpocock-skills-zh-CN★ 5.5ksame name
- withcoral/coral★ 4.9ksame name
- epicenter-md/epicenter★ 4.8ksame name
- EpicenterHQ/epicenter★ 4.8ksame name
181 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 repository11 other files it gives its agents.
- agnes-aiSkill
- auto-approveSkill
- blog-pipelineSkill
- context-monitorSkill
- curator-pipelineSkill
- grok-imageSkill
- opportunity-radarSkill
- public-apisSkill
- readme-writerSkill
- sentinelSkill
- smart-fetchSkill
The file
Files
工作交接（Handoff）
同一个项目轮流让不同 agent（Claude Code / Codex / Kimi CLI…）来做，切换时会丢上下文、 留下半成品工作区，下一棒接手容易出错。这个 skill 把"人类同事交接班"那套协议固化下来： 交出方负责把现场交代清楚、留干净工作区；接手方负责对账后再动手。
核心分工：机械、确定性的事（采集 git 状态、探测测试命令、检查工作区是否干净）交给脚本， 保证不同 agent 行为一致；需要判断的事（总结进度、规划下一步）交给你（LLM）。
何时做哪个动作
- 用户在交出（要离开 / 要换 agent / "整理进度交接"）→ 走 A. 交接出去。
- 用户在接手（刚切过来 / "继续上一个 agent 的活" / "读一下进度"）→ 走 B. 接手。
判断不了就直接问一句："你是要把当前进度交接出去，还是接手上一棒的活？"
A. 交接出去（handoff）
目标产物：一份写实的 HANDOFF.md + 一个干净的工作区 + 一段可直接粘贴给下一棒的交接话术。
1. 采集客观事实（先跑脚本，别凭记忆）
bash <skill-dir>/scripts/handoff.sh脚本会给出：当前分支、工作区是否干净、改动统计、最近 commit、疑似敏感文件、探测到的测试命令。 先读它的输出，再写总结。 你对"做了什么"的记忆可能漏或错，git 才是真相——拿脚本输出对账。
2. 写 HANDOFF.md
用 references/HANDOFF_TEMPLATE.md 的结构，写到项目根目录的 HANDOFF.md。
关键是"进行中"和"下一步"要具体到文件:行 + 思路 + 卡在哪 + 验证标准——
让接手方不用猜就能继续，而不是"继续做认证功能"这种空话。
测试状态据脚本探测如实填：跑过且通过就写命令和结果；没跑或探测不到就写"未知/需人工"， 不要假装测试通过。
3. 提议 commit，等用户确认（不要自动提交）
把改动按逻辑分组，给出原子 commit 方案（每个 commit 一件事，conventional 风格的 message）， 列给用户看，等确认后再执行。这一步绝不自动跑——闷头 commit 可能把半成品或凭证提进去。
铁律：脚本"疑似敏感文件"里命中的（*.local.*、.env*、密钥证书等）绝不进交接 commit。
在 HANDOFF.md 里标注它们存在但不提交。
确认后按方案提交。该忽略的提醒用户加进 .gitignore。
4. 自检并报告
再跑一次 git status，确认工作区真的干净（除了刻意保留、且已在 HANDOFF.md 标注的本地文件）。
向用户报告：交接单写好了、提交了哪几个 commit、工作区状态、测试状态。
有没做完或不确定的，明说，别粉饰。
5. 产出可粘贴的「交接话术」给用户（默认主动给，别等用户开口）
报告完，主动附一段可直接整段复制、粘贴给下一棒 agent（Codex / Kimi…）的简短话术。
用户通常是手动把任务转交出去的：HANDOFF.md 是交接载体，这段话术是"点醒下一棒去读它、
并知道第一步干什么"的钥匙——没有它，用户就得自己再写一遍。漏给这段=交接没做完。
话术要素（精炼几句，用代码块包住方便整段复制）：
- 项目路径 + 分支；第一句就让它读
HANDOFF.md全文（+ 必要时DESIGN.md/CLAUDE.md）再动手，并跑pickup.sh对账。 - 一句话交代当前状态（已完成 / 待推进）。
- 点明接手后第一步做什么；若有悬而未决、需先和用户确认的，写明"先别埋头改，先给方案等拍板"。
- 关键约束（交流语言、设计系统、测试 / 部署方式…）一句带过，细节让它去 HANDOFF.md 看。
- 末尾要求它先复述理解 + 说清第一步，再开干（呼应 B 的接手纪律）。
B. 接手（pickup）
目标：在动手前确认"交接单说的"和"仓库真实状态"一致，把上下文真正装进来。
1. 读交接单 + 对账
bash <skill-dir>/scripts/pickup.sh脚本会打印 HANDOFF.md 全文，并把当前工作区状态、最近 commit 摆出来供核对。
2. 核对一致性
- 交接单说"工作区干净"，脚本却显示 DIRTY？→ 上一棒没交接干净，先向用户指出，别假装没看见。
- 交接单提到的 commit hash 在
git log里找得到吗？找不到说明分支/状态对不上，先澄清。 - 标注"不提交"的敏感文件还在且未被误提交吗？
3. 复述 + 确认后开工
用一两句话向用户复述你的理解：当前目标、接下来第一步打算做什么。得到确认（或纠正）再动手。 这一步花几秒钟，能挡住"基于错误理解一路做下去"的大错。
接手完成、开始正式干活后，旧的 HANDOFF.md 可以删掉或留作记录（问用户偏好；默认保留，下次交接覆盖）。
给其它 agent 用（Codex 等）
本 skill 的可移植性来自协议文件（HANDOFF.md）和脚本都与平台无关——任何能读文件、跑 bash、用 git
的 agent 都能参与。Claude Code 通过这个 SKILL.md 触发；Codex 没有 skill 系统，但可以在项目的
AGENTS.md 里加一段约定，指向同一套脚本和同一个 HANDOFF.md，行为就对齐了。
参见 references/codex-agents-snippet.md。
文件
scripts/handoff.sh— 交出方：采集客观快照（只读）scripts/pickup.sh— 接手方：交接单与仓库状态对账（只读）references/HANDOFF_TEMPLATE.md— 交接单结构references/codex-agents-snippet.md— 给 Codex 的 AGENTS.md 约定片段
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.