agentleFS
chenklein26-makerchenklein26-maker/Harness-Starter/.agents/skills/handover/SKILL.md

handover

Skill119 starsChanged 52 days agoMITView on GitHub

将当前会话中的技术决策、运维流程或阶段性研发进展,归档为标准工程文档(ADR / SOP / Handover),并自动更新模块内的 README 归档索引。

51 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use incident, brainstorm and 7 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.
  • JkudjoSkill

    incident

    Production incident response — structured triage, hypothesis tree, safe remediation, incident record

    Also in 3 projects that use this

  • nicolasestremSkill

    brainstorm

    Structured idea generation and solution exploration with systematic analysis.

    Also in 3 projects that use this

  • GoogleSkill

    to-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 3 projects that use this

  • BlockSkill

    plan

    Draft a TDD, PRD, or lightweight plan in the conversation without committing it.

    Also in 3 projects that use this

  • MicrosoftSkill

    caveman

    Ultra-compressed response style that reduces output token count while preserving technical accuracy, with intensity levels and auto-clarity safety rules

    Also in 3 projects that use this

  • GoogleSkill

    grilling

    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 3 projects that use this

  • +2 more from google

The file

Files
SKILL.md

工程交接与架构归档指南 (Engineering Handover & ADR & SOP)

你好!当你在一次开发会话中完成了关键攻坚、做了重要技术选型、或者跑通了一套复杂的运维跑批流程时,把这些成果及时沉淀下来,是保证后续其他同学或新会话 Agent 能无缝接力、不踩重复坑的最稳妥方式。


一、 框架定位:HDD (Handoff-Driven Development)

本 Skill 属于 HDD 体系的 Handoffs 层:

  • 职责核心:专职解决跨会话、跨模型周期的“状态机转移、物理事实防幻觉与真理知识沉淀”;
  • 非目标 (Non-Goals):本 Skill 不做日常编码流程的裁判(不强制 TDD、不限制具体的开发范式),只负责在阶段性收口或交接时打出高保真断点;
  • 抗模型迭代衰减:无论未来底层大模型推理能力如何升级,AI 均无法凭空预知你的私有业务决策、客观时序冲突与当前跑批状态。结构化的 Handoffs 是系统长期演进中抵御遗忘的最坚固防线。

本 Skill 采用控制逻辑与参考模板分离的轻量设计:主文件负责流程导航,骨架模板按需单点查阅。


二、 快速确定文档类型 (ADR / SOP / Handover)

根据当前会话的核心成果,挑选最契合的一个类型,并查阅对应的模板文件:

文档类型适用场景状态标签 (Status 推荐)对应参考模板核心目标
ADR (架构决策)技术选型、航道拆分/合并、引入新库、重大权衡或决定“暂不改动”架构决策 (ADR)、探讨/提案 (RFC)references/adr_template.md讲清为什么选 A 不选 B,避免未来盲目推倒重来
SOP (运维手册)定时任务、周末跑批、凭据更新、自动化巡检、故障排查生产固化 (Active)、维护中 (Draft)references/sop_template.md给出复制即用的命令与自愈预案,保证无人值守稳定运行
Handover (研发交接)每日收工、攻坚战役完成、门禁规则升级、代码重构收口生产基准 (Current)、版本归档 (Archived)references/handover_template.md交代今天改了哪、跑了什么单测、明天接班第一步敲什么

提示:如果用户未指定类型,且当前会话主要是修了 Bug、优化了业务代码并跑通了验证,请默认采用 Handover 类型。


三、 两步正向直出工作流 (SOP)

当被触发执行归档交接时,请直接执行以下两个步骤,杜绝无意义的中间态工具调用:

第一步:查阅对应模板并落盘文档

  1. 物理事实核验(杜绝文件幻觉):
    • 绝对不要凭多轮对话的模糊记忆盲猜改动文件。在列出“改动清单”和“核心代码资产”之前,先锚定真实的物理事实:
      • 若工作区存在 Git:运行 git status -s 查看真实改动;
      • 若工作区非 Git:核实本会话实际通过 write_to_file 或 replace_file_content 动过的文件,或在终端检查目标模块最近修改的文件时间戳;
    • 真实存在性保障:文档中引用的每一个文件路径与链接,必须在磁盘中真实存在,严禁凭空构造不存在的辅助脚本或类库。
  2. 规范模板要素(路由地图 + 正向资产交互):
    • 必须在顶部包含清晰扁平的 路由式摘要(注明当前状态、关键决策、改动范围、接班即刻动作及重点必读章节);
    • 涉及大型数据底册或日志时,在涉及文件清单中正向注明抽样或 grep 建议,杜绝大篇幅罗列禁区的“负向激发反模式(粉色大象)”。
  3. 按需查阅模板:使用 view_file 查阅上述对应的单个模板(例如确定写 ADR 则仅阅读 references/adr_template.md,无需阅读其他模板)。
  4. 生成命名并落盘:
    • 文件名规范:YYYY-MM-DD_<topic_slug>.md(如 2026-09-18_quality_gates_upgrade.md);
    • 写入对应业务模块下的 docs/handovers/ 目录;
    • 使用 write_to_file 工具直接写入目标目录。

第二步:更新归档索引表 (README.md)

  1. 使用 view_file 查阅该目录下的 README.md。
  2. 时间序归档表追加:在 ## 归档索引 表格的最上方(紧随表头后第一行),插入本次新文档的归档行:
    | YYYY-MM-DD | [YYYY-MM-DD 文档标题](./文档文件名.md) | 核心主题摘要(2~3 句话清晰提炼) | 状态标签 |
  3. 主题与分类导航同步:若该 README 维护了按主题分类导航(如 ### 架构决策 (ADR)、### 运维指南 (SOP) 等板块),同步在该分类列表下追加对应的超链接与一句话定位,实现时间序与主题序双维检索。
  4. 使用 replace_file_content 将新增内容合并入 README.md,保持索引看板永远最新。

四、 写作风格与接班导引

  • 老程序员带新人的口吻:语言平实、温和、逻辑严谨,多解释“为什么要这样做”,避免使用生硬或压迫性字眼;
  • 信息高保真度:严禁含糊其辞,关键代码使用可点击的 Markdown 文件链接,运维操作给出完整的带参命令行,验证给出明确的测试断言与耗时;
  • 新 Agent 快速冷启动:新接手的 Agent 进入项目时,只需查阅 docs/handovers/README.md 顶部的最新交接文档,通过顶部的 路由式摘要 建立大局观,再按指引跳转到关键章节,即可在 10 秒内理解当前系统状态并执行下一步操作。

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.