TA

task-handoff-checklist

Automates structured handoff documentation upon task completion.

Install

mkdir -p .claude/skills/task-handoff-checklist && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/16753" && unzip -o skill.zip -d .claude/skills/task-handoff-checklist && rm skill.zip

Installs to .claude/skills/task-handoff-checklist

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

开发任务完成后自动扫描变更,从导航、文档、规则、工作流、测试、风险、代码质量、后续事项八个维度生成结构化交接报告,让验收者零追问即可核对。触发词:"交接"、"验收"、"handoff"、"/handoff"。
104 charsno explicit “when” trigger
Intermediate

Key capabilities

  • Scan code changes for task completion
  • Generate structured handoff reports across eight dimensions
  • Identify navigation and entry point changes
  • Document changes in rules and conventions
  • Outline test plans and preview URLs

How it works

The skill scans code changes after a development task is complete and generates a structured handoff report covering eight dimensions, including navigation, documentation, rules, workflow, testing, risks, code quality, and follow-up items.

Inputs & outputs

You give it
Completed development task with code changes
You get back
A structured handoff report detailing changes, tests, and risks

When to use task-handoff-checklist

  • Generate task completion report
  • Hand off finished tasks
  • Document system changes

About this skill

任务交接清单

版本:v2.0.0 | 先取证,后总结,不把模板当事实

何时使用

  • 跨多个文件、模块或接口的任务完成后。
  • 需要换人、提 PR、发布或交给产品负责人验收时。
  • 小型文字修改可直接给简短说明,无需强行生成大报告。

Phase 1:建立事实范围

  1. 动态发现远端默认分支并计算 merge-base。
  2. 收集已提交差异、未提交差异和未跟踪文件,明确哪些未进入提交。
  3. 读取仓库级与变更目录最近的规则文件。
  4. 从构建清单和 CI 发现模块及验证命令,不硬编码技术栈。

参考命令见 reference/scan-commands.md

Phase 2:八维扫描

维度必须回答的问题
入口与使用路径用户从哪里进入,新增或改变了哪些页面、命令、API、事件或配置入口?
文档与决策需求、设计、操作手册、迁移说明、决策记录是否需要同步?
契约与数据API、schema、事件、存储、权限、配置和兼容性是否变化?
测试与证据运行了什么,断言了什么,哪些用户路径有真实证据?
发布与运维部署、迁移、回滚、监控、开关、依赖和环境变量是否变化?
安全与隐私凭据、日志、权限、用户数据和供应链风险是否处理?
已知风险哪些限制仍存在,影响谁,触发条件是什么?
后续行动负责人、优先级、完成条件和依赖是什么?

只有证据支持时才写“已完成”。无法验证时写“未验证”并说明原因。

Phase 3:预览与验收入口

若仓库安装了权威预览技能或部署工具,调用其真实查询命令取得地址。不得根据分支名、项目名或历史规律拼接 URL。若没有预览能力,写明“未发现权威预览提供方”,不要给猜测地址。

对非技术用户,交接中同时写:

  • 从哪里开始。
  • 按什么顺序操作。
  • 预期看到什么。
  • 如需登录,凭据从哪个安全渠道取得;不得把密码写入仓库或公开报告。

Phase 4:输出

# 任务交接清单

## 一句话结果
<谁现在能多做什么,以及当前是否可交付>

## 改动范围
- 基线:<base and merge-base>
- 模块:<modules>
- 文件:<count and summary>

## 使用与验收
- 入口:<route, command, API or none>
- 操作步骤:<plain-language steps>
- 预览:<authoritative URL or unavailable>
- 登录:<secure retrieval method or not required>

## 八维检查
| 维度 | 状态 | 证据或待办 |
|---|---|---|

## 已运行验证
| 命令或路径 | 断言 | 结果 |
|---|---|---|

## 风险与后续
| 事项 | 影响 | 优先级 | 负责人 | 完成条件 |
|---|---|---|---|---|

完整示例见 reference/example.md

不可违反

  1. 不把未运行的测试写成通过。
  2. 不泄露密钥、账号密码或内部日志。
  3. 不硬编码某个产品的目录、导航表、数据库或平台。
  4. 不只给技术 diff,必须说明用户价值和实际操作路径。
  5. 不把“后续再测”包装成已完成。

When not to use it

  • When a task is not yet completed and ready for handoff
  • When the goal is to improve the pitch content itself

Limitations

  • The skill requires `git` commands to scan changes.
  • The skill's report generation is based on predefined templates and dimensions.

How it compares

This skill automates the generation of a complete, multi-dimensional handoff report, ensuring all aspects of a task are documented for review, unlike a manual process that might miss details.

Compared to similar skills

task-handoff-checklist side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
task-handoff-checklist (this skill)01moReviewIntermediate
session-wrap17moReviewIntermediate
workthrough109moReviewBeginner
doc-check42moReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

session-wrap

team-attention

This skill should be used when the user asks to "wrap up session", "end session", "session wrap", "/wrap", "document learnings", "what should I commit", or wants to analyze completed work before ending a coding session.

14

workthrough

bear2u

Automatically document all development work and code modifications in a structured workthrough format. Use this skill after completing any development task, bug fix, feature implementation, or code refactoring to create comprehensive documentation.

1085

doc-check

coder

Checks if code changes require documentation updates

427

pr-draft-summary

openai

Create a PR title and draft description after substantive code changes are finished. Trigger when wrapping up a moderate-or-larger change (runtime code, tests, build config, docs with behavior impact) and you need the PR-ready summary block with change summary plus PR draft text.

326

create-pr-description

antinomyhq

Generate and create pull request descriptions automatically using GitHub CLI. Use when the user asks to create a PR, generate a PR description, make a pull request, or submit changes for review. Analyzes git diff and commit history to create comprehensive, meaningful PR descriptions that explain what changed, why it matters, and how to test it.

213

github-contributor

daymade

Strategic guide for becoming an effective GitHub contributor. Covers opportunity discovery, project selection, high-quality PR creation, and reputation building. Use when looking to contribute to open-source projects, building GitHub presence, or learning contribution best practices.

17

Search skills

Search the agent skills registry