resume-handoff by parcadei/continuous-claude-v3
npx skills add https://github.com/parcadei/continuous-claude-v3 --skill resume-handoff你需要通过交互式流程从交接文档中恢复工作。这些交接文档包含了先前工作会话的关键上下文、经验教训和后续步骤,需要理解并继续。
当调用此命令时:
* 如果参数中提供了交接文档路径,则跳过默认消息
* 立即完整阅读交接文档
* 立即阅读其在 `thoughts/shared/plans` 或 `thoughts/shared/research` 下链接的任何研究或计划文档。**不要**使用子代理来阅读这些关键文件。
* 通过吸收交接文档中的相关上下文、阅读其提到的其他文件来开始分析过程
* 然后向用户提出行动方案并确认,或就方向请求澄清。
2. 如果提供了工单号(如 ENG-XXXX):
* 定位该工单最新的交接文档。工单将位于 `thoughts/shared/handoffs/ENG-XXXX` 目录下,其中 `ENG-XXXX` 是工单号。例如,对于 `ENG-2124`,交接文档将在 `thoughts/shared/handoffs/ENG-2124/` 目录中。**列出此目录的内容。**
* 目录中可能有零个、一个或多个文件。
* **如果目录中没有文件,或者目录不存在**:告诉用户:"抱歉,我似乎找不到那个交接文档。您能提供它的路径吗?"
* **如果目录中只有一个文件**:使用该交接文档继续
* **如果目录中有多个文件**:使用文件名中指定的日期和时间(格式为 `YYYY-MM-DD_HH-MM-SS`,24小时制),使用**最新的**交接文档继续。
* 立即完整阅读交接文档
* 立即阅读其在 `thoughts/shared/plans` 或 `thoughts/shared/research` 下链接的任何研究或计划文档;**不要**使用子代理来阅读这些关键文件。
* 通过吸收交接文档中的相关上下文、阅读其提到的其他文件来开始分析过程
* 然后向用户提出行动方案并确认,或就方向请求澄清。
3. ,则回复:
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
我将帮助您从交接文档恢复工作。让我查找可用的交接文档。
您希望从哪个交接文档恢复?
提示:您可以直接使用交接文档路径调用此命令:`/resume_handoff `thoughts/shared/handoffs/ENG-XXXX/YYYY-MM-DD_HH-MM-SS_ENG-XXXX_description.md`
或者使用工单号从该工单的最新交接文档恢复:`/resume_handoff ENG-XXXX`
然后等待用户的输入。
* 使用 Read 工具,**不带** limit/offset 参数
* 提取所有部分:
* 任务及其状态
* 最近的更改
* 经验教训
* 产出物
* 行动项和后续步骤
* 其他备注
2. 生成聚焦的研究任务:根据交接内容,生成并行研究任务以验证当前状态:
任务 1 - 收集产出物上下文:
阅读交接文档中提到的所有产出物。
1. 阅读"产出物"中列出的功能文档
2. 阅读引用的实施计划
3. 阅读任何提到的研究文档
4. 提取关键需求和决策
使用工具:Read
返回:产出物内容摘要和关键决策
3. 等待所有子任务完成后再继续
* 完整阅读"经验教训"部分的文件
* 阅读"最近的更改"部分的文件以了解修改内容
* 阅读研究过程中发现的任何新的相关文件
呈现全面的分析:
我已分析了由[研究员]于[日期]进行的交接。以下是当前情况:
原始任务:
已验证的关键经验教训:
最近更改状态:
已审查的产出物:
建议的后续行动: 根据交接文档的行动项和当前状态:
已识别的潜在问题:
我是否应该继续执行[建议的行动 1],或者您想调整方法?
在继续之前获取确认
* 将交接文档中的行动项转换为待办事项
* 添加分析过程中发现的任何新任务
* 根据依赖关系和交接指南确定优先级
2. 呈现计划:
我已根据交接文档和当前分析创建了任务列表:
[显示待办事项列表]
准备好开始第一个任务:[任务描述]吗?
关键:不要直接实施。始终通过 Task 工具生成。
负责人(可以生成工作者):
| 代理 | 领域 | 用于 |
|---|---|---|
kraken | 实施 | 大型功能、新系统、主要组件 |
architect | 计划 | 功能设计、系统架构、实施规划 |
phoenix | 计划 | 重构计划、迁移、代码库重组 |
herald | 部署 | 发布、部署、发布 |
maestro | 编排 | 复杂的多代理工作流 |
工作者(专注的专家):
| 代理 | 领域 | 用于 |
|---|---|---|
spark | 实施 | 快速修复、补丁、小调整 |
scribe | 文档 | 文档、指南、解释 |
sleuth | 调试 | 错误调查、跟踪、根本原因分析 |
aegis | 调试 | 安全审计、漏洞扫描 |
profiler | 调试 | 性能优化、瓶颈分析 |
arbiter | 验证 | 单元测试 |
atlas | 验证 | E2E/集成测试 |
oracle | 研究 | 外部文档、最佳实践、操作指南 |
scout | 研究 | 代码库探索、查找现有代码 |
pathfinder | 研究 | 仓库结构分析 |
plan-reviewer | 审查 | 功能计划审查、设计验证 |
plan-reviewer | 审查 | 迁移审查、重构验证 |
chronicler | 会话 | 会话分析、历史摘要 |
通过 Task 工具生成专家:
使用 Task 工具,参数如下:
在提示中包含交接上下文:
* 交接文档中的关键经验教训
* 附带行号的文件引用
* 要遵循的模式
* 要避免的陷阱
4. 等待代理完成,然后继续下一个任务
* 首先完整阅读交接文档
* 验证所有提到的更改仍然存在
* 检查是否有任何回归或冲突
* 阅读所有引用的产出物
2. 保持交互性:
* 在开始工作前呈现发现
* 就方法达成一致
* 允许进行方向调整
* 根据当前状态与交接状态的差异进行调整
3. 利用交接文档的智慧:
* 特别关注"经验教训"部分
* 应用记录的模式和方法
* 避免重复提到的错误
* 在已发现的解决方案基础上继续
4. 保持连续性:
* 使用 TodoWrite 保持任务连续性
* 在提交中引用交接文档
* 记录与原始计划的任何偏差
* 考虑在完成后创建新的交接文档
5. 行动前验证:
* 切勿假设交接状态与当前状态一致
* 验证所有文件引用是否仍然存在
* 检查自交接以来是否有破坏性更改
* 确认模式是否仍然有效
User: /resume_handoff specification/feature/handoffs/handoff-0.md
Assistant: 让我阅读并分析那个交接文档...
[完整阅读交接文档]
[生成研究任务]
[等待完成]
[阅读已识别的文件]
我已分析了[日期]的交接文档。以下是当前情况...
[呈现分析]
我是否应该继续实施 webhook 验证修复,或者您想调整方法?
User: 是的,继续处理 webhook 验证
Assistant: 这是一个错误修复任务,所以我会路由到 `spark` 代理。
[使用 Task 工具,参数为 subagent_type="spark",提示包含:
- webhook 验证修复任务
- 交接文档中的关键经验教训
- 相关的文件:行号引用
- 要遵循的模式]
[等待 spark 代理完成]
spark 代理已完成 webhook 验证修复。继续下一个任务...
每周安装量
198
仓库
GitHub 星标数
3.6K
首次出现
2026年1月24日
安全审计
安装在
opencode192
gemini-cli190
codex190
github-copilot187
cursor186
amp184
You are tasked with resuming work from a handoff document through an interactive process. These handoffs contain critical context, learnings, and next steps from previous work sessions that need to be understood and continued.
When this command is invoked:
If the path to a handoff document was provided :
thoughts/shared/plans or thoughts/shared/research. do NOT use a sub-agent to read these critical files.If a ticket number (like ENG-XXXX) was provided :
thoughts/shared/handoffs/ENG-XXXX where ENG-XXXX is the ticket number. e.g. for ENG-2124 the handoffs would be in thoughts/shared/handoffs/ENG-2124/. List this directory's contents.YYYY-MM-DD_HH-MM-SS in 24-hour time format), proceed with the most recent handoff document.thoughts/shared/plans or thoughts/shared/research; do NOT use a sub-agent to read these critical files.If no parameters provided , respond with:
I'll help you resume work from a handoff document. Let me find the available handoffs.
Which handoff would you like to resume from?
Tip: You can invoke this command directly with a handoff path: `/resume_handoff `thoughts/shared/handoffs/ENG-XXXX/YYYY-MM-DD_HH-MM-SS_ENG-XXXX_description.md`
or using a ticket number to resume from the most recent handoff for that ticket: `/resume_handoff ENG-XXXX`
Then wait for the user's input.
Read handoff document completely :
Spawn focused research tasks : Based on the handoff content, spawn parallel research tasks to verify current state:
Task 1 - Gather artifact context:
Read all artifacts mentioned in the handoff.
1. Read feature documents listed in "Artifacts"
2. Read implementation plans referenced
3. Read any research documents mentioned
4. Extract key requirements and decisions
Use tools: Read
Return: Summary of artifact contents and key decisions
Wait for ALL sub-tasks to complete before proceeding
Read critical files identified :
Present comprehensive analysis :
I've analyzed the handoff from [date] by [researcher]. Here's the current situation:
**Original Tasks:**
- [Task 1]: [Status from handoff] → [Current verification]
- [Task 2]: [Status from handoff] → [Current verification]
**Key Learnings Validated:**
- [Learning with file:line reference] - [Still valid/Changed]
- [Pattern discovered] - [Still applicable/Modified]
**Recent Changes Status:**
- [Change 1] - [Verified present/Missing/Modified]
- [Change 2] - [Verified present/Missing/Modified]
**Artifacts Reviewed:**
- [Document 1]: [Key takeaway]
- [Document 2]: [Key takeaway]
**Recommended Next Actions:**
Based on the handoff's action items and current state:
1. [Most logical next step based on handoff]
2. [Second priority action]
3. [Additional tasks discovered]
**Potential Issues Identified:**
- [Any conflicts or regressions found]
- [Missing dependencies or broken code]
Shall I proceed with [recommended action 1], or would you like to adjust the approach?
Get confirmation before proceeding
Use TodoWrite to create task list :
Present the plan :
I've created a task list based on the handoff and current analysis:
[Show todo list]
Ready to begin with the first task: [task description]?
CRITICAL: Do NOT implement directly. Always spawn via Task tool.
Leads (can spawn workers):
| Agent | Domain | Use For |
|---|---|---|
kraken | implement | Large features, new systems, major components |
architect | plan | Feature design, system architecture, implementation planning |
phoenix | plan | Refactoring plans, migrations, codebase restructuring |
herald | deploy | Releases, deployments, publishing |
maestro | orchestrate |
Workers (focused specialists):
| Agent | Domain | Use For |
|---|---|---|
spark | implement | Quick fixes, patches, minor tweaks |
scribe | document | Documentation, guides, explanations |
sleuth | debug | Bug investigation, tracing, root cause analysis |
aegis | debug | Security audits, vulnerability scanning |
profiler | debug | Performance optimization, bottleneck analysis |
Spawn the specialist via Task tool :
Use Task tool with:
- subagent_type: [selected agent from above]
- prompt: [task description + relevant handoff context + learnings]
Include handoff context in the prompt :
Wait for agent completion , then proceed to next task
Be Thorough in Analysis :
Be Interactive :
Leverage Handoff Wisdom :
Track Continuity :
Validate Before Acting :
User: /resume_handoff specification/feature/handoffs/handoff-0.md
Assistant: Let me read and analyze that handoff document...
[Reads handoff completely]
[Spawns research tasks]
[Waits for completion]
[Reads identified files]
I've analyzed the handoff from [date]. Here's the current situation...
[Presents analysis]
Shall I proceed with implementing the webhook validation fix, or would you like to adjust the approach?
User: Yes, proceed with the webhook validation
Assistant: This is a bugfix task, so I'll route to the `spark` agent.
[Uses Task tool with subagent_type="spark" and prompt containing:
- The webhook validation fix task
- Key learnings from handoff
- Relevant file:line references
- Patterns to follow]
[Waits for spark agent to complete]
The spark agent has completed the webhook validation fix. Moving to the next task...
Weekly Installs
198
Repository
GitHub Stars
3.6K
First Seen
Jan 24, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykFail
Installed on
opencode192
gemini-cli190
codex190
github-copilot187
cursor186
amp184
开源项目教练指南 - 诊断问题、制定行动计划、优化开源项目运营
31,600 周安装
| Complex multi-agent workflows |
arbiter | validate | Unit tests |
atlas | validate | E2E/integration tests |
oracle | research | External docs, best practices, how-to |
scout | research | Codebase exploration, finding existing code |
pathfinder | research | Repository structure analysis |
plan-reviewer | review | Feature plan review, design validation |
plan-reviewer | review | Migration review, refactoring validation |
chronicler | session | Session analysis, history summaries |