Token导航 LogoToken导航TokenDH.com
研究检索执行命令github未标认证来源可访问clear审计异常

resume-handoff恢复切换

Agent Skill

resume-handoff 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

6,962

周安装

296

GitHub Stars

3,675

下载量

2,439
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

3

许可证

MIT

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:resume-handoff(恢复切换)
来源仓库:https://github.com/parcadei/continuous-claude-v3
仓库路径:skills/resume-handoff
安装命令:
npx skills add https://github.com/parcadei/continuous-claude-v3 --skill resume-handoff
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/parcadei/continuous-claude-v3 --skill resume-handoff

简介

用于查找、检索和筛选相关信息,支持基于关键词或任务场景快速定位结果。

  • 适用于需要从多来源线索中提取有效信息的场景。
  • 通过 npx skills add 命令从指定 GitHub 仓库安装使用。
  • 建议确认权限范围和维护状态,避免触发联网或文件读写操作。
  • resume-handoff 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

Resume work from a handoff document

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.

Initial Response

When this command is invoked:

  1. If the path to a handoff document was provided:

- If a handoff document path was provided as a parameter, skip the default message - Immediately read the handoff document FULLY - Immediately read any research or plan documents that it links to under thoughts/shared/plans or thoughts/shared/research. do NOT use a sub-agent to read these critical files. - Begin the analysis process by ingesting relevant context from the handoff document, reading additional files it mentions - Then propose a course of action to the user and confirm, or ask for clarification on direction.

  1. If a ticket number (like ENG-XXXX) was provided:

- locate the most recent handoff document for the ticket. Tickets will be located in 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. - There may be zero, one or multiple files in the directory. - If there are zero files in the directory, or the directory does not exist: tell the user: "I'm sorry, I can't seem to find that handoff document. Can you please provide me with a path to it?" - If there is only one file in the directory: proceed with that handoff - If there are multiple files in the directory: using the date and time specified in the file name (it will be in the format YYYY-MM-DD_HH-MM-SS in 24-hour time format), proceed with the *most recent* handoff document. - Immediately read the handoff document FULLY - Immediately read any research or plan documents that it links to under thoughts/shared/plans or thoughts/shared/research; do NOT use a sub-agent to read these critical files. - Begin the analysis process by ingesting relevant context from the handoff document, reading additional files it mentions - Then propose a course of action to the user and confirm, or ask for clarification on direction.

  1. 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.

Process Steps

Step 1: Read and Analyze Handoff

  1. Read handoff document completely:

- Use the Read tool WITHOUT limit/offset parameters - Extract all sections: - Task(s) and their statuses - Recent changes - Learnings - Artifacts - Action items and next steps - Other notes

  1. 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
  2. Wait for ALL sub-tasks to complete before proceeding
  3. Read critical files identified:

- Read files from "Learnings" section completely - Read files from "Recent changes" to understand modifications - Read any new related files discovered during research

Step 2: Synthesize and Present Analysis

  1. 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?
  2. Get confirmation before proceeding

Step 3: Create Action Plan

  1. Use TodoWrite to create task list:

- Convert action items from handoff into todos - Add any new tasks discovered during analysis - Prioritize based on dependencies and handoff guidance

  1. 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]?

Step 4: Route to Specialist Agent

CRITICAL: Do NOT implement directly. Always spawn via Task tool.

  1. Analyze task type and select specialist agent: 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 Complex multi-agent workflows 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 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
  2. Spawn the specialist via Task tool: Use Task tool with: - subagent_type: [selected agent from above] - prompt: [task description + relevant handoff context + learnings]
  3. Include handoff context in the prompt:

- Key learnings from the handoff - File references with line numbers - Patterns to follow - Pitfalls to avoid

  1. Wait for agent completion, then proceed to next task

Guidelines

  1. Be Thorough in Analysis:

- Read the entire handoff document first - Verify ALL mentioned changes still exist - Check for any regressions or conflicts - Read all referenced artifacts

  1. Be Interactive:

- Present findings before starting work - Get buy-in on the approach - Allow for course corrections - Adapt based on current state vs handoff state

  1. Leverage Handoff Wisdom:

- Pay special attention to "Learnings" section - Apply documented patterns and approaches - Avoid repeating mistakes mentioned - Build on discovered solutions

  1. Track Continuity:

- Use TodoWrite to maintain task continuity - Reference the handoff document in commits - Document any deviations from original plan - Consider creating a new handoff when done

  1. Validate Before Acting:

- Never assume handoff state matches current state - Verify all file references still exist - Check for breaking changes since handoff - Confirm patterns are still valid

Common Scenarios

Scenario 1: Clean Continuation

  • All changes from handoff are present
  • No conflicts or regressions
  • Clear next steps in action items
  • Proceed with recommended actions

Scenario 2: Diverged Codebase

  • Some changes missing or modified
  • New related code added since handoff
  • Need to reconcile differences
  • Adapt plan based on current state

Scenario 3: Incomplete Handoff Work

  • Tasks marked as "in_progress" in handoff
  • Need to complete unfinished work first
  • May need to re-understand partial implementations
  • Focus on completing before new work

Scenario 4: Stale Handoff

  • Significant time has passed
  • Major refactoring has occurred
  • Original approach may no longer apply
  • Need to re-evaluate strategy

Example Interaction Flow

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...

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

04

需要参考平台分布和安装热度时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Claude Code

29.17%
按下载量换算711

OpenCode

21.51%
按下载量换算525

Gemini CLI

15.89%
按下载量换算388

Codex

12.16%
按下载量换算297

Antigravity

8.21%
按下载量换算200

windsurf

3.2%
按下载量换算78

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

未通过

权限和风险

执行命令

安装流程涉及命令执行,可能通过 npx skills add https://github.com/parcadei/continuous-claude-v3 --skill resume-handoff;npx skills add parcadei/continuous-claude-v3 --skill "resume-handoff" 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。

来源信息

继续浏览同类 Skills