---
id: gh-claude-handoff
name: "claude-handoff"
url: https://skills.yangsir.net/skill/gh-claude-handoff
author: mattpocock
domain: ai-dev-tools-workflow
tags: ["handoff", "background-agent", "conversation-summary", "claude", "workflow-automation"]
install_count: 415900
rating: 4.90 (120 reviews)
github: https://github.com/mattpocock/skills/tree/main/skills/in-progress/claude-handoff
---

# claude-handoff

> 此技能能将当前对话总结并立即启动一个后台AI代理继续工作，无需手动保存或重新粘贴上下文。适用于长时间任务、调试或分析场景，提升开发者工作流自动化程度。

**Stats**: 415,900 installs · 4.9/5 (120 reviews)

## Before / After 对比

### 对话交接效率

**Before**:

用户需要手动复制对话总结、新建会话、粘贴上下文并重新设置指令，平均耗时15分钟，且容易遗漏信息。

**After**:

此技能一键生成总结并启动后台代理，整个过程约1分钟，信息完整且无需人工干预。

| Metric | Before | After | Change |
|---|---|---|---|
| 交接时间 | 15分钟 | 1分钟 | -93% |

## Readme

Write a handoff summary of the current conversation so a fresh agent can continue the work. Instead of saving it, launch a background agent seeded with the summary as its prompt: `claude --bg --name "<descriptive name>" "<handoff summary>"`. It starts in the current working directory and returns immediately; the user manages it with `claude agents`.

Always pass `-n`/`--name` with a descriptive name (e.g. `--name "Fix login bug"`) — it sets the display name shown in the job list, session picker, and terminal title.

Include a "suggested skills" section in the summary, which suggests skills that the agent should invoke.

Do not duplicate content already captured in other artifacts (PRDs, plans, ADRs, issues, commits, diffs). Reference them by path or URL instead.

Redact any sensitive information, such as API keys, passwords, or personally identifiable information — the summary becomes the agent's prompt.

If the user passed arguments, treat them as a description of what the next session will focus on and tailor the summary accordingly.


---
*Source: https://skills.yangsir.net/skill/gh-claude-handoff*
*Markdown mirror: https://skills.yangsir.net/api/skill/gh-claude-handoff/markdown*