AgentStack
SKILL verified MIT Self-run

Claude Handoff

skill-wenwuzhidao-mattpocock-skills-zh-claude-handoff · by WenWuZhiDao

把当前对话交接给一个全新的后台智能体,让它立即接手工作。

No reviews yet
0 installs
12 views
0.0% view→install

Install

$ agentstack add skill-wenwuzhidao-mattpocock-skills-zh-claude-handoff

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Claude Handoff? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

编写一份当前对话的交接摘要,让一个全新的智能体能够接手继续工作。不要保存它,而是启动一个后台智能体,用该摘要作为它的提示作为种子:claude --bg --name "" ""。它在当前工作目录中启动并立即返回;用户通过 claude agents 来管理它。

始终传入 -n/--name 并给一个描述性的名字(例如 --name "Fix login bug")—— 它设定在任务列表、会话选择器和终端标题中显示的名称。

在摘要中加入一个"建议技能"章节,列出该智能体应当调用的技能。

不要重复其他产物(PRD、方案、ADR、issue、提交、diff)中已经记录的内容。改为通过路径或 URL 引用它们。

对任何敏感信息(例如 API 密钥、密码或个人可识别信息)进行脱敏处理 —— 这份摘要会成为该智能体的提示。

如果用户传入了参数,将其视为对下一次会话所要聚焦内容的描述,并据此调整摘要。

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.