switch-chat
Skill38 starsChanged 10 days agoMITView on GitHub
当用户需要切换会话并交接任务时使用,生成可视化交接文档,确保新会话能无缝继承工作目标
- Reads credentials
In this repository32 other files it gives its agents.
- bad-solutionSkill
- blog-narratorSkill
- clakSkill
- esflowSkill
- fetch-what-saySkill
- git-reviewSkill
- holiday-of-12306Skill
- html-cutSkill
- juyaSkill
- lan-chatSkill
- md-to-pngSkill
- meet-digestSkill
- meet-record-htmlSkill
- memory-cardSkill
- memory-graphSkill
- mindmapSkill
- mock-ollamaSkill
- okr-to-htmlSkill
- port-to-publicSkill
- similar-judgeSkill
- skill-linkerSkill
- skill-publish-verifySkill
- speak-7dSkill
- summary-user-saidSkill
- task-pollingSkill
- testcaseSkill
- tmux-servSkill
- vite-plusSkill
- voice-cloneSkill
- voice-to-meSkill
- weather-searchSkill
- webfetch-plusSkill
The file
Files
Switch Chat
任务交接 Skill,直接传文本生成可编辑的可视化 HTML。
生成交接文档
Agent 用法(heredoc 直接传文本)
python3 {skill}/scripts/gen.py --open << 'EOF'
# 任务交接:用户中心重构
## 工作目标
用户中心模块正在从 REST API 迁移到 GraphQL。
## 当前进度
- [x] 完成 Schema 设计
- [ ] 实现 resolver
## 注意事项
测试库用 .env.test。
EOF从已有文件填充
python3 {skill}/scripts/gen.py --from handoff.md --open页面操作
打开后直接在浏览器中编辑:点击任意文本输入、添加/删除行、切换完成状态。
- 点击「回写」:把当前页面内容写回
{skill}/assets/continue.html,并复制/switch-chat 继续到剪贴板 - 点击「复制」:复制当前交接 Markdown 到剪贴板
- 点击「导出文件」:下载
switch-chat.md
--open 会启动本地回写服务,5 分钟无回写会自动退出。
新会话读取
当用户输入 /switch-chat 继续 时,必须执行:
python3 {skill}/scripts/read.py执行后按输出的结构化交接文本继续工作:
- 先确认是否包含「工作目标」「当前进度」「注意事项」
- 如果读取失败,明确提示
{skill}/assets/continue.html不存在或未回写
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

