skills/SKILL.md
Web-based tmux 终端客户端,支持 iPhone/iPad/桌面,带 AI 命令生成和语音输入
npx skillsauth add includewudi/opencode-tmuxweb opencode-tmuxwebInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
测试
TmuxWeb 是一个 Web 端的 tmux 终端客户端,核心场景是从 iPhone/iPad 远程管理 macOS 上的 tmux 会话。支持 AI 命令生成(DeepSeek/OpenAI)和讯飞语音输入。
opencode-tmuxweb/
├── TmuxWeb/ # 主项目(Node.js + React)
│ ├── server/ # Express 后端
│ │ ├── index.js # 入口:HTTP/S + WebSocket
│ │ ├── routes/ # API 路由(18个文件)
│ │ ├── services/ # 核心服务
│ │ │ ├── terminal.js # PTY 连接管理
│ │ │ └── speech.js # 讯飞 STT 代理
│ │ └── db/ # MySQL 连接池 + schema
│ ├── web/ # React 前端
│ │ └── src/
│ │ ├── desktop/ # 桌面版 UI
│ │ ├── mobile/ # 移动版 UI(/m 路由)
│ │ └── components/ # 共享组件
│ └── ecosystem.config.js # PM2 配置
├── TmuxMobile/ # React Native 移动端(实验性)
├── VoiceTmuxCore/ # Swift 原生 iOS(实验性)
└── docs/ # 文档
| 能力 | 说明 | 详见 |
|------|------|------|
| 终端连接 | WebSocket + node-pty 连接 tmux pane | architecture.md |
| AI 命令生成 | 7 种内置角色 + 自定义角色 | api.md |
| 语音输入 | 讯飞 STT WebSocket 代理 | architecture.md |
| 任务追踪 | AI 会话 → MySQL 任务记录 | api.md |
| 双端 UI | 桌面 / + 移动 /m | development.md |
| 文件 | 内容 | |------|------| | architecture.md | 核心架构、WebSocket 数据流、PTY 管理 | | api.md | REST API 端点、WebSocket 协议 | | development.md | 开发环境、构建、部署 | | data-model.md | 数据库 Schema、ER 关系、常用查询 | | troubleshooting.md | 故障排查、已知问题解决方案 | | tmux-restart | 重启所有 tmux session(自动跳过 opencode) |
cd TmuxWeb
npm run install:all # 安装前后端依赖
npm run build # 构建前端
cp server/config.json server/private_config.json # 创建私有配置
node server/index.js # 启动服务
访问 https://<ip>:8215(HTTPS 需要 mkcert 证书)。
private_config.json 中的 tokenserver/db/init.sqldevelopment
Maintainer-only workflow for handling GitHub Secret Scanning alerts on OpenClaw. Use when Codex needs to triage, redact, clean up, and resolve secret leakage found in issue comments, issue bodies, PR comments, or other GitHub content.
development
Maintainer workflow for OpenClaw releases, prereleases, changelog release notes, and publish validation. Use when Codex needs to prepare or verify stable or beta release steps, align version naming, assemble release notes, check release auth requirements, or validate publish-time commands and artifacts.
development
Run, watch, debug, and extend OpenClaw QA testing with qa-lab and qa-channel. Use when Codex needs to execute the repo-backed QA suite, inspect live QA artifacts, debug failing scenarios, add new QA scenarios, or explain the OpenClaw QA workflow. Prefer the live OpenAI lane with regular openai/gpt-5.4 in fast mode; do not use gpt-5.4-pro or gpt-5.4-mini unless the user explicitly overrides that policy.
development
End-to-end Parallels smoke, upgrade, and rerun workflow for OpenClaw across macOS, Windows, and Linux guests. Use when Codex needs to run, rerun, debug, or interpret VM-based install, onboarding, gateway smoke tests, latest-release-to-main upgrade checks, fresh snapshot retests, or optional Discord roundtrip verification under Parallels.