[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6K2VGZH8A1258VK5VV0MP3E":3,"skill-same:01M6K2VGZH8A1258VK5VV0MP3E":109},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":23,"publishedAt":35,"linkOnly":36,"markdownContent":37,"markdownBody":38,"frontMatter":39,"refName":41,"commitSha":42,"skillDirectory":43,"forksCount":44,"repositoryHtmlUrl":45,"repositoryHomepageUrl":46,"ownerHtmlUrl":47,"ownerBlogUrl":46,"ownerDescription":6,"updatedAt":48,"install":49,"resources":62},"01M6K2VGZH8A1258VK5VV0MP3E","install-qwenpaw",null,"在 Alibaba Cloud Linux 4 (Alinux 4) 服务器上完成 QwenPaw AI 助理的安装部署，包括脚本安装、直接写入配置文件、百炼模型 API Key 配置、钉钉频道接入。当用户需要安装 QwenPaw、部署 AI 助理、配置钉钉机器人或百炼模型时使用此技能。","agentic-os-org\u002FANOLISA","agentic-os-org","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F326861446?v=4","01M6K2QGJPXKNJFSPNB3FYW1R3","Agentic OS","01M6K2QGQ6W3S1A9J9DR1G88NZ",665,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fagentic-os-org\u002FANOLISA\u002Fblob\u002Fmain\u002Fsrc\u002Fos-skills\u002Fai\u002Finstall-qwenpaw\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000011","运维与部署","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34],"install","install qwenpaw","qwenpaw","linux","cloud","api","application","文件","usage","alibaba","alinux","2026-11-10 10:12:30",false,"---\nname: install-qwenpaw\nversion: 1.0.0\ndescription: 在 Alibaba Cloud Linux 4 (Alinux 4) 服务器上完成 QwenPaw AI 助理的安装部署，包括脚本安装、直接写入配置文件、百炼模型 API Key 配置、钉钉频道接入。当用户需要安装 QwenPaw、部署 AI 助理、配置钉钉机器人或百炼模型时使用此技能。\nlayer: application\nlifecycle: usage\n---\n\n# QwenPaw Linux 服务器安装部署\n\n## 前置信息收集\n\n开始前**必须**向用户获取以下信息，缺一不可：\n\n1. **百炼 API Key** — 格式以 `sk-` 开头，从 https:\u002F\u002Fbailian.console.aliyun.com\u002F 获取\n2. **钉钉 Client ID** — 即 AppKey，从钉钉开发者后台获取\n3. **钉钉 Client Secret** — 即 AppSecret，从钉钉开发者后台获取\n4. **模型名称**（可选）— 默认 `qwen3-max`，可选 `qwen3-235b-a22b-thinking-2507`、`deepseek-v3.2` 等\n\n---\n\n## 一键部署（推荐）\n\n本 skill 提供了一键部署脚本 `scripts\u002Fsetup.sh`，收集到用户信息后直接执行：\n\n```bash\nbash scripts\u002Fsetup.sh \u003C百炼API_KEY> \u003C钉钉CLIENT_ID> \u003C钉钉CLIENT_SECRET> [模型名称]\n```\n\n示例：\n\n```bash\nbash scripts\u002Fsetup.sh sk-76f003xxx dingxxxxx your_secret\nbash scripts\u002Fsetup.sh sk-76f003xxx dingxxxxx your_secret qwen3-235b-a22b-thinking-2507\n```\n\n脚本会自动完成：检查 uv → 安装 QwenPaw → 创建目录 → 写入配置（替换占位符）→ 验证文件 → 后台启动服务。\n\n执行前需要先将本 skill 目录上传到服务器，或通过工具将 `scripts\u002Fsetup.sh` 和 `reference\u002F` 目录写入服务器。\n\n---\n\n## 手动分步部署\n\n如果脚本不可用，按以下步骤手动操作。\n\n### 步骤 1: 检查并安装 uv\n\nQwenPaw 依赖 `uv` 作为 Python 包管理器。优先通过阿里云镜像安装，失败时用官方脚本兜底：\n\n```bash\nif command -v uv &>\u002Fdev\u002Fnull; then\n  echo \"uv 已安装: $(uv --version)\"\nelse\n  # 方式 1: pip + 阿里云镜像（推荐）\n  pip install uv -i https:\u002F\u002Fmirrors.aliyun.com\u002Fpypi\u002Fsimple\u002F\n  # 方式 2: 官方安装脚本（pip 不可用时）\n  # curl -LsSf https:\u002F\u002Fastral.sh\u002Fuv\u002Finstall.sh | sh\nfi\n```\n\n### 步骤 2: 安装 QwenPaw\n\n```bash\n# 方式 1: 阿里云镜像（推荐）\nuv pip install qwenpaw --index-url https:\u002F\u002Fmirrors.aliyun.com\u002Fpypi\u002Fsimple\u002F\n\n# 方式 2: 官方安装脚本（镜像不可用时）\n# curl -fsSL https:\u002F\u002Fqwenpaw.agentscope.io\u002Finstall.sh | bash\n# source ~\u002F.bashrc\n```\n\n验证：\n\n```bash\nqwenpaw --version\n```\n\n找不到命令时手动加 PATH：\n\n```bash\nexport PATH=\"$HOME\u002F.qwenpaw\u002Fbin:$PATH\"\necho 'export PATH=\"$HOME\u002F.qwenpaw\u002Fbin:$PATH\"' >> ~\u002F.bashrc\nsource ~\u002F.bashrc\n```\n\n### 步骤 3: 创建目录结构\n\n```bash\nmkdir -p ~\u002F.qwenpaw\u002Fmedia\nmkdir -p ~\u002F.qwenpaw\u002Factive_skills\nmkdir -p ~\u002F.qwenpaw\u002Fcustomized_skills\nmkdir -p ~\u002F.qwenpaw.secret\u002Fproviders\u002Fbuiltin\nmkdir -p ~\u002F.qwenpaw.secret\u002Fproviders\u002Fcustom\nchmod 700 ~\u002F.qwenpaw.secret ~\u002F.qwenpaw.secret\u002Fproviders ~\u002F.qwenpaw.secret\u002Fproviders\u002Fbuiltin ~\u002F.qwenpaw.secret\u002Fproviders\u002Fcustom\n```\n\n### 步骤 4: 写入配置文件\n\n读取 `reference\u002F` 下的模板文件，替换占位符后写入目标路径。\n\n#### 3a: config.json（含钉钉频道配置）\n\n读取 `reference\u002Fconfig.json.example`，替换后写入 `~\u002F.qwenpaw\u002Fconfig.json`：\n\n```\n替换:\n  {DINGTALK_CLIENT_ID} → 用户的钉钉 Client ID\n  {DINGTALK_CLIENT_SECRET} → 用户的钉钉 Client Secret\n```\n\n钉钉已预设 `\"enabled\": true`。`qwenpaw app` 启动时会自动迁移生成 `agent.json` 等文件。\n\n#### 3b: dashscope.json\n\n读取 `reference\u002Fdashscope.json`，替换后写入 `~\u002F.qwenpaw.secret\u002Fproviders\u002Fbuiltin\u002Fdashscope.json`：\n\n```\n替换: {DASHSCOPE_API_KEY} → 用户的百炼 API Key\n```\n\n```bash\nchmod 600 ~\u002F.qwenpaw.secret\u002Fproviders\u002Fbuiltin\u002Fdashscope.json\n```\n\n#### 3c: active_model.json\n\n读取 `reference\u002Factive_model.json`，替换后写入 `~\u002F.qwenpaw.secret\u002Fproviders\u002Factive_model.json`：\n\n```\n替换: {MODEL_NAME} → 用户指定的模型（默认 qwen3-max）\n```\n\n```bash\nchmod 600 ~\u002F.qwenpaw.secret\u002Fproviders\u002Factive_model.json\n```\n\n#### 3d: Markdown 文件\n\n原样复制到 `~\u002F.qwenpaw\u002F`（无占位符）：\n\n```\nreference\u002FAGENTS.md    → ~\u002F.qwenpaw\u002FAGENTS.md\nreference\u002FSOUL.md      → ~\u002F.qwenpaw\u002FSOUL.md\nreference\u002FPROFILE.md   → ~\u002F.qwenpaw\u002FPROFILE.md\nreference\u002FMEMORY.md    → ~\u002F.qwenpaw\u002FMEMORY.md\nreference\u002FBOOTSTRAP.md → ~\u002F.qwenpaw\u002FBOOTSTRAP.md\nreference\u002FHEARTBEAT.md → ~\u002F.qwenpaw\u002FHEARTBEAT.md\n```\n\n#### 3e: 验证文件完整性\n\n```bash\nfor f in \\\n  ~\u002F.qwenpaw\u002Fconfig.json \\\n  ~\u002F.qwenpaw.secret\u002Fproviders\u002Fbuiltin\u002Fdashscope.json \\\n  ~\u002F.qwenpaw.secret\u002Fproviders\u002Factive_model.json \\\n  ~\u002F.qwenpaw\u002FAGENTS.md \\\n  ~\u002F.qwenpaw\u002FSOUL.md \\\n  ~\u002F.qwenpaw\u002FPROFILE.md \\\n  ~\u002F.qwenpaw\u002FMEMORY.md \\\n  ~\u002F.qwenpaw\u002FBOOTSTRAP.md \\\n  ~\u002F.qwenpaw\u002FHEARTBEAT.md; do\n  [ -f \"$f\" ] && echo \"OK: $f\" || echo \"MISSING: $f\"\ndone\n```\n\n### 步骤 5: 启动服务\n\n```bash\nnohup qwenpaw app --host 0.0.0.0 --port 8088 > ~\u002F.qwenpaw\u002Fqwenpaw.log 2>&1 &\necho \"QwenPaw PID: $!\"\nsleep 5\n```\n\n> `--host 0.0.0.0` 使外部可访问。仅本机访问用 `127.0.0.1`。\n\n### 步骤 6: 验证部署\n\n```bash\ncurl -s -N -X POST \"http:\u002F\u002Flocalhost:8088\u002Fapi\u002Fagent\u002Fprocess\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"input\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"你好\"}]}],\"session_id\":\"test123\"}' \\\n  | head -c 500\n```\n\n返回 SSE 流式数据（`data:` 开头）表示服务正常。\n\n```bash\nqwenpaw channels list\n```\n\n确认 dingtalk 显示 `enabled: True`。\n\n---\n\n## 故障排查\n\n### qwenpaw 命令找不到\n\n```bash\nexport PATH=\"$HOME\u002F.qwenpaw\u002Fbin:$PATH\"\nsource ~\u002F.bashrc\n```\n\n### 模型返回错误\n\n```bash\ncat ~\u002F.qwenpaw.secret\u002Fproviders\u002Fbuiltin\u002Fdashscope.json | python3 -m json.tool\ncat ~\u002F.qwenpaw.secret\u002Fproviders\u002Factive_model.json | python3 -m json.tool\n```\n\n确认 `api_key` 以 `sk-` 开头，`model` 字段有值。\n\n### 钉钉机器人不回复\n\n```bash\npython3 -c \"\nimport json\nwith open('$HOME\u002F.qwenpaw\u002Fconfig.json') as f:\n    c = json.load(f)\nprint(json.dumps(c.get('channels',{}).get('dingtalk',{}), indent=2, ensure_ascii=False))\n\"\ntail -100 ~\u002F.qwenpaw\u002Fqwenpaw.log | grep -i dingtalk\n```\n\n钉钉侧检查：应用已发布、Stream 模式已启用、Client ID\u002FSecret 正确。\n\n### 端口占用\n\n```bash\nlsof -i :8088\nnohup qwenpaw app --host 0.0.0.0 --port 9090 > ~\u002F.qwenpaw\u002Fqwenpaw.log 2>&1 &\n```\n\n### 停止服务\n\n```bash\nkill $(pgrep -f \"qwenpaw app\")\n```\n\n---\n\n## 钉钉应用创建指引（提供给用户）\n\n如果用户还没有钉钉应用凭证，告知以下步骤：\n\n1. 打开 https:\u002F\u002Fopen-dev.dingtalk.com\u002F\n2. 进入「应用开发 → 企业内部应用 → 钉钉应用 → 创建应用」\n3. 在「应用能力 → 添加应用能力」中添加「机器人」\n4. 配置机器人：消息接收模式选择 **Stream 模式**，点击「发布」\n5. 在「应用发布 → 版本管理与发布」中创建新版本并保存\n6. 在「基础信息 → 凭证与基础信息」中复制 **Client ID** 和 **Client Secret**\n7. （可选）在「安全设置 → 服务器出口 IP」添加服务器公网 IP（`curl ifconfig.me` 获取），支持图片\u002F文件下载\n\n## 文件清单\n\n```\ninstall-qwenpaw\u002F\n├── SKILL.md\n├── scripts\u002F\n│   └── setup.sh                 # 一键部署脚本\n└── reference\u002F\n    ├── config.json.example      → ~\u002F.qwenpaw\u002Fconfig.json\n    ├── dashscope.json           → ~\u002F.qwenpaw.secret\u002Fproviders\u002Fbuiltin\u002Fdashscope.json\n    ├── active_model.json        → ~\u002F.qwenpaw.secret\u002Fproviders\u002Factive_model.json\n    ├── AGENTS.md                → ~\u002F.qwenpaw\u002FAGENTS.md\n    ├── SOUL.md                  → ~\u002F.qwenpaw\u002FSOUL.md\n    ├── PROFILE.md               → ~\u002F.qwenpaw\u002FPROFILE.md\n    ├── MEMORY.md                → ~\u002F.qwenpaw\u002FMEMORY.md\n    ├── BOOTSTRAP.md             → ~\u002F.qwenpaw\u002FBOOTSTRAP.md\n    └── HEARTBEAT.md             → ~\u002F.qwenpaw\u002FHEARTBEAT.md\n```\n","# QwenPaw Linux 服务器安装部署\n\n## 前置信息收集\n\n开始前**必须**向用户获取以下信息，缺一不可：\n\n1. **百炼 API Key** — 格式以 `sk-` 开头，从 https:\u002F\u002Fbailian.console.aliyun.com\u002F 获取\n2. **钉钉 Client ID** — 即 AppKey，从钉钉开发者后台获取\n3. **钉钉 Client Secret** — 即 AppSecret，从钉钉开发者后台获取\n4. **模型名称**（可选）— 默认 `qwen3-max`，可选 `qwen3-235b-a22b-thinking-2507`、`deepseek-v3.2` 等\n\n---\n\n## 一键部署（推荐）\n\n本 skill 提供了一键部署脚本 `scripts\u002Fsetup.sh`，收集到用户信息后直接执行：\n\n```bash\nbash scripts\u002Fsetup.sh \u003C百炼API_KEY> \u003C钉钉CLIENT_ID> \u003C钉钉CLIENT_SECRET> [模型名称]\n```\n\n示例：\n\n```bash\nbash scripts\u002Fsetup.sh sk-76f003xxx dingxxxxx your_secret\nbash scripts\u002Fsetup.sh sk-76f003xxx dingxxxxx your_secret qwen3-235b-a22b-thinking-2507\n```\n\n脚本会自动完成：检查 uv → 安装 QwenPaw → 创建目录 → 写入配置（替换占位符）→ 验证文件 → 后台启动服务。\n\n执行前需要先将本 skill 目录上传到服务器，或通过工具将 `scripts\u002Fsetup.sh` 和 `reference\u002F` 目录写入服务器。\n\n---\n\n## 手动分步部署\n\n如果脚本不可用，按以下步骤手动操作。\n\n### 步骤 1: 检查并安装 uv\n\nQwenPaw 依赖 `uv` 作为 Python 包管理器。优先通过阿里云镜像安装，失败时用官方脚本兜底：\n\n```bash\nif command -v uv &>\u002Fdev\u002Fnull; then\n  echo \"uv 已安装: $(uv --version)\"\nelse\n  # 方式 1: pip + 阿里云镜像（推荐）\n  pip install uv -i https:\u002F\u002Fmirrors.aliyun.com\u002Fpypi\u002Fsimple\u002F\n  # 方式 2: 官方安装脚本（pip 不可用时）\n  # curl -LsSf https:\u002F\u002Fastral.sh\u002Fuv\u002Finstall.sh | sh\nfi\n```\n\n### 步骤 2: 安装 QwenPaw\n\n```bash\n# 方式 1: 阿里云镜像（推荐）\nuv pip install qwenpaw --index-url https:\u002F\u002Fmirrors.aliyun.com\u002Fpypi\u002Fsimple\u002F\n\n# 方式 2: 官方安装脚本（镜像不可用时）\n# curl -fsSL https:\u002F\u002Fqwenpaw.agentscope.io\u002Finstall.sh | bash\n# source ~\u002F.bashrc\n```\n\n验证：\n\n```bash\nqwenpaw --version\n```\n\n找不到命令时手动加 PATH：\n\n```bash\nexport PATH=\"$HOME\u002F.qwenpaw\u002Fbin:$PATH\"\necho 'export PATH=\"$HOME\u002F.qwenpaw\u002Fbin:$PATH\"' >> ~\u002F.bashrc\nsource ~\u002F.bashrc\n```\n\n### 步骤 3: 创建目录结构\n\n```bash\nmkdir -p ~\u002F.qwenpaw\u002Fmedia\nmkdir -p ~\u002F.qwenpaw\u002Factive_skills\nmkdir -p ~\u002F.qwenpaw\u002Fcustomized_skills\nmkdir -p ~\u002F.qwenpaw.secret\u002Fproviders\u002Fbuiltin\nmkdir -p ~\u002F.qwenpaw.secret\u002Fproviders\u002Fcustom\nchmod 700 ~\u002F.qwenpaw.secret ~\u002F.qwenpaw.secret\u002Fproviders ~\u002F.qwenpaw.secret\u002Fproviders\u002Fbuiltin ~\u002F.qwenpaw.secret\u002Fproviders\u002Fcustom\n```\n\n### 步骤 4: 写入配置文件\n\n读取 `reference\u002F` 下的模板文件，替换占位符后写入目标路径。\n\n#### 3a: config.json（含钉钉频道配置）\n\n读取 `reference\u002Fconfig.json.example`，替换后写入 `~\u002F.qwenpaw\u002Fconfig.json`：\n\n```\n替换:\n  {DINGTALK_CLIENT_ID} → 用户的钉钉 Client ID\n  {DINGTALK_CLIENT_SECRET} → 用户的钉钉 Client Secret\n```\n\n钉钉已预设 `\"enabled\": true`。`qwenpaw app` 启动时会自动迁移生成 `agent.json` 等文件。\n\n#### 3b: dashscope.json\n\n读取 `reference\u002Fdashscope.json`，替换后写入 `~\u002F.qwenpaw.secret\u002Fproviders\u002Fbuiltin\u002Fdashscope.json`：\n\n```\n替换: {DASHSCOPE_API_KEY} → 用户的百炼 API Key\n```\n\n```bash\nchmod 600 ~\u002F.qwenpaw.secret\u002Fproviders\u002Fbuiltin\u002Fdashscope.json\n```\n\n#### 3c: active_model.json\n\n读取 `reference\u002Factive_model.json`，替换后写入 `~\u002F.qwenpaw.secret\u002Fproviders\u002Factive_model.json`：\n\n```\n替换: {MODEL_NAME} → 用户指定的模型（默认 qwen3-max）\n```\n\n```bash\nchmod 600 ~\u002F.qwenpaw.secret\u002Fproviders\u002Factive_model.json\n```\n\n#### 3d: Markdown 文件\n\n原样复制到 `~\u002F.qwenpaw\u002F`（无占位符）：\n\n```\nreference\u002FAGENTS.md    → ~\u002F.qwenpaw\u002FAGENTS.md\nreference\u002FSOUL.md      → ~\u002F.qwenpaw\u002FSOUL.md\nreference\u002FPROFILE.md   → ~\u002F.qwenpaw\u002FPROFILE.md\nreference\u002FMEMORY.md    → ~\u002F.qwenpaw\u002FMEMORY.md\nreference\u002FBOOTSTRAP.md → ~\u002F.qwenpaw\u002FBOOTSTRAP.md\nreference\u002FHEARTBEAT.md → ~\u002F.qwenpaw\u002FHEARTBEAT.md\n```\n\n#### 3e: 验证文件完整性\n\n```bash\nfor f in \\\n  ~\u002F.qwenpaw\u002Fconfig.json \\\n  ~\u002F.qwenpaw.secret\u002Fproviders\u002Fbuiltin\u002Fdashscope.json \\\n  ~\u002F.qwenpaw.secret\u002Fproviders\u002Factive_model.json \\\n  ~\u002F.qwenpaw\u002FAGENTS.md \\\n  ~\u002F.qwenpaw\u002FSOUL.md \\\n  ~\u002F.qwenpaw\u002FPROFILE.md \\\n  ~\u002F.qwenpaw\u002FMEMORY.md \\\n  ~\u002F.qwenpaw\u002FBOOTSTRAP.md \\\n  ~\u002F.qwenpaw\u002FHEARTBEAT.md; do\n  [ -f \"$f\" ] && echo \"OK: $f\" || echo \"MISSING: $f\"\ndone\n```\n\n### 步骤 5: 启动服务\n\n```bash\nnohup qwenpaw app --host 0.0.0.0 --port 8088 > ~\u002F.qwenpaw\u002Fqwenpaw.log 2>&1 &\necho \"QwenPaw PID: $!\"\nsleep 5\n```\n\n> `--host 0.0.0.0` 使外部可访问。仅本机访问用 `127.0.0.1`。\n\n### 步骤 6: 验证部署\n\n```bash\ncurl -s -N -X POST \"http:\u002F\u002Flocalhost:8088\u002Fapi\u002Fagent\u002Fprocess\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d '{\"input\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"你好\"}]}],\"session_id\":\"test123\"}' \\\n  | head -c 500\n```\n\n返回 SSE 流式数据（`data:` 开头）表示服务正常。\n\n```bash\nqwenpaw channels list\n```\n\n确认 dingtalk 显示 `enabled: True`。\n\n---\n\n## 故障排查\n\n### qwenpaw 命令找不到\n\n```bash\nexport PATH=\"$HOME\u002F.qwenpaw\u002Fbin:$PATH\"\nsource ~\u002F.bashrc\n```\n\n### 模型返回错误\n\n```bash\ncat ~\u002F.qwenpaw.secret\u002Fproviders\u002Fbuiltin\u002Fdashscope.json | python3 -m json.tool\ncat ~\u002F.qwenpaw.secret\u002Fproviders\u002Factive_model.json | python3 -m json.tool\n```\n\n确认 `api_key` 以 `sk-` 开头，`model` 字段有值。\n\n### 钉钉机器人不回复\n\n```bash\npython3 -c \"\nimport json\nwith open('$HOME\u002F.qwenpaw\u002Fconfig.json') as f:\n    c = json.load(f)\nprint(json.dumps(c.get('channels',{}).get('dingtalk',{}), indent=2, ensure_ascii=False))\n\"\ntail -100 ~\u002F.qwenpaw\u002Fqwenpaw.log | grep -i dingtalk\n```\n\n钉钉侧检查：应用已发布、Stream 模式已启用、Client ID\u002FSecret 正确。\n\n### 端口占用\n\n```bash\nlsof -i :8088\nnohup qwenpaw app --host 0.0.0.0 --port 9090 > ~\u002F.qwenpaw\u002Fqwenpaw.log 2>&1 &\n```\n\n### 停止服务\n\n```bash\nkill $(pgrep -f \"qwenpaw app\")\n```\n\n---\n\n## 钉钉应用创建指引（提供给用户）\n\n如果用户还没有钉钉应用凭证，告知以下步骤：\n\n1. 打开 https:\u002F\u002Fopen-dev.dingtalk.com\u002F\n2. 进入「应用开发 → 企业内部应用 → 钉钉应用 → 创建应用」\n3. 在「应用能力 → 添加应用能力」中添加「机器人」\n4. 配置机器人：消息接收模式选择 **Stream 模式**，点击「发布」\n5. 在「应用发布 → 版本管理与发布」中创建新版本并保存\n6. 在「基础信息 → 凭证与基础信息」中复制 **Client ID** 和 **Client Secret**\n7. （可选）在「安全设置 → 服务器出口 IP」添加服务器公网 IP（`curl ifconfig.me` 获取），支持图片\u002F文件下载\n\n## 文件清单\n\n```\ninstall-qwenpaw\u002F\n├── SKILL.md\n├── scripts\u002F\n│   └── setup.sh                 # 一键部署脚本\n└── reference\u002F\n    ├── config.json.example      → ~\u002F.qwenpaw\u002Fconfig.json\n    ├── dashscope.json           → ~\u002F.qwenpaw.secret\u002Fproviders\u002Fbuiltin\u002Fdashscope.json\n    ├── active_model.json        → ~\u002F.qwenpaw.secret\u002Fproviders\u002Factive_model.json\n    ├── AGENTS.md                → ~\u002F.qwenpaw\u002FAGENTS.md\n    ├── SOUL.md                  → ~\u002F.qwenpaw\u002FSOUL.md\n    ├── PROFILE.md               → ~\u002F.qwenpaw\u002FPROFILE.md\n    ├── MEMORY.md                → ~\u002F.qwenpaw\u002FMEMORY.md\n    ├── BOOTSTRAP.md             → ~\u002F.qwenpaw\u002FBOOTSTRAP.md\n    └── HEARTBEAT.md             → ~\u002F.qwenpaw\u002FHEARTBEAT.md\n```\n",{"name":5,"layer":30,"version":40,"lifecycle":32,"description":7},"1.0.0","main","d2c8a75e03a304c97d2b049d59f85c2ef0b08519","src\u002Fos-skills\u002Fai\u002Finstall-qwenpaw",195,"https:\u002F\u002Fgithub.com\u002Fagentic-os-org\u002FANOLISA","https:\u002F\u002Fagentic-os.sh\u002F","https:\u002F\u002Fgithub.com\u002Fagentic-os-org","2026-11-14 23:49:17",{"source":8,"skillName":5,"commands":50,"prompt":60,"zipAvailable":61},[51,54,57],{"tool":52,"command":53},"npx","npx skills add agentic-os-org\u002FANOLISA --skill install-qwenpaw",{"tool":55,"command":56},"bunx","bunx skills add agentic-os-org\u002FANOLISA --skill install-qwenpaw",{"tool":58,"command":59},"pnpm","pnpm dlx skills add agentic-os-org\u002FANOLISA --skill install-qwenpaw","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fagentic-os-org\u002FANOLISA\u002Fblob\u002Fmain\u002Fsrc\u002Fos-skills\u002Fai\u002Finstall-qwenpaw\u002FSKILL.md",true,[63,69,73,77,83,87,91,95,99,103],{"path":64,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":67,"sourceHtmlUrl":68},"reference\u002Factive_model.json","REFERENCE","参考文档",60,"https:\u002F\u002Fgithub.com\u002Fagentic-os-org\u002FANOLISA\u002Fblob\u002Fmain\u002Fsrc\u002Fos-skills\u002Fai\u002Finstall-qwenpaw\u002Freference\u002Factive_model.json",{"path":70,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":71,"sourceHtmlUrl":72},"reference\u002FAGENTS.md",5580,"https:\u002F\u002Fgithub.com\u002Fagentic-os-org\u002FANOLISA\u002Fblob\u002Fmain\u002Fsrc\u002Fos-skills\u002Fai\u002Finstall-qwenpaw\u002Freference\u002FAGENTS.md",{"path":74,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":75,"sourceHtmlUrl":76},"reference\u002FBOOTSTRAP.md",1363,"https:\u002F\u002Fgithub.com\u002Fagentic-os-org\u002FANOLISA\u002Fblob\u002Fmain\u002Fsrc\u002Fos-skills\u002Fai\u002Finstall-qwenpaw\u002Freference\u002FBOOTSTRAP.md",{"path":78,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":81,"sourceHtmlUrl":82},"reference\u002Fconfig.json.example","OTHER","其他",7409,"https:\u002F\u002Fgithub.com\u002Fagentic-os-org\u002FANOLISA\u002Fblob\u002Fmain\u002Fsrc\u002Fos-skills\u002Fai\u002Finstall-qwenpaw\u002Freference\u002Fconfig.json.example",{"path":84,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":85,"sourceHtmlUrl":86},"reference\u002Fdashscope.json",639,"https:\u002F\u002Fgithub.com\u002Fagentic-os-org\u002FANOLISA\u002Fblob\u002Fmain\u002Fsrc\u002Fos-skills\u002Fai\u002Finstall-qwenpaw\u002Freference\u002Fdashscope.json",{"path":88,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":89,"sourceHtmlUrl":90},"reference\u002FHEARTBEAT.md",242,"https:\u002F\u002Fgithub.com\u002Fagentic-os-org\u002FANOLISA\u002Fblob\u002Fmain\u002Fsrc\u002Fos-skills\u002Fai\u002Finstall-qwenpaw\u002Freference\u002FHEARTBEAT.md",{"path":92,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":93,"sourceHtmlUrl":94},"reference\u002FMEMORY.md",474,"https:\u002F\u002Fgithub.com\u002Fagentic-os-org\u002FANOLISA\u002Fblob\u002Fmain\u002Fsrc\u002Fos-skills\u002Fai\u002Finstall-qwenpaw\u002Freference\u002FMEMORY.md",{"path":96,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":97,"sourceHtmlUrl":98},"reference\u002FPROFILE.md",661,"https:\u002F\u002Fgithub.com\u002Fagentic-os-org\u002FANOLISA\u002Fblob\u002Fmain\u002Fsrc\u002Fos-skills\u002Fai\u002Finstall-qwenpaw\u002Freference\u002FPROFILE.md",{"path":100,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":101,"sourceHtmlUrl":102},"reference\u002FSOUL.md",1598,"https:\u002F\u002Fgithub.com\u002Fagentic-os-org\u002FANOLISA\u002Fblob\u002Fmain\u002Fsrc\u002Fos-skills\u002Fai\u002Finstall-qwenpaw\u002Freference\u002FSOUL.md",{"path":104,"resourceType":105,"resourceTypeDesc":106,"sizeBytes":107,"sourceHtmlUrl":108},"scripts\u002Fsetup.sh","SCRIPT","脚本",7880,"https:\u002F\u002Fgithub.com\u002Fagentic-os-org\u002FANOLISA\u002Fblob\u002Fmain\u002Fsrc\u002Fos-skills\u002Fai\u002Finstall-qwenpaw\u002Fscripts\u002Fsetup.sh",[110,123,154,171,187,200],{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":116,"publishedAt":35},"01M6K30MJVPNFF4VA778AZC512","ws-ckpt","Linux 工作区快照(ws-ckpt)。用户想保存或备份工作区当前状态(\"保存一下\"、\"留个底\"、\"先备份\"), 想撤销或恢复文件改动(\"回滚\"、\"撤销\"、\"改回去\"、\"恢复到之前\"、\"刚才那版\"), 想查看、对比或删除历史版本,或要开启\u002F关闭每回合自动快照、定时快照、快照保留策略时使用。 用户没提\"快照\"、只表达保存或恢复工作区文件的意图时同样适用;用户点名 git 操作(commit、branch、reset 到某提交)时不适用。","https:\u002F\u002Fgithub.com\u002Fagentic-os-org\u002FANOLISA\u002Fblob\u002Fmain\u002Fsrc\u002Fws-ckpt\u002Fsrc\u002Fskills\u002Fws-ckpt\u002FSKILL.md",[],[117,27,118,119,120,121,122,31],"ws ckpt","commit","git","branch","reset","定时",{"skillNo":124,"name":125,"nameZh":6,"description":126,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":127,"categories":128,"keywords":132,"publishedAt":35},"01M6K30G7BBZB1VCPE3NE08KZP","skillfs-mount","Help users configure, mount, and unmount a skillfs FUSE virtual filesystem on their local machine (e.g. for openclaw). Covers analyzing existing skill usage to suggest view configuration, generating skillfs-views.toml, mounting, and graceful unmount. Use this skill when the user asks to: set up skillfs, configure skill views, mount or unmount skillfs, check if skillfs is running, or get help organizing their skills directory (especially for openclaw users).","https:\u002F\u002Fgithub.com\u002Fagentic-os-org\u002FANOLISA\u002Fblob\u002Fmain\u002Fsrc\u002Fskillfs\u002Fdocs\u002Fskills\u002Fskillfs-mount\u002FSKILL.md",[129],{"categoryNo":130,"categoryName":131,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,32,150,151,152,153],"skillfs mount","mount","virtual","get","local","existing skill","up","use","view","filesystem","toml","configure","skill usage","SET","analyzing","openclaw","machine","for","when","running","directory",{"skillNo":155,"name":156,"nameZh":6,"description":157,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":158,"categories":159,"keywords":164,"publishedAt":35},"01M6K30CJW0X3V5PG4GP26TB63","test-skill","A test skill used in integration tests.","https:\u002F\u002Fgithub.com\u002Fagentic-os-org\u002FANOLISA\u002Fblob\u002Fmain\u002Fsrc\u002Fskillfs\u002Fcrates\u002Fskillfs-fuse\u002Ftests\u002Ffixtures\u002Ftest-skill\u002FSKILL.md",[160,163],{"categoryNo":161,"categoryName":162,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":130,"categoryName":131,"taxonomyType":21,"taxonomyTypeDesc":22},[165,166,167,168,169,170],"test","Test Skill","true","integration tests","integration","tests",{"skillNo":172,"name":173,"nameZh":6,"description":174,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":175,"categories":176,"keywords":177,"publishedAt":35},"01M6K304VCM7N6AR4PMYNDP3A7","storage-resize","Linux 磁盘扩容技能（RPM 包管理系统），实现云盘扩容后自动完成分区调整和文件系统扩容。支持系统盘\u002F数据盘在线扩容，适配 XFS\u002FEXT4\u002FBtrfs 文件系统。适用于 RPM 包管理的 Linux 系统（如 Alibaba Cloud Linux）。","https:\u002F\u002Fgithub.com\u002Fagentic-os-org\u002FANOLISA\u002Fblob\u002Fmain\u002Fsrc\u002Fos-skills\u002Fsystem-admin\u002Fstorage-resize\u002FSKILL.md",[],[178,179,180,27,28,181,182,183,184,31,185,33,186],"storage resize","storage","system","operations","btrfs","ecs","aliyun","rpm","数据",{"skillNo":188,"name":189,"nameZh":6,"description":190,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":191,"categories":192,"keywords":193,"publishedAt":35},"01M6K2ZJEGANYH9TGGG25H7WVF","ktuner","内核参数自动调优。分析系统配置，输出调优建议并可一键应用，支持自动回滚。使用场景：系统性能优化、安全加固、内核参数诊断。","https:\u002F\u002Fgithub.com\u002Fagentic-os-org\u002FANOLISA\u002Fblob\u002Fmain\u002Fsrc\u002Fos-skills\u002Fsystem-admin\u002Fktuner\u002FSKILL.md",[],[189,194,195,196,197,198,199],"core","run","Production","shell","安全","command",{"skillNo":201,"name":202,"nameZh":6,"description":203,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":204,"categories":205,"keywords":206,"publishedAt":35},"01M6K2ZD5K40XCX8R1EA85MS7P","backup-restore","处理所有备份与恢复任务，覆盖四个层面：工作区（项目\u002F数据库\u002F代码）、用户数据（家目录\u002Fdotfiles\u002F密钥）、操作系统（全量系统\u002F磁盘镜像\u002FLVM 快照）、阿里云快照（云盘快照\u002F自动策略\u002F跨地域复制\u002F整机镜像）。适用于 RPM 包管理的 Linux 系统（如 Alibaba Cloud Linux）纯命令行环境，使用 yum 包管理器。当用户提到备份、恢复、快照、归档、回滚、克隆、迁移、容灾等任何涉及数据保存或恢复的请求时触发此技能，即使请求看起来很简单也应使用。","https:\u002F\u002Fgithub.com\u002Fagentic-os-org\u002FANOLISA\u002Fblob\u002Fmain\u002Fsrc\u002Fos-skills\u002Fsystem-admin\u002Fbackup-restore\u002FSKILL.md",[],[207,208,209,28,210,211,212,185,33,213,186,214,215,27,184],"backup restore","backup","restore","beta","release","lvm","runtime","maintenance","dotfiles"]