{
  "schemaVersion": "1.0",
  "item": {
    "slug": "video-pipeline-bundle",
    "name": "Video Pipeline Bundle",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/Leochens/video-pipeline-bundle",
    "canonicalUrl": "https://clawhub.ai/Leochens/video-pipeline-bundle",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/video-pipeline-bundle",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=video-pipeline-bundle",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "scripts/burn_subtitle.py",
      "scripts/ffmpeg_tools.py",
      "scripts/pipeline.py",
      "scripts/video_clip.py",
      "scripts/video_to_text.py"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-30T16:55:25.780Z",
      "expiresAt": "2026-05-07T16:55:25.780Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
        "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/video-pipeline-bundle"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/video-pipeline-bundle",
    "agentPageUrl": "https://openagent3.xyz/skills/video-pipeline-bundle/agent",
    "manifestUrl": "https://openagent3.xyz/skills/video-pipeline-bundle/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/video-pipeline-bundle/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Video Pipeline Bundle",
        "body": "视频一站式工作流技能包，整合剪辑、转写、烧录、拼接全流程。"
      },
      {
        "title": "文件结构",
        "body": "video-pipeline-bundle/\n├── SKILL.md\n└── scripts/\n    ├── pipeline.py      # 工作流编排\n    ├── video_clip.py    # 视频剪辑（去静音）\n    ├── video_to_text.py # 语音转字幕\n    ├── burn_subtitle.py # 烧录字幕\n    └── ffmpeg_tools.py  # FFmpeg 工具箱"
      },
      {
        "title": "依赖",
        "body": "ffmpeg + ffprobe\nPython 3.8+\nauto-editor（视频剪辑）\nfaster-whisper + requests（语音转写）\nMiniMax API Key（LLM 纠错）"
      },
      {
        "title": "1. 自动安装依赖",
        "body": "首次使用时，脚本会自动检测并安装所需依赖：\n\n# 自动检测并安装\npython3 skills/video-pipeline-bundle/scripts/pipeline.py --install-deps\n\n自动安装的内容：\n\npip3 install auto-editor --break-system-packages\npip3 install faster-whisper requests"
      },
      {
        "title": "2. 配置 MiniMax API Key",
        "body": "方式一：环境变量（推荐）\n\nexport MINIMAX_API_KEY=\"your-api-key-here\"\n\n方式二：运行时传入\n\npython3 skills/video-pipeline-bundle/scripts/pipeline.py \\\n  --all \\\n  --input \"/path/to/videos\" \\\n  --api-key \"your-api-key-here\"\n\n获取 API Key：\n\n访问 MiniMax 开放平台\n注册账号并创建 API Key\n充值或获取免费额度"
      },
      {
        "title": "3. 依赖检查脚本",
        "body": "如果不确定环境是否满足要求，可以运行：\n\npython3 skills/video-pipeline-bundle/scripts/pipeline.py --check-deps\n\n输出示例：\n\n✅ ffmpeg: 已安装 (6.1.1)\n❌ auto-editor: 未安装\n❌ faster-whisper: 未安装\n❌ MINIMAX_API_KEY: 未设置\n\n请运行: python3 skills/video-pipeline-bundle/scripts/pipeline.py --install-deps\n\n如果有存在未安装的，就自动检测用户系统并帮用户安装。"
      },
      {
        "title": "1. 视频剪辑 (video_clip.py)",
        "body": "去除视频中的静音片段，保留有效内容。\n\npython3 skills/video-pipeline-bundle/scripts/video_clip.py \\\n  --input \"/path/to/input.mp4\" \\\n  --output \"/path/to/output.mp4\" \\\n  --threshold -40"
      },
      {
        "title": "2. 语音转写 (video_to_text.py)",
        "body": "用 Faster Whisper 识别语音，生成 SRT 字幕，然后用 MiniMax LLM 词级别纠错。\n\npython3 skills/video-pipeline-bundle/scripts/video_to_text.py \\\n  --input \"/path/to/video.mp4\" \\\n  --output \"/path/to/subtitle.srt\" \\\n  --model small \\\n  --api-key \"your-api-key\"\n\n参数：\n\n参数说明默认--modelWhisper 模型 (tiny/small/base)small--margin静音片段缓冲秒数0.5--api-keyMiniMax API Key环境变量 MINIMAX_API_KEY\n\n模型选择：\n\n模型内存速度tiny~1GB最快small~2GB较快base~3GB中等"
      },
      {
        "title": "3. 烧录字幕 (burn_subtitle.py)",
        "body": "将 SRT 字幕烧录进视频。\n\npython3 skills/video-pipeline-bundle/scripts/burn_subtitle.py \\\n  --input \"/path/to/video.mp4\" \\\n  --subtitle \"/path/to/subtitle.srt\" \\\n  --output \"/path/to/output.mp4\""
      },
      {
        "title": "4. FFmpeg 工具箱 (ffmpeg_tools.py)",
        "body": "支持拼接、格式转换等操作。\n\n# 拼接视频\npython3 skills/video-pipeline-bundle/scripts/ffmpeg_tools.py concat \\\n  --inputs \"1.mp4\" \"2.mp4\" \\\n  --output \"merged.mp4\"\n\n# 格式转换\npython3 skills/video-pipeline-bundle/scripts/ffmpeg_tools.py convert \\\n  --input \"video.mov\" \\\n  --output \"video.mp4\"\n\n# 查看视频信息\npython3 skills/video-pipeline-bundle/scripts/ffmpeg_tools.py info \\\n  --input \"/path/to/videos\""
      },
      {
        "title": "5. 完整工作流 (pipeline.py)",
        "body": "一站式处理，支持分步执行。\n\n# 检查依赖\npython3 skills/video-pipeline-bundle/scripts/pipeline.py --check-deps\n\n# 安装依赖\npython3 skills/video-pipeline-bundle/scripts/pipeline.py --install-deps\n\n# 扫描目录\npython3 skills/video-pipeline-bundle/scripts/pipeline.py \\\n  --list \\\n  --input \"/path/to/videos\"\n\n# 执行单步\npython3 skills/video-pipeline-bundle/scripts/pipeline.py \\\n  --step 1 \\\n  --input \"/path/to/videos\" \\\n  --output \"/path/to/output\"\n\n# 执行全量\npython3 skills/video-pipeline-bundle/scripts/pipeline.py \\\n  --all \\\n  --input \"/path/to/videos\" \\\n  --output \"/path/to/output\" \\\n  --subtitle \"/path/to/subtitles\" \\\n  --api-key \"your-api-key\"\n\n# 带确认模式\npython3 skills/video-pipeline-bundle/scripts/pipeline.py \\\n  --all \\\n  --input \"/path/to/videos\" \\\n  --output \"/path/to/output\" \\\n  --confirm"
      },
      {
        "title": "步骤说明",
        "body": "步骤功能输入输出1剪辑（去静音）原始视频已剪辑视频2转写（生成字幕）已剪辑视频SRT 字幕3烧录已剪辑视频 + 字幕已烧录视频4拼接多个视频合并视频"
      },
      {
        "title": "输出目录结构",
        "body": "输入目录/\n├── 文字稿/           # 字幕文件\n├── 项目名/           # 处理后的视频\n│   ├── 1_已剪辑.mp4\n│   └── 2_已剪辑.mp4\n└── 项目名_成品/     # 最终成品\n    └── 合并视频.mp4"
      },
      {
        "title": "1. 消息通知（可选，默认关闭）",
        "body": "脚本支持发送进度通知到 Feishu，但：\n\n默认不发送消息（--notify false 即可禁用）\n如需启用，请设置 OPENCLAW_TARGET 环境变量为可信目标\n通知内容会包含文件名，请注意信息安全\n\n# 禁用通知（推荐）\npython3 ... --notify false\n\n# 启用通知（仅可信目标）\nexport OPENCLAW_TARGET=\"your-safe-target\""
      },
      {
        "title": "2. 自动安装（默认仅提示）",
        "body": "--install-deps 选项会检测缺失的依赖并提供安装命令，但：\n\n不会自动执行 sudo/apt-get/brew\n仅显示需要手动执行的命令\n建议在虚拟环境或容器中安装"
      },
      {
        "title": "3. API Key 安全",
        "body": "使用环境变量 MINIMAX_API_KEY 而非硬编码\n或使用 --api-key 参数（注意命令历史）\n建议使用受限权限的 API Key"
      },
      {
        "title": "4. 建议的测试方式",
        "body": "# 1. 先检查依赖\npython3 skills/video-pipeline-bundle/scripts/pipeline.py --check-deps\n\n# 2. 手动安装缺失的依赖（不要用 --install-deps 自动安装系统包）\n\n# 3. 在隔离环境测试\npython3 skills/video-pipeline-bundle/scripts/pipeline.py \\\n  --list \\\n  --input \"/path/to/test/videos\" \\\n  --notify false"
      },
      {
        "title": "常见问题",
        "body": "Q: 提示 \"auto-editor 未安装\"\nA: 运行 python3 skills/video-pipeline-bundle/scripts/pipeline.py --install-deps\n\nQ: 提示 \"MINIMAX_API_KEY 未设置\"\nA: 设置环境变量 export MINIMAX_API_KEY=\"your-key\"，或使用 --api-key 参数\n\nQ: 显存不够怎么办？\nA: 使用 --model tiny 参数，tiny 模型只需要 ~1GB 内存\n\nQ: ffmpeg 未安装？\nA: Ubuntu/Debian: sudo apt install ffmpeg | macOS: brew install ffmpeg | Windows: 下载 ffmpeg.exe"
      }
    ],
    "body": "Video Pipeline Bundle\n\n视频一站式工作流技能包，整合剪辑、转写、烧录、拼接全流程。\n\n文件结构\nvideo-pipeline-bundle/\n├── SKILL.md\n└── scripts/\n    ├── pipeline.py      # 工作流编排\n    ├── video_clip.py    # 视频剪辑（去静音）\n    ├── video_to_text.py # 语音转字幕\n    ├── burn_subtitle.py # 烧录字幕\n    └── ffmpeg_tools.py  # FFmpeg 工具箱\n\n依赖\nffmpeg + ffprobe\nPython 3.8+\nauto-editor（视频剪辑）\nfaster-whisper + requests（语音转写）\nMiniMax API Key（LLM 纠错）\n安装与配置\n1. 自动安装依赖\n\n首次使用时，脚本会自动检测并安装所需依赖：\n\n# 自动检测并安装\npython3 skills/video-pipeline-bundle/scripts/pipeline.py --install-deps\n\n\n自动安装的内容：\n\npip3 install auto-editor --break-system-packages\npip3 install faster-whisper requests\n2. 配置 MiniMax API Key\n\n方式一：环境变量（推荐）\n\nexport MINIMAX_API_KEY=\"your-api-key-here\"\n\n\n方式二：运行时传入\n\npython3 skills/video-pipeline-bundle/scripts/pipeline.py \\\n  --all \\\n  --input \"/path/to/videos\" \\\n  --api-key \"your-api-key-here\"\n\n\n获取 API Key：\n\n访问 MiniMax 开放平台\n注册账号并创建 API Key\n充值或获取免费额度\n3. 依赖检查脚本\n\n如果不确定环境是否满足要求，可以运行：\n\npython3 skills/video-pipeline-bundle/scripts/pipeline.py --check-deps\n\n\n输出示例：\n\n✅ ffmpeg: 已安装 (6.1.1)\n❌ auto-editor: 未安装\n❌ faster-whisper: 未安装\n❌ MINIMAX_API_KEY: 未设置\n\n请运行: python3 skills/video-pipeline-bundle/scripts/pipeline.py --install-deps\n\n\n如果有存在未安装的，就自动检测用户系统并帮用户安装。\n\n核心功能\n1. 视频剪辑 (video_clip.py)\n\n去除视频中的静音片段，保留有效内容。\n\npython3 skills/video-pipeline-bundle/scripts/video_clip.py \\\n  --input \"/path/to/input.mp4\" \\\n  --output \"/path/to/output.mp4\" \\\n  --threshold -40\n\n2. 语音转写 (video_to_text.py)\n\n用 Faster Whisper 识别语音，生成 SRT 字幕，然后用 MiniMax LLM 词级别纠错。\n\npython3 skills/video-pipeline-bundle/scripts/video_to_text.py \\\n  --input \"/path/to/video.mp4\" \\\n  --output \"/path/to/subtitle.srt\" \\\n  --model small \\\n  --api-key \"your-api-key\"\n\n\n参数：\n\n参数\t说明\t默认\n--model\tWhisper 模型 (tiny/small/base)\tsmall\n--margin\t静音片段缓冲秒数\t0.5\n--api-key\tMiniMax API Key\t环境变量 MINIMAX_API_KEY\n\n模型选择：\n\n模型\t内存\t速度\ntiny\t~1GB\t最快\nsmall\t~2GB\t较快\nbase\t~3GB\t中等\n3. 烧录字幕 (burn_subtitle.py)\n\n将 SRT 字幕烧录进视频。\n\npython3 skills/video-pipeline-bundle/scripts/burn_subtitle.py \\\n  --input \"/path/to/video.mp4\" \\\n  --subtitle \"/path/to/subtitle.srt\" \\\n  --output \"/path/to/output.mp4\"\n\n4. FFmpeg 工具箱 (ffmpeg_tools.py)\n\n支持拼接、格式转换等操作。\n\n# 拼接视频\npython3 skills/video-pipeline-bundle/scripts/ffmpeg_tools.py concat \\\n  --inputs \"1.mp4\" \"2.mp4\" \\\n  --output \"merged.mp4\"\n\n# 格式转换\npython3 skills/video-pipeline-bundle/scripts/ffmpeg_tools.py convert \\\n  --input \"video.mov\" \\\n  --output \"video.mp4\"\n\n# 查看视频信息\npython3 skills/video-pipeline-bundle/scripts/ffmpeg_tools.py info \\\n  --input \"/path/to/videos\"\n\n5. 完整工作流 (pipeline.py)\n\n一站式处理，支持分步执行。\n\n# 检查依赖\npython3 skills/video-pipeline-bundle/scripts/pipeline.py --check-deps\n\n# 安装依赖\npython3 skills/video-pipeline-bundle/scripts/pipeline.py --install-deps\n\n# 扫描目录\npython3 skills/video-pipeline-bundle/scripts/pipeline.py \\\n  --list \\\n  --input \"/path/to/videos\"\n\n# 执行单步\npython3 skills/video-pipeline-bundle/scripts/pipeline.py \\\n  --step 1 \\\n  --input \"/path/to/videos\" \\\n  --output \"/path/to/output\"\n\n# 执行全量\npython3 skills/video-pipeline-bundle/scripts/pipeline.py \\\n  --all \\\n  --input \"/path/to/videos\" \\\n  --output \"/path/to/output\" \\\n  --subtitle \"/path/to/subtitles\" \\\n  --api-key \"your-api-key\"\n\n# 带确认模式\npython3 skills/video-pipeline-bundle/scripts/pipeline.py \\\n  --all \\\n  --input \"/path/to/videos\" \\\n  --output \"/path/to/output\" \\\n  --confirm\n\n步骤说明\n步骤\t功能\t输入\t输出\n1\t剪辑（去静音）\t原始视频\t已剪辑视频\n2\t转写（生成字幕）\t已剪辑视频\tSRT 字幕\n3\t烧录\t已剪辑视频 + 字幕\t已烧录视频\n4\t拼接\t多个视频\t合并视频\n输出目录结构\n输入目录/\n├── 文字稿/           # 字幕文件\n├── 项目名/           # 处理后的视频\n│   ├── 1_已剪辑.mp4\n│   └── 2_已剪辑.mp4\n└── 项目名_成品/     # 最终成品\n    └── 合并视频.mp4\n\n⚠️ 安全注意事项\n1. 消息通知（可选，默认关闭）\n\n脚本支持发送进度通知到 Feishu，但：\n\n默认不发送消息（--notify false 即可禁用）\n如需启用，请设置 OPENCLAW_TARGET 环境变量为可信目标\n通知内容会包含文件名，请注意信息安全\n# 禁用通知（推荐）\npython3 ... --notify false\n\n# 启用通知（仅可信目标）\nexport OPENCLAW_TARGET=\"your-safe-target\"\n\n2. 自动安装（默认仅提示）\n\n--install-deps 选项会检测缺失的依赖并提供安装命令，但：\n\n不会自动执行 sudo/apt-get/brew\n仅显示需要手动执行的命令\n建议在虚拟环境或容器中安装\n3. API Key 安全\n使用环境变量 MINIMAX_API_KEY 而非硬编码\n或使用 --api-key 参数（注意命令历史）\n建议使用受限权限的 API Key\n4. 建议的测试方式\n# 1. 先检查依赖\npython3 skills/video-pipeline-bundle/scripts/pipeline.py --check-deps\n\n# 2. 手动安装缺失的依赖（不要用 --install-deps 自动安装系统包）\n\n# 3. 在隔离环境测试\npython3 skills/video-pipeline-bundle/scripts/pipeline.py \\\n  --list \\\n  --input \"/path/to/test/videos\" \\\n  --notify false\n\n常见问题\n\nQ: 提示 \"auto-editor 未安装\" A: 运行 python3 skills/video-pipeline-bundle/scripts/pipeline.py --install-deps\n\nQ: 提示 \"MINIMAX_API_KEY 未设置\" A: 设置环境变量 export MINIMAX_API_KEY=\"your-key\"，或使用 --api-key 参数\n\nQ: 显存不够怎么办？ A: 使用 --model tiny 参数，tiny 模型只需要 ~1GB 内存\n\nQ: ffmpeg 未安装？ A: Ubuntu/Debian: sudo apt install ffmpeg | macOS: brew install ffmpeg | Windows: 下载 ffmpeg.exe"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/Leochens/video-pipeline-bundle",
    "publisherUrl": "https://clawhub.ai/Leochens/video-pipeline-bundle",
    "owner": "Leochens",
    "version": "1.0.2",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/video-pipeline-bundle",
    "downloadUrl": "https://openagent3.xyz/downloads/video-pipeline-bundle",
    "agentUrl": "https://openagent3.xyz/skills/video-pipeline-bundle/agent",
    "manifestUrl": "https://openagent3.xyz/skills/video-pipeline-bundle/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/video-pipeline-bundle/agent.md"
  }
}