{
  "schemaVersion": "1.0",
  "item": {
    "slug": "video-news-downloader",
    "name": "Video News Downloader",
    "source": "tencent",
    "type": "skill",
    "category": "其他",
    "sourceUrl": "https://clawhub.ai/Cyberpsychosissss/video-news-downloader",
    "canonicalUrl": "https://clawhub.ai/Cyberpsychosissss/video-news-downloader",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/video-news-downloader",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=video-news-downloader",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "references/cron-setup.md",
      "references/workflow.md",
      "scripts/setup_cron.sh",
      "scripts/setup_server.sh",
      "scripts/subtitle_proofreader.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": "2026-04-23T16:43:11.935Z",
      "expiresAt": "2026-04-30T16:43:11.935Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
        "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.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-news-downloader"
    },
    "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-news-downloader",
    "agentPageUrl": "https://openagent3.xyz/skills/video-news-downloader/agent",
    "manifestUrl": "https://openagent3.xyz/skills/video-news-downloader/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/video-news-downloader/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 News Downloader with AI Subtitle Proofreading",
        "body": "Complete workflow for downloading daily news videos, processing subtitles, and serving them via HTTP with web players."
      },
      {
        "title": "Overview",
        "body": "This skill automates:\n\nVideo Download: CBS Evening News + BBC News at Ten from YouTube\nSubtitle Processing: Extract auto-captions and convert to VTT format\nAI Proofreading: Use DeepSeek to fix speech recognition errors\nHTTP Streaming: Serve videos with embedded web players\nScheduled Updates: Daily cron jobs at configurable times"
      },
      {
        "title": "1. Download Latest News",
        "body": "python3 scripts/video_download.py --cbs --bbc"
      },
      {
        "title": "2. Proofread Subtitles",
        "body": "python3 scripts/subtitle_proofreader.py /path/to/subtitle.vtt\n\nOr use DeepSeek directly:\n\n\"校对字幕文件 /path/to/subtitle.vtt\""
      },
      {
        "title": "3. Start HTTP Servers",
        "body": "bash scripts/setup_server.sh"
      },
      {
        "title": "4. Setup Daily Cron Jobs",
        "body": "bash scripts/setup_cron.sh"
      },
      {
        "title": "Video Download Script",
        "body": "Download CBS only:\n\npython3 scripts/video_download.py --cbs\n\nDownload BBC only:\n\npython3 scripts/video_download.py --bbc\n\nDownload both:\n\npython3 scripts/video_download.py --cbs --bbc\n\nWith subtitle proofreading:\n\npython3 scripts/video_download.py --cbs --bbc --proofread"
      },
      {
        "title": "Subtitle Proofreading",
        "body": "Proofread single file:\n\npython3 scripts/subtitle_proofreader.py <vtt_file_path>\n\nAuto-proofread all news subtitles:\n\npython3 scripts/subtitle_proofreader.py --all"
      },
      {
        "title": "Server Management",
        "body": "Start servers:\n\nbash scripts/setup_server.sh start\n\nCheck status:\n\nbash scripts/setup_server.sh status\n\nStop servers:\n\nbash scripts/setup_server.sh stop"
      },
      {
        "title": "File Structure",
        "body": "/workspace/\n├── cbs-live-local/\n│   ├── cbs_latest.mp4\n│   ├── cbs_latest.en.vtt          # Original subtitle\n│   ├── cbs_latest.en.vtt-backup   # Backup\n│   ├── cbs_latest-corrected.txt   # DeepSeek corrected text\n│   └── cbs_latest-corrections.md  # Error list\n│\n├── bbc-news-live/\n│   ├── bbc_news_latest.mp4\n│   ├── bbc_news_latest.en.vtt\n│   ├── bbc_news_latest.en.vtt-backup\n│   ├── bbc_news_latest-corrected.txt\n│   └── bbc_news_latest-corrections.md\n│\n└── temp/                           # Temporary download files"
      },
      {
        "title": "HTTP Endpoints",
        "body": "EndpointDescriptionhttp://IP:8093/CBS Evening News playerhttp://IP:8093/cbs_latest.mp4CBS video directhttp://IP:8095/BBC News at Ten playerhttp://IP:8095/bbc_news_latest.mp4BBC video direct"
      },
      {
        "title": "Default Schedule (Beijing Time)",
        "body": "TimeTask20:00Download latest CBS + BBC videos20:30DeepSeek proofread subtitles"
      },
      {
        "title": "Manual Cron Setup",
        "body": "See references/cron-setup.md for detailed cron configuration."
      },
      {
        "title": "What Gets Fixed",
        "body": "Speech recognition errors (e.g., \"noraster\" → \"nor'easter\")\nName errors (e.g., \"trunk\" → \"Trump\")\nLocation name errors\nProfessional terminology errors\nObvious spelling mistakes"
      },
      {
        "title": "Output Files",
        "body": "For each subtitle file, generates:\n\n-backup.vtt - Original subtitle (never modified)\n-corrected.txt - AI-corrected plain text\n-corrections.md - List of corrections made"
      },
      {
        "title": "Video Download Fails",
        "body": "Check yt-dlp is installed: yt-dlp --version\nCheck YouTube URL is accessible\nTry manual download first"
      },
      {
        "title": "Subtitle Extraction Fails",
        "body": "Some videos don't have auto-captions\nCheck if --list-subs shows available languages"
      },
      {
        "title": "Server Won't Start",
        "body": "Check ports 8093/8095 are free: lsof -i :8093\nCheck Python http.server is available"
      },
      {
        "title": "Proofreading Issues",
        "body": "Ensure DeepSeek model is available\nCheck subtitle file exists and is valid VTT format"
      },
      {
        "title": "See Also",
        "body": "references/workflow.md - Detailed workflow documentation\nreferences/cron-setup.md - Cron job configuration guide"
      }
    ],
    "body": "Video News Downloader with AI Subtitle Proofreading\n\nComplete workflow for downloading daily news videos, processing subtitles, and serving them via HTTP with web players.\n\nOverview\n\nThis skill automates:\n\nVideo Download: CBS Evening News + BBC News at Ten from YouTube\nSubtitle Processing: Extract auto-captions and convert to VTT format\nAI Proofreading: Use DeepSeek to fix speech recognition errors\nHTTP Streaming: Serve videos with embedded web players\nScheduled Updates: Daily cron jobs at configurable times\nQuick Start\n1. Download Latest News\npython3 scripts/video_download.py --cbs --bbc\n\n2. Proofread Subtitles\npython3 scripts/subtitle_proofreader.py /path/to/subtitle.vtt\n\n\nOr use DeepSeek directly:\n\n\"校对字幕文件 /path/to/subtitle.vtt\"\n\n3. Start HTTP Servers\nbash scripts/setup_server.sh\n\n4. Setup Daily Cron Jobs\nbash scripts/setup_cron.sh\n\nCommands\nVideo Download Script\n\nDownload CBS only:\n\npython3 scripts/video_download.py --cbs\n\n\nDownload BBC only:\n\npython3 scripts/video_download.py --bbc\n\n\nDownload both:\n\npython3 scripts/video_download.py --cbs --bbc\n\n\nWith subtitle proofreading:\n\npython3 scripts/video_download.py --cbs --bbc --proofread\n\nSubtitle Proofreading\n\nProofread single file:\n\npython3 scripts/subtitle_proofreader.py <vtt_file_path>\n\n\nAuto-proofread all news subtitles:\n\npython3 scripts/subtitle_proofreader.py --all\n\nServer Management\n\nStart servers:\n\nbash scripts/setup_server.sh start\n\n\nCheck status:\n\nbash scripts/setup_server.sh status\n\n\nStop servers:\n\nbash scripts/setup_server.sh stop\n\nFile Structure\n/workspace/\n├── cbs-live-local/\n│   ├── cbs_latest.mp4\n│   ├── cbs_latest.en.vtt          # Original subtitle\n│   ├── cbs_latest.en.vtt-backup   # Backup\n│   ├── cbs_latest-corrected.txt   # DeepSeek corrected text\n│   └── cbs_latest-corrections.md  # Error list\n│\n├── bbc-news-live/\n│   ├── bbc_news_latest.mp4\n│   ├── bbc_news_latest.en.vtt\n│   ├── bbc_news_latest.en.vtt-backup\n│   ├── bbc_news_latest-corrected.txt\n│   └── bbc_news_latest-corrections.md\n│\n└── temp/                           # Temporary download files\n\nHTTP Endpoints\nEndpoint\tDescription\nhttp://IP:8093/\tCBS Evening News player\nhttp://IP:8093/cbs_latest.mp4\tCBS video direct\nhttp://IP:8095/\tBBC News at Ten player\nhttp://IP:8095/bbc_news_latest.mp4\tBBC video direct\nCron Jobs\nDefault Schedule (Beijing Time)\nTime\tTask\n20:00\tDownload latest CBS + BBC videos\n20:30\tDeepSeek proofread subtitles\nManual Cron Setup\n\nSee references/cron-setup.md for detailed cron configuration.\n\nDeepSeek Proofreading\nWhat Gets Fixed\nSpeech recognition errors (e.g., \"noraster\" → \"nor'easter\")\nName errors (e.g., \"trunk\" → \"Trump\")\nLocation name errors\nProfessional terminology errors\nObvious spelling mistakes\nOutput Files\n\nFor each subtitle file, generates:\n\n-backup.vtt - Original subtitle (never modified)\n-corrected.txt - AI-corrected plain text\n-corrections.md - List of corrections made\nTroubleshooting\nVideo Download Fails\nCheck yt-dlp is installed: yt-dlp --version\nCheck YouTube URL is accessible\nTry manual download first\nSubtitle Extraction Fails\nSome videos don't have auto-captions\nCheck if --list-subs shows available languages\nServer Won't Start\nCheck ports 8093/8095 are free: lsof -i :8093\nCheck Python http.server is available\nProofreading Issues\nEnsure DeepSeek model is available\nCheck subtitle file exists and is valid VTT format\nSee Also\nreferences/workflow.md - Detailed workflow documentation\nreferences/cron-setup.md - Cron job configuration guide"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/Cyberpsychosissss/video-news-downloader",
    "publisherUrl": "https://clawhub.ai/Cyberpsychosissss/video-news-downloader",
    "owner": "Cyberpsychosissss",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/video-news-downloader",
    "downloadUrl": "https://openagent3.xyz/downloads/video-news-downloader",
    "agentUrl": "https://openagent3.xyz/skills/video-news-downloader/agent",
    "manifestUrl": "https://openagent3.xyz/skills/video-news-downloader/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/video-news-downloader/agent.md"
  }
}