{
  "schemaVersion": "1.0",
  "item": {
    "slug": "youtube-transcript-yt-dlp",
    "name": "YouTube Transcript (yt-dlp captions)",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/ItzSubhadip/youtube-transcript-yt-dlp",
    "canonicalUrl": "https://clawhub.ai/ItzSubhadip/youtube-transcript-yt-dlp",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/youtube-transcript-yt-dlp",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=youtube-transcript-yt-dlp",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "scripts/yt_transcript.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": "2026-05-07T17:22:31.273Z",
      "expiresAt": "2026-05-14T17:22:31.273Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report",
        "contentDisposition": "attachment; filename=\"afrexai-annual-report-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/youtube-transcript-yt-dlp"
    },
    "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/youtube-transcript-yt-dlp",
    "agentPageUrl": "https://openagent3.xyz/skills/youtube-transcript-yt-dlp/agent",
    "manifestUrl": "https://openagent3.xyz/skills/youtube-transcript-yt-dlp/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/youtube-transcript-yt-dlp/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": "YouTube Transcript (Captions-Only)",
        "body": "This skill extracts transcripts from existing YouTube captions.\n\nPrimary behavior\n\nPrefer manual subtitles when available.\nFall back to auto-generated captions.\nOutput either:\n\nJSON segments (default) or\nplain text (--text)\n\n\nCache results locally in SQLite for speed.\n\nReliability behavior\n\nIf YouTube blocks anonymous access (bot-check), provide cookies.txt.\nIf yt-dlp reports no captions for a video, the script tries a fallback:\n\nYouTube’s transcript panel (youtubei get_transcript) when accessible\n\nThis published version intentionally does not call third-party transcript providers.\n\nPrivacy note: This published version only contacts YouTube directly (via yt-dlp and the transcript panel fallback). It does not send video IDs/URLs to third-party transcript providers.\n\nCookies: Cookies are treated as secrets.\n\nThe script supports --cookies / YT_TRANSCRIPT_COOKIES, but does not auto-load cookies from inside the skill directory.\nStore cookies under ~/.config/yt-transcript/.\n\nPath safety: This skill restricts --cookies and --cache paths to approved directories.\n\ncookies allowed under: ~/.config/yt-transcript/\ncache allowed under: {baseDir}/cache/ and ~/.config/yt-transcript/"
      },
      {
        "title": "How to run",
        "body": "Script path:\n\n{baseDir}/scripts/yt_transcript.py\n\nTypical usage:\n\npython3 {baseDir}/scripts/yt_transcript.py <youtube_url_or_id>\npython3 {baseDir}/scripts/yt_transcript.py <url> --lang en\npython3 {baseDir}/scripts/yt_transcript.py <url> --text\npython3 {baseDir}/scripts/yt_transcript.py <url> --no-ts\n\nCookies (optional, but often required on VPS IPs):\n\npython3 {baseDir}/scripts/yt_transcript.py <url> --cookies /path/to/youtube-cookies.txt\nor set env var: YT_TRANSCRIPT_COOKIES=/path/to/youtube-cookies.txt\n\nPublishing safety note: Cookies are optional, so YT_TRANSCRIPT_COOKIES is intentionally not required by skill metadata. Only set it if you need authenticated access.\n\nBest practice: store cookies outside the skill folder (so you never accidentally publish them), e.g. ~/.config/yt-transcript/youtube-cookies.txt, and point to it via --cookies or YT_TRANSCRIPT_COOKIES."
      },
      {
        "title": "JSON mode (default)",
        "body": "A JSON object:\n\nvideo_id: 11-char id\nlang: chosen language\nsource: manual | auto | panel\nsegments: list of { start, duration, text } (or text-only when --no-ts)"
      },
      {
        "title": "Text mode (--text)",
        "body": "A newline-separated transcript.\n\nBy default timestamps are included as [12.34s].\nUse --no-ts to output only the text lines."
      },
      {
        "title": "Caching",
        "body": "Default cache DB:\n\n{baseDir}/cache/transcripts.sqlite\n\nCache key includes:\n\nvideo_id, lang, source, include_timestamp, format"
      },
      {
        "title": "Cookie handling (important)",
        "body": "Cookies must be in Netscape cookies.txt format.\nTreat cookies as secrets.\nNever commit / publish cookies to ClawHub.\n\nRecommended local path (ignored by git/publish):\n\n{baseDir}/cache/youtube-cookies.txt (chmod 600)"
      },
      {
        "title": "Notes (safety + reliability)",
        "body": "Only accept a YouTube URL or an 11-character video ID.\nDo not forward arbitrary user-provided flags into the command.\nIf yt-dlp is missing, instruct the user to install it (recommended):\n\ninstall pipx\npipx install yt-dlp\nensure yt-dlp is on PATH"
      }
    ],
    "body": "YouTube Transcript (Captions-Only)\n\nThis skill extracts transcripts from existing YouTube captions.\n\nPrimary behavior\n\nPrefer manual subtitles when available.\nFall back to auto-generated captions.\nOutput either:\nJSON segments (default) or\nplain text (--text)\nCache results locally in SQLite for speed.\n\nReliability behavior\n\nIf YouTube blocks anonymous access (bot-check), provide cookies.txt.\nIf yt-dlp reports no captions for a video, the script tries a fallback:\nYouTube’s transcript panel (youtubei get_transcript) when accessible\n\nThis published version intentionally does not call third-party transcript providers.\n\nPrivacy note: This published version only contacts YouTube directly (via yt-dlp and the transcript panel fallback). It does not send video IDs/URLs to third-party transcript providers.\n\nCookies: Cookies are treated as secrets.\n\nThe script supports --cookies / YT_TRANSCRIPT_COOKIES, but does not auto-load cookies from inside the skill directory.\nStore cookies under ~/.config/yt-transcript/.\n\nPath safety: This skill restricts --cookies and --cache paths to approved directories.\n\ncookies allowed under: ~/.config/yt-transcript/\ncache allowed under: {baseDir}/cache/ and ~/.config/yt-transcript/\nHow to run\n\nScript path:\n\n{baseDir}/scripts/yt_transcript.py\n\nTypical usage:\n\npython3 {baseDir}/scripts/yt_transcript.py <youtube_url_or_id>\npython3 {baseDir}/scripts/yt_transcript.py <url> --lang en\npython3 {baseDir}/scripts/yt_transcript.py <url> --text\npython3 {baseDir}/scripts/yt_transcript.py <url> --no-ts\n\nCookies (optional, but often required on VPS IPs):\n\npython3 {baseDir}/scripts/yt_transcript.py <url> --cookies /path/to/youtube-cookies.txt\nor set env var: YT_TRANSCRIPT_COOKIES=/path/to/youtube-cookies.txt\n\nPublishing safety note: Cookies are optional, so YT_TRANSCRIPT_COOKIES is intentionally not required by skill metadata. Only set it if you need authenticated access.\n\nBest practice: store cookies outside the skill folder (so you never accidentally publish them), e.g. ~/.config/yt-transcript/youtube-cookies.txt, and point to it via --cookies or YT_TRANSCRIPT_COOKIES.\n\nWhat the script returns\nJSON mode (default)\n\nA JSON object:\n\nvideo_id: 11-char id\nlang: chosen language\nsource: manual | auto | panel\nsegments: list of { start, duration, text } (or text-only when --no-ts)\nText mode (--text)\n\nA newline-separated transcript.\n\nBy default timestamps are included as [12.34s].\nUse --no-ts to output only the text lines.\nCaching\n\nDefault cache DB:\n\n{baseDir}/cache/transcripts.sqlite\n\nCache key includes:\n\nvideo_id, lang, source, include_timestamp, format\nCookie handling (important)\nCookies must be in Netscape cookies.txt format.\nTreat cookies as secrets.\nNever commit / publish cookies to ClawHub.\n\nRecommended local path (ignored by git/publish):\n\n{baseDir}/cache/youtube-cookies.txt (chmod 600)\nNotes (safety + reliability)\nOnly accept a YouTube URL or an 11-character video ID.\nDo not forward arbitrary user-provided flags into the command.\nIf yt-dlp is missing, instruct the user to install it (recommended):\ninstall pipx\npipx install yt-dlp\nensure yt-dlp is on PATH"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/ItzSubhadip/youtube-transcript-yt-dlp",
    "publisherUrl": "https://clawhub.ai/ItzSubhadip/youtube-transcript-yt-dlp",
    "owner": "ItzSubhadip",
    "version": "1.0.5",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/youtube-transcript-yt-dlp",
    "downloadUrl": "https://openagent3.xyz/downloads/youtube-transcript-yt-dlp",
    "agentUrl": "https://openagent3.xyz/skills/youtube-transcript-yt-dlp/agent",
    "manifestUrl": "https://openagent3.xyz/skills/youtube-transcript-yt-dlp/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/youtube-transcript-yt-dlp/agent.md"
  }
}