{ "schemaVersion": "1.0", "item": { "slug": "yt-summary", "name": "Youtube Summary", "source": "tencent", "type": "skill", "category": "通讯协作", "sourceUrl": "https://clawhub.ai/chapati23/yt-summary", "canonicalUrl": "https://clawhub.ai/chapati23/yt-summary", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/yt-summary", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=yt-summary", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "README.md", "SKILL.md", "requirements.txt", "scripts/extract.py", "scripts/prompts.py", "scripts/utils.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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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/yt-summary" }, "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/yt-summary", "agentPageUrl": "https://openagent3.xyz/skills/yt-summary/agent", "manifestUrl": "https://openagent3.xyz/skills/yt-summary/agent.json", "briefUrl": "https://openagent3.xyz/skills/yt-summary/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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "YouTube Summary Skill", "body": "Summarize YouTube videos by extracting transcripts via TranscriptAPI.com and generating structured summaries." }, { "title": "Prerequisites", "body": "Python 3.10+\nA TranscriptAPI.com account ($5/mo for 1,000 transcripts)\nOptional: pass (Unix password manager) for secure key storage" }, { "title": "Installation", "body": "Sign up at transcriptapi.com and get your API key\nProvide the API key via one of these methods:\n\nEnvironment variable (simplest): export TRANSCRIPT_API_KEY=\"your-key-here\"\npass password store (most secure): pass insert transcriptapi/api-key\n\n\nInstall Python dependencies:\npip install -r skills/youtube-summary/requirements.txt" }, { "title": "Detection", "body": "Trigger on messages containing YouTube URLs matching any of:\n\nyoutube.com/watch?v=ID\nyoutu.be/ID\nyoutube.com/shorts/ID\nm.youtube.com/watch?v=ID\nyoutube.com/live/ID" }, { "title": "⚠️ Critical Rules", "body": "NEVER use web_search as a fallback. If transcript extraction fails, report the error and stop.\nNEVER fabricate transcript content. Only summarize what the extraction script returns.\nAlways run the extraction script. Do not skip it, even for well-known videos." }, { "title": "Step 1: Extract transcript", "body": "If using pass:\n\n_yt_key_file=$(mktemp) && pass transcriptapi/api-key > \"$_yt_key_file\" && python3 skills/youtube-summary/scripts/extract.py \"YOUTUBE_URL_OR_ID\" --api-key-file \"$_yt_key_file\"; rm -f \"$_yt_key_file\"\n\nIf using env var:\n\npython3 skills/youtube-summary/scripts/extract.py \"YOUTUBE_URL_OR_ID\"\n\n(Reads TRANSCRIPT_API_KEY from the environment automatically.)\n\nSecurity note: The pass + temp file approach avoids exposing the key in ps output or shell history. The env var approach is simpler but the key is visible in the process environment.\n\nParse stdout:\n\nPROGRESS: lines → relay to user as status updates (optional)\nERROR: lines → relay error to user, stop\nRESULT: line → parse the JSON after RESULT: — contains: header, transcript, language, tokens, title, channel, duration_str" }, { "title": "Step 2: Summarize the transcript", "body": "Use the extracted transcript to generate a summary. The summary language must match the transcript language (from the language field).\n\nIf tokens < 50000 — single-pass: summarize the full transcript in one request.\n\nIf tokens ≥ 50000 — tell the user it's a long video and summarize the first ~40K tokens with a note that it was truncated.\n\nDefault summary format (use when no custom prompt given):\n\n{header}\n\n**TL;DR:** 2-3 sentence summary.\n\n**Key Points:**\n• Point one\n• Point two\n• (3-7 total)\n\n**Notable Quotes:** (only if genuinely quotable lines exist)\n> \"Quote here\"\n\nCustom prompt — if the user included text alongside the URL, append it as additional instructions for the summary." }, { "title": "Step 3: Reply", "body": "Keep output under 4000 characters for Telegram\nIf the summary would exceed 4000 chars, send the TL;DR first, then the rest as a follow-up\nAlways include the header line from the extraction result" }, { "title": "Error Handling", "body": "ERROR: API_ERROR: Invalid API key → \"TranscriptAPI key is invalid. Check pass transcriptapi/api-key.\"\nERROR: No transcript available → \"This video doesn't have captions available.\"\nERROR: Video not found → \"Couldn't find that video — double-check the URL.\"\nAny other ERROR: → relay the message as-is. Do NOT fall back to web_search." }, { "title": "Why TranscriptAPI?", "body": "YouTube aggressively blocks datacenter/IPv6 ranges from accessing transcripts. Most cloud VPS (Hetzner, DigitalOcean, AWS, etc.) are blocked — direct transcript fetching fails for most videos when running from a server.\n\nTranscriptAPI.com proxies requests through residential IPs, bypassing these blocks reliably. The $5/mo plan covers 1,000 transcript fetches.\n\n💡 Tip: Add instructions after the URL to customize the summary (e.g. \"focus on the technical details\")." } ], "body": "YouTube Summary Skill\n\nSummarize YouTube videos by extracting transcripts via TranscriptAPI.com and generating structured summaries.\n\nSetup\nPrerequisites\nPython 3.10+\nA TranscriptAPI.com account ($5/mo for 1,000 transcripts)\nOptional: pass (Unix password manager) for secure key storage\nInstallation\nSign up at transcriptapi.com and get your API key\nProvide the API key via one of these methods:\nEnvironment variable (simplest): export TRANSCRIPT_API_KEY=\"your-key-here\"\npass password store (most secure): pass insert transcriptapi/api-key\nInstall Python dependencies:\npip install -r skills/youtube-summary/requirements.txt\n\nDetection\n\nTrigger on messages containing YouTube URLs matching any of:\n\nyoutube.com/watch?v=ID\nyoutu.be/ID\nyoutube.com/shorts/ID\nm.youtube.com/watch?v=ID\nyoutube.com/live/ID\n⚠️ Critical Rules\nNEVER use web_search as a fallback. If transcript extraction fails, report the error and stop.\nNEVER fabricate transcript content. Only summarize what the extraction script returns.\nAlways run the extraction script. Do not skip it, even for well-known videos.\nWorkflow\nStep 1: Extract transcript\n\nIf using pass:\n\n_yt_key_file=$(mktemp) && pass transcriptapi/api-key > \"$_yt_key_file\" && python3 skills/youtube-summary/scripts/extract.py \"YOUTUBE_URL_OR_ID\" --api-key-file \"$_yt_key_file\"; rm -f \"$_yt_key_file\"\n\n\nIf using env var:\n\npython3 skills/youtube-summary/scripts/extract.py \"YOUTUBE_URL_OR_ID\"\n\n\n(Reads TRANSCRIPT_API_KEY from the environment automatically.)\n\nSecurity note: The pass + temp file approach avoids exposing the key in ps output or shell history. The env var approach is simpler but the key is visible in the process environment.\n\nParse stdout:\n\nPROGRESS: lines → relay to user as status updates (optional)\nERROR: lines → relay error to user, stop\nRESULT: line → parse the JSON after RESULT: — contains: header, transcript, language, tokens, title, channel, duration_str\nStep 2: Summarize the transcript\n\nUse the extracted transcript to generate a summary. The summary language must match the transcript language (from the language field).\n\nIf tokens < 50000 — single-pass: summarize the full transcript in one request.\n\nIf tokens ≥ 50000 — tell the user it's a long video and summarize the first ~40K tokens with a note that it was truncated.\n\nDefault summary format (use when no custom prompt given):\n\n{header}\n\n**TL;DR:** 2-3 sentence summary.\n\n**Key Points:**\n• Point one\n• Point two\n• (3-7 total)\n\n**Notable Quotes:** (only if genuinely quotable lines exist)\n> \"Quote here\"\n\n\nCustom prompt — if the user included text alongside the URL, append it as additional instructions for the summary.\n\nStep 3: Reply\nKeep output under 4000 characters for Telegram\nIf the summary would exceed 4000 chars, send the TL;DR first, then the rest as a follow-up\nAlways include the header line from the extraction result\nError Handling\nERROR: API_ERROR: Invalid API key → \"TranscriptAPI key is invalid. Check pass transcriptapi/api-key.\"\nERROR: No transcript available → \"This video doesn't have captions available.\"\nERROR: Video not found → \"Couldn't find that video — double-check the URL.\"\nAny other ERROR: → relay the message as-is. Do NOT fall back to web_search.\nWhy TranscriptAPI?\n\nYouTube aggressively blocks datacenter/IPv6 ranges from accessing transcripts. Most cloud VPS (Hetzner, DigitalOcean, AWS, etc.) are blocked — direct transcript fetching fails for most videos when running from a server.\n\nTranscriptAPI.com proxies requests through residential IPs, bypassing these blocks reliably. The $5/mo plan covers 1,000 transcript fetches.\n\n💡 Tip: Add instructions after the URL to customize the summary (e.g. \"focus on the technical details\")." }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/chapati23/yt-summary", "publisherUrl": "https://clawhub.ai/chapati23/yt-summary", "owner": "chapati23", "version": "1.3.2", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/yt-summary", "downloadUrl": "https://openagent3.xyz/downloads/yt-summary", "agentUrl": "https://openagent3.xyz/skills/yt-summary/agent", "manifestUrl": "https://openagent3.xyz/skills/yt-summary/agent.json", "briefUrl": "https://openagent3.xyz/skills/yt-summary/agent.md" } }