{ "schemaVersion": "1.0", "item": { "slug": "video-intel", "name": "Video Intelligence", "source": "tencent", "type": "skill", "category": "其他", "sourceUrl": "https://clawhub.ai/nogara/video-intel", "canonicalUrl": "https://clawhub.ai/nogara/video-intel", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/video-intel", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=video-intel", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "scripts/video-intel.sh", "scripts/parse-vtt.py", "SKILL.md" ], "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-intel" }, "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-intel", "agentPageUrl": "https://openagent3.xyz/skills/video-intel/agent", "manifestUrl": "https://openagent3.xyz/skills/video-intel/agent.json", "briefUrl": "https://openagent3.xyz/skills/video-intel/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-intel", "body": "Downloads videos and extracts transcripts using yt-dlp (captions) with OpenAI Whisper fallback." }, { "title": "Required Dependencies", "body": "DependencyPurposeRequired?yt-dlpFetch captions and download audio/video✅ Alwayspython3Parse VTT/SRT caption files✅ AlwayscurlCall OpenAI Whisper API✅ For Whisper fallbackffmpegExtract audio from TikTok/Instagram/X⚠️ Non-YouTube onlyOPENAI_API_KEYAuthenticate with OpenAI Whisper API⚠️ Only if captions unavailable\n\nInstall binaries:\n\n# yt-dlp\ncurl -L https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp -o ~/bin/yt-dlp && chmod +x ~/bin/yt-dlp\n\n# ffmpeg (Debian/Ubuntu)\nsudo apt install ffmpeg" }, { "title": "⚠️ Privacy Notice — OpenAI Audio Upload", "body": "When captions are unavailable (common for TikTok, Instagram, X), the script downloads the audio and uploads it to OpenAI's transcription API (https://api.openai.com/v1/audio/transcriptions). This means:\n\nAudio content leaves your machine and is sent to OpenAI\nRequires OPENAI_API_KEY to be set\nIf you don't want external transmission: don't set OPENAI_API_KEY, or use a local transcription model\n\nYouTube videos almost always have captions and will not trigger an upload." }, { "title": "Script", "body": "~/.openclaw/skills/video-intel/scripts/video-intel.sh" }, { "title": "Get transcript", "body": "~/.openclaw/skills/video-intel/scripts/video-intel.sh transcript \n\nYouTube: uses built-in captions/auto-subs (fast, no audio download or external upload)\nTikTok/Instagram/X: downloads audio → uploads to OpenAI Whisper for transcription\nPreferred language: --lang pt for Portuguese" }, { "title": "Get video info", "body": "~/.openclaw/skills/video-intel/scripts/video-intel.sh info " }, { "title": "List available caption tracks", "body": "~/.openclaw/skills/video-intel/scripts/video-intel.sh captions " }, { "title": "Download video", "body": "~/.openclaw/skills/video-intel/scripts/video-intel.sh download [--format audio|720p|best]" }, { "title": "After getting transcript", "body": "Summary: Summarize in 3-5 bullet points\nKey quotes: Extract most notable quotes\nFull summary: Write a paragraph summary with context\nTranslation: Translate to the user's language if different" }, { "title": "Notes", "body": "YouTube auto-captions are usually available even without ffmpeg\nTikTok/Instagram/X require ffmpeg for audio extraction\nLarge videos (>25MB audio) may hit OpenAI's file size limit — use --format audio to get a smaller mp3\nOutput cached in /tmp/video-intel/ by default" } ], "body": "video-intel\n\nDownloads videos and extracts transcripts using yt-dlp (captions) with OpenAI Whisper fallback.\n\nRequired Dependencies\nDependency\tPurpose\tRequired?\nyt-dlp\tFetch captions and download audio/video\t✅ Always\npython3\tParse VTT/SRT caption files\t✅ Always\ncurl\tCall OpenAI Whisper API\t✅ For Whisper fallback\nffmpeg\tExtract audio from TikTok/Instagram/X\t⚠️ Non-YouTube only\nOPENAI_API_KEY\tAuthenticate with OpenAI Whisper API\t⚠️ Only if captions unavailable\n\nInstall binaries:\n\n# yt-dlp\ncurl -L https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp -o ~/bin/yt-dlp && chmod +x ~/bin/yt-dlp\n\n# ffmpeg (Debian/Ubuntu)\nsudo apt install ffmpeg\n\n⚠️ Privacy Notice — OpenAI Audio Upload\n\nWhen captions are unavailable (common for TikTok, Instagram, X), the script downloads the audio and uploads it to OpenAI's transcription API (https://api.openai.com/v1/audio/transcriptions). This means:\n\nAudio content leaves your machine and is sent to OpenAI\nRequires OPENAI_API_KEY to be set\nIf you don't want external transmission: don't set OPENAI_API_KEY, or use a local transcription model\n\nYouTube videos almost always have captions and will not trigger an upload.\n\nScript\n~/.openclaw/skills/video-intel/scripts/video-intel.sh\n\nWorkflows\nGet transcript\n~/.openclaw/skills/video-intel/scripts/video-intel.sh transcript \n\nYouTube: uses built-in captions/auto-subs (fast, no audio download or external upload)\nTikTok/Instagram/X: downloads audio → uploads to OpenAI Whisper for transcription\nPreferred language: --lang pt for Portuguese\nGet video info\n~/.openclaw/skills/video-intel/scripts/video-intel.sh info \n\nList available caption tracks\n~/.openclaw/skills/video-intel/scripts/video-intel.sh captions \n\nDownload video\n~/.openclaw/skills/video-intel/scripts/video-intel.sh download [--format audio|720p|best]\n\nAfter getting transcript\nSummary: Summarize in 3-5 bullet points\nKey quotes: Extract most notable quotes\nFull summary: Write a paragraph summary with context\nTranslation: Translate to the user's language if different\nNotes\nYouTube auto-captions are usually available even without ffmpeg\nTikTok/Instagram/X require ffmpeg for audio extraction\nLarge videos (>25MB audio) may hit OpenAI's file size limit — use --format audio to get a smaller mp3\nOutput cached in /tmp/video-intel/ by default" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/nogara/video-intel", "publisherUrl": "https://clawhub.ai/nogara/video-intel", "owner": "nogara", "version": "1.0.1", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/video-intel", "downloadUrl": "https://openagent3.xyz/downloads/video-intel", "agentUrl": "https://openagent3.xyz/skills/video-intel/agent", "manifestUrl": "https://openagent3.xyz/skills/video-intel/agent.json", "briefUrl": "https://openagent3.xyz/skills/video-intel/agent.md" } }