{ "schemaVersion": "1.0", "item": { "slug": "video-understanding", "name": "Video Understanding", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/bill492/video-understanding", "canonicalUrl": "https://clawhub.ai/bill492/video-understanding", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/video-understanding", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=video-understanding", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "scripts/analyze_video.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-understanding" }, "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-understanding", "agentPageUrl": "https://openagent3.xyz/skills/video-understanding/agent", "manifestUrl": "https://openagent3.xyz/skills/video-understanding/agent.json", "briefUrl": "https://openagent3.xyz/skills/video-understanding/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 Understanding (Gemini)", "body": "Analyze videos using Google Gemini's multimodal video understanding. Supports 1000+ video sources via yt-dlp." }, { "title": "Requirements", "body": "yt-dlp — brew install yt-dlp / pip install yt-dlp\nffmpeg — brew install ffmpeg (for merging video+audio streams)\nGEMINI_API_KEY environment variable" }, { "title": "Default Output", "body": "Returns structured JSON:\n\ntranscript — Verbatim transcript with [MM:SS] timestamps\ndescription — Visual description (people, setting, UI, text on screen, flow)\nsummary — 2-3 sentence summary\nduration_seconds — Estimated duration\nspeakers — Identified speakers" }, { "title": "Analyze a video (structured JSON output)", "body": "uv run {baseDir}/scripts/analyze_video.py \"\"" }, { "title": "Ask a question (adds \"answer\" field)", "body": "uv run {baseDir}/scripts/analyze_video.py \"\" -q \"What product is shown?\"" }, { "title": "Override prompt entirely", "body": "uv run {baseDir}/scripts/analyze_video.py \"\" -p \"Custom prompt\" --raw" }, { "title": "Download only (no analysis)", "body": "uv run {baseDir}/scripts/analyze_video.py \"\" --download-only -o video.mp4" }, { "title": "Options", "body": "FlagDescriptionDefault-q / --questionQuestion to answer (added to default fields)none-p / --promptOverride entire prompt (ignores -q)structured JSON-m / --modelGemini modelgemini-2.5-flash-o / --outputSave output to filestdout--keepKeep downloaded video filefalse--download-onlyDownload only, skip analysisfalse--max-sizeMax file size in MB500--rawRaw text output instead of JSONfalse" }, { "title": "How It Works", "body": "YouTube URLs → Passed directly to Gemini (no download needed)\nAll other URLs → Downloaded via yt-dlp → uploaded to Gemini File API → poll until processed\nGemini analyzes video with structured prompt → returns JSON\nTemp files and Gemini uploads cleaned up automatically" }, { "title": "Supported Sources", "body": "Any URL supported by yt-dlp: Loom, YouTube, TikTok, Vimeo, Twitter/X, Instagram, Dailymotion, Twitch, and 1000+ more." }, { "title": "Tips", "body": "Use -q for targeted questions on top of the full analysis\nYouTube is fastest (no download step)\nLarge videos (10min+) work fine — Gemini File API supports up to 2GB (free) / 20GB (paid)\nThe script auto-installs Python dependencies via uv" } ], "body": "Video Understanding (Gemini)\n\nAnalyze videos using Google Gemini's multimodal video understanding. Supports 1000+ video sources via yt-dlp.\n\nRequirements\nyt-dlp — brew install yt-dlp / pip install yt-dlp\nffmpeg — brew install ffmpeg (for merging video+audio streams)\nGEMINI_API_KEY environment variable\nDefault Output\n\nReturns structured JSON:\n\ntranscript — Verbatim transcript with [MM:SS] timestamps\ndescription — Visual description (people, setting, UI, text on screen, flow)\nsummary — 2-3 sentence summary\nduration_seconds — Estimated duration\nspeakers — Identified speakers\nUsage\nAnalyze a video (structured JSON output)\nuv run {baseDir}/scripts/analyze_video.py \"\"\n\nAsk a question (adds \"answer\" field)\nuv run {baseDir}/scripts/analyze_video.py \"\" -q \"What product is shown?\"\n\nOverride prompt entirely\nuv run {baseDir}/scripts/analyze_video.py \"\" -p \"Custom prompt\" --raw\n\nDownload only (no analysis)\nuv run {baseDir}/scripts/analyze_video.py \"\" --download-only -o video.mp4\n\nOptions\nFlag\tDescription\tDefault\n-q / --question\tQuestion to answer (added to default fields)\tnone\n-p / --prompt\tOverride entire prompt (ignores -q)\tstructured JSON\n-m / --model\tGemini model\tgemini-2.5-flash\n-o / --output\tSave output to file\tstdout\n--keep\tKeep downloaded video file\tfalse\n--download-only\tDownload only, skip analysis\tfalse\n--max-size\tMax file size in MB\t500\n--raw\tRaw text output instead of JSON\tfalse\nHow It Works\nYouTube URLs → Passed directly to Gemini (no download needed)\nAll other URLs → Downloaded via yt-dlp → uploaded to Gemini File API → poll until processed\nGemini analyzes video with structured prompt → returns JSON\nTemp files and Gemini uploads cleaned up automatically\nSupported Sources\n\nAny URL supported by yt-dlp: Loom, YouTube, TikTok, Vimeo, Twitter/X, Instagram, Dailymotion, Twitch, and 1000+ more.\n\nTips\nUse -q for targeted questions on top of the full analysis\nYouTube is fastest (no download step)\nLarge videos (10min+) work fine — Gemini File API supports up to 2GB (free) / 20GB (paid)\nThe script auto-installs Python dependencies via uv" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/bill492/video-understanding", "publisherUrl": "https://clawhub.ai/bill492/video-understanding", "owner": "bill492", "version": "1.1.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/video-understanding", "downloadUrl": "https://openagent3.xyz/downloads/video-understanding", "agentUrl": "https://openagent3.xyz/skills/video-understanding/agent", "manifestUrl": "https://openagent3.xyz/skills/video-understanding/agent.json", "briefUrl": "https://openagent3.xyz/skills/video-understanding/agent.md" } }