{ "schemaVersion": "1.0", "item": { "slug": "video-agent", "name": "Video Agent", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/michaelwang11394/video-agent", "canonicalUrl": "https://clawhub.ai/michaelwang11394/video-agent", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/video-agent", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=video-agent", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "references/assets.md", "references/authentication.md", "references/avatars.md", "references/backgrounds.md", "references/captions.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": "2026-05-07T17:22:31.273Z", "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/video-agent" }, "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-agent", "agentPageUrl": "https://openagent3.xyz/skills/video-agent/agent", "manifestUrl": "https://openagent3.xyz/skills/video-agent/agent.json", "briefUrl": "https://openagent3.xyz/skills/video-agent/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": "HeyGen API (Deprecated)", "body": "This skill is deprecated. Use the focused skills instead:\n\ncreate-video — Generate videos from a text prompt (Video Agent API)\navatar-video — Build videos with specific avatars, voices, scripts, and scenes (v2 API)\n\nThis skill remains for backward compatibility but will be removed in a future release.\n\nAI avatar video creation API for generating talking-head videos, explainers, and presentations." }, { "title": "Tool Selection", "body": "If HeyGen MCP tools are available (mcp__heygen__*), prefer them over direct HTTP API calls — they handle authentication and request formatting automatically.\n\nTaskMCP ToolFallback (Direct API)Generate video from promptmcp__heygen__generate_video_agentPOST /v1/video_agent/generateCheck video status / get URLmcp__heygen__get_videoGET /v2/videos/{video_id}List account videosmcp__heygen__list_videosGET /v2/videosDelete a videomcp__heygen__delete_videoDELETE /v2/videos/{video_id}\n\nIf no HeyGen MCP tools are available, use direct HTTP API calls with X-Api-Key: $HEYGEN_API_KEY header as documented in the reference files." }, { "title": "Default Workflow", "body": "Prefer Video Agent for most video requests.\nAlways use prompt-optimizer.md guidelines to structure prompts with scenes, timing, and visual styles.\n\nWith MCP tools:\n\nWrite an optimized prompt using prompt-optimizer.md → visual-styles.md\nCall mcp__heygen__generate_video_agent with prompt and config (duration_sec, orientation, avatar_id)\nCall mcp__heygen__get_video with the returned video_id to poll status and get the download URL\n\nWithout MCP tools (direct API):\n\nWrite an optimized prompt using prompt-optimizer.md → visual-styles.md\nPOST /v1/video_agent/generate — see video-agent.md\nGET /v2/videos/ — see video-status.md\n\nOnly use v2/video/generate when user explicitly needs:\n\nExact script without AI modification\nSpecific voice_id selection\nDifferent avatars/backgrounds per scene\nPrecise per-scene timing control\nProgrammatic/batch generation with exact specs" }, { "title": "Quick Reference", "body": "TaskMCP ToolReadGenerate video from prompt (easy)mcp__heygen__generate_video_agentprompt-optimizer.md → visual-styles.md → video-agent.mdGenerate video with precise control—video-generation.md, avatars.md, voices.mdCheck video status / get download URLmcp__heygen__get_videovideo-status.mdAdd captions or text overlays—captions.md, text-overlays.mdTransparent video for compositing—video-generation.md (WebM section)Use with Remotion—remotion-integration.md" }, { "title": "Foundation", "body": "references/authentication.md - API key setup and X-Api-Key header\nreferences/quota.md - Credit system and usage limits\nreferences/video-status.md - Polling patterns and download URLs\nreferences/assets.md - Uploading images, videos, audio" }, { "title": "Core Video Creation", "body": "references/avatars.md - Listing avatars, styles, avatar_id selection\nreferences/voices.md - Listing voices, locales, speed/pitch\nreferences/scripts.md - Writing scripts, pauses, pacing\nreferences/video-generation.md - POST /v2/video/generate and multi-scene videos\nreferences/video-agent.md - One-shot prompt video generation\nreferences/prompt-optimizer.md - Writing effective Video Agent prompts (core workflow + rules)\nreferences/visual-styles.md - 20 named visual styles with full specs\nreferences/prompt-examples.md - Full production prompt example + ready-to-use templates\nreferences/dimensions.md - Resolution and aspect ratios" }, { "title": "Video Customization", "body": "references/backgrounds.md - Solid colors, images, video backgrounds\nreferences/text-overlays.md - Adding text with fonts and positioning\nreferences/captions.md - Auto-generated captions and subtitles" }, { "title": "Advanced Features", "body": "references/templates.md - Template listing and variable replacement\nreferences/photo-avatars.md - Creating avatars from photos\nreferences/webhooks.md - Webhook endpoints and events" }, { "title": "Integration", "body": "references/remotion-integration.md - Using HeyGen in Remotion compositions" } ], "body": "HeyGen API (Deprecated)\n\nThis skill is deprecated. Use the focused skills instead:\n\ncreate-video — Generate videos from a text prompt (Video Agent API)\navatar-video — Build videos with specific avatars, voices, scripts, and scenes (v2 API)\n\nThis skill remains for backward compatibility but will be removed in a future release.\n\nAI avatar video creation API for generating talking-head videos, explainers, and presentations.\n\nTool Selection\n\nIf HeyGen MCP tools are available (mcp__heygen__*), prefer them over direct HTTP API calls — they handle authentication and request formatting automatically.\n\nTask\tMCP Tool\tFallback (Direct API)\nGenerate video from prompt\tmcp__heygen__generate_video_agent\tPOST /v1/video_agent/generate\nCheck video status / get URL\tmcp__heygen__get_video\tGET /v2/videos/{video_id}\nList account videos\tmcp__heygen__list_videos\tGET /v2/videos\nDelete a video\tmcp__heygen__delete_video\tDELETE /v2/videos/{video_id}\n\nIf no HeyGen MCP tools are available, use direct HTTP API calls with X-Api-Key: $HEYGEN_API_KEY header as documented in the reference files.\n\nDefault Workflow\n\nPrefer Video Agent for most video requests. Always use prompt-optimizer.md guidelines to structure prompts with scenes, timing, and visual styles.\n\nWith MCP tools:\n\nWrite an optimized prompt using prompt-optimizer.md → visual-styles.md\nCall mcp__heygen__generate_video_agent with prompt and config (duration_sec, orientation, avatar_id)\nCall mcp__heygen__get_video with the returned video_id to poll status and get the download URL\n\nWithout MCP tools (direct API):\n\nWrite an optimized prompt using prompt-optimizer.md → visual-styles.md\nPOST /v1/video_agent/generate — see video-agent.md\nGET /v2/videos/ — see video-status.md\n\nOnly use v2/video/generate when user explicitly needs:\n\nExact script without AI modification\nSpecific voice_id selection\nDifferent avatars/backgrounds per scene\nPrecise per-scene timing control\nProgrammatic/batch generation with exact specs\nQuick Reference\nTask\tMCP Tool\tRead\nGenerate video from prompt (easy)\tmcp__heygen__generate_video_agent\tprompt-optimizer.md → visual-styles.md → video-agent.md\nGenerate video with precise control\t—\tvideo-generation.md, avatars.md, voices.md\nCheck video status / get download URL\tmcp__heygen__get_video\tvideo-status.md\nAdd captions or text overlays\t—\tcaptions.md, text-overlays.md\nTransparent video for compositing\t—\tvideo-generation.md (WebM section)\nUse with Remotion\t—\tremotion-integration.md\nReference Files\nFoundation\nreferences/authentication.md - API key setup and X-Api-Key header\nreferences/quota.md - Credit system and usage limits\nreferences/video-status.md - Polling patterns and download URLs\nreferences/assets.md - Uploading images, videos, audio\nCore Video Creation\nreferences/avatars.md - Listing avatars, styles, avatar_id selection\nreferences/voices.md - Listing voices, locales, speed/pitch\nreferences/scripts.md - Writing scripts, pauses, pacing\nreferences/video-generation.md - POST /v2/video/generate and multi-scene videos\nreferences/video-agent.md - One-shot prompt video generation\nreferences/prompt-optimizer.md - Writing effective Video Agent prompts (core workflow + rules)\nreferences/visual-styles.md - 20 named visual styles with full specs\nreferences/prompt-examples.md - Full production prompt example + ready-to-use templates\nreferences/dimensions.md - Resolution and aspect ratios\nVideo Customization\nreferences/backgrounds.md - Solid colors, images, video backgrounds\nreferences/text-overlays.md - Adding text with fonts and positioning\nreferences/captions.md - Auto-generated captions and subtitles\nAdvanced Features\nreferences/templates.md - Template listing and variable replacement\nreferences/photo-avatars.md - Creating avatars from photos\nreferences/webhooks.md - Webhook endpoints and events\nIntegration\nreferences/remotion-integration.md - Using HeyGen in Remotion compositions" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/michaelwang11394/video-agent", "publisherUrl": "https://clawhub.ai/michaelwang11394/video-agent", "owner": "michaelwang11394", "version": "2.21.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/video-agent", "downloadUrl": "https://openagent3.xyz/downloads/video-agent", "agentUrl": "https://openagent3.xyz/skills/video-agent/agent", "manifestUrl": "https://openagent3.xyz/skills/video-agent/agent.json", "briefUrl": "https://openagent3.xyz/skills/video-agent/agent.md" } }