{
  "schemaVersion": "1.0",
  "item": {
    "slug": "ai-ugc",
    "name": "AI UGC",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/tfcbot/ai-ugc",
    "canonicalUrl": "https://clawhub.ai/tfcbot/ai-ugc",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/ai-ugc",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=ai-ugc",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "reference.md",
      "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/ai-ugc"
    },
    "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/ai-ugc",
    "agentPageUrl": "https://openagent3.xyz/skills/ai-ugc/agent",
    "manifestUrl": "https://openagent3.xyz/skills/ai-ugc/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/ai-ugc/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": "RawUGC API",
        "body": "Procedural knowledge for agents to call the RawUGC API. All requests require an API key from the RawUGC dashboard, passed via environment variable."
      },
      {
        "title": "Authentication",
        "body": "Environment variable: Read the API key from RAWUGC_API_KEY. The key is created in the RawUGC dashboard and must be kept secret; do not hardcode or log it.\nHeader: Send on every request: Authorization: Bearer <value of RAWUGC_API_KEY>.\nIf RAWUGC_API_KEY is missing or empty, inform the user they must set it and obtain a key from the RawUGC dashboard."
      },
      {
        "title": "Base URL",
        "body": "Production: https://rawugc.com/api/v1\nAll paths below are relative to this base."
      },
      {
        "title": "API Versioning",
        "body": "RawUGC uses date-based API versioning. The current latest version is 2026-03-06.\n\nRawUGC-Version request header: Override the version per-request (recommended).\nAPI key pinned version: Set when creating the key in the dashboard.\nFallback: Latest version (2026-03-06) if neither is set.\n\nAlways send RawUGC-Version: 2026-03-06 in requests to ensure consistent behavior."
      },
      {
        "title": "POST /videos/generate",
        "body": "Initiate video generation.\n\nRequest body (JSON):\n\nFieldTypeRequiredDescriptionmodelstringYessora-2-text-to-video, sora-2-image-to-video, kling-2.6/motion-control, veo3, veo3_fastpromptstringFor text-to-video / veo3Text description (1-5000 chars)imageUrlsstring[]For image-to-video / klingURLs, max 10. Veo3/veo3_fast accept up to 2 optional images.videoUrlsstring[]For klingURLs, max 1. Required for kling-2.6/motion-controlaspectRatiostringNoSora: portrait/landscape. Veo3: 16:9/9:16/AutonFramesstringNo\"10\" or \"15\" (Sora only)selectedCharacterstringNoCharacter username (e.g. rawugc.mia)characterOrientationstringNoimage or video (kling only)modestringNo720p or 1080p (kling only)\n\nResponse (201): videoId, model, status, creditsUsed, newBalance, estimatedCompletionTime, createdAt."
      },
      {
        "title": "GET /videos/:videoId",
        "body": "Get video status. Returns videoId, status, model, prompt, creditsUsed, url (when completed), createdAt, completedAt, failCode, failMessage, versions (edit history array)."
      },
      {
        "title": "GET /videos",
        "body": "List videos. Query: status, limit (1-100, default 50), page. Returns videos array + pagination."
      },
      {
        "title": "POST /videos/captions",
        "body": "Add styled captions to a completed video. Costs 1 credit.\n\nFieldTypeRequiredDescriptionvideoIdstringYesVideo identifier (vid_xxx)languagestringNoLanguage code (e.g. en). Defaults to auto-detect\n\nResponse (200): videoId, url, version, operation, creditsUsed."
      },
      {
        "title": "POST /videos/overlay",
        "body": "Add text overlay to a completed video.\n\nFieldTypeRequiredDescriptionvideoIdstringYesVideo identifier (vid_xxx)textstringYesOverlay text (1-500 chars)positionstringNotop, center, or bottomfontSizeintegerNo8-200 pixelstopBottomMarginintegerNo0-500 pixelsstrokeThicknessnumberNo0-10\n\nResponse (200): videoId, url, version, operation, creditsUsed."
      },
      {
        "title": "POST /images/generate",
        "body": "Generate AI images using Nano Banana models. Async -- poll GET /images/:imageId.\n\nFieldTypeRequiredDescriptionmodelstringYesnano-banana-2 (text-to-image, 4 credits) or google/nano-banana-edit (image editing, 2 credits)promptstringYesText description or edit instruction (1-20000 chars)imageUrlsstring[]For editingSource images. Required for google/nano-banana-edit. Optional for nano-banana-2 (reference images, max 14).aspectRatiostringNoFor nano-banana-2: 1:1, 16:9, 9:16, auto, etc.imageSizestringNoFor google/nano-banana-edit: 1:1, 16:9, 9:16, auto, etc.resolutionstringNoFor nano-banana-2: 1K, 2K, 4KoutputFormatstringNopng, jpeg, jpggoogleSearchbooleanNoUse Google Web Search grounding (nano-banana-2 only)\n\nResponse (201): imageId, model, status, creditsUsed, newBalance, estimatedCompletionTime, createdAt."
      },
      {
        "title": "GET /images/:imageId",
        "body": "Get image status. Returns imageId, status, model, prompt, url (when completed), imageSize, resolution, outputFormat, creditsUsed, createdAt, completedAt, failCode, failMessage."
      },
      {
        "title": "GET /images",
        "body": "List images. Query: status, limit (1-100, default 20), page. Returns images array + pagination."
      },
      {
        "title": "POST /music/generate",
        "body": "Generate AI music using Suno models. 3 credits per generation. Async -- poll GET /music/:musicId.\n\nFieldTypeRequiredDescriptionpromptstringYesMusic description (1-2000 chars)modelstringNoV3_5, V4, V4_5, V4_5PLUS, V4_5ALL, V5 (default: V5)instrumentalbooleanNoInstrumental only, no vocals (default: true)titlestringNoTrack title (max 200 chars). Enables custom mode with style.stylestringNoStyle descriptor (max 500 chars, e.g. lo-fi hip hop)\n\nResponse (201): musicId, model, status, creditsUsed, newBalance, estimatedCompletionTime, createdAt."
      },
      {
        "title": "GET /music/:musicId",
        "body": "Get music status. Returns musicId, status, model, prompt, audioUrl (when completed), albumArtUrl, duration, title, creditsUsed, createdAt, completedAt, failCode, failMessage."
      },
      {
        "title": "GET /music",
        "body": "List music tracks. Query: status, limit (1-100, default 20), page. Returns tracks array + pagination."
      },
      {
        "title": "POST /upload",
        "body": "Upload a video or image file. Returns a URL for use in generation requests (imageUrls, videoUrls) or analyze-video. Max 100MB.\n\nRequest: multipart/form-data with file field. Accepted types: video/mp4, video/quicktime, video/webm, image/png, image/jpeg, image/webp.\n\nResponse (200): url, contentType, size."
      },
      {
        "title": "GET /characters",
        "body": "List all available AI characters (built-in + custom). Returns characters array, count, adminCount, userCount."
      },
      {
        "title": "GET /characters/:characterId",
        "body": "Get a character by ID. Returns _id, username, displayName, description, videoPreviewUrl, type (admin/user), isActive, createdAt, updatedAt."
      },
      {
        "title": "Personas (CRUD)",
        "body": "Personas define target audiences for content plan generation.\n\nGET /personas -- List all. Returns personas array + count.\nPOST /personas -- Create. Body: name (required, max 200), description (required, max 5000). Returns id.\nGET /personas/:personaId -- Get one.\nPATCH /personas/:personaId -- Update. Body: name, description (both optional).\nDELETE /personas/:personaId -- Delete.\n\nPersonaResponse: _id, organizationId, name, description, createdAt, updatedAt."
      },
      {
        "title": "Messaging (CRUD)",
        "body": "Brand/positioning messaging templates.\n\nGET /messaging -- List all. Returns messages array + count.\nPOST /messaging -- Create. Body: name (required, max 200), body (required, max 5000). Returns id.\nGET /messaging/:messageId -- Get one.\nPATCH /messaging/:messageId -- Update. Body: name, body (both optional).\nDELETE /messaging/:messageId -- Delete.\n\nMessagingResponse: _id, organizationId, name, body, createdAt, updatedAt."
      },
      {
        "title": "Products (CRUD)",
        "body": "Products for video generation.\n\nGET /products -- List all. Returns products array + count.\nPOST /products -- Create. Body: name (required, max 200), photos (required, URL array), description (max 1000), messaging (max 5000). Returns id.\nGET /products/:productId -- Get one.\nPATCH /products/:productId -- Update. Body: name, description, photos, messaging (all optional).\nDELETE /products/:productId -- Delete.\n\nProductResponse: _id, name, description, photos, messaging, createdAt, updatedAt."
      },
      {
        "title": "Styles (CRUD)",
        "body": "Video/image creative styles with optional prompt templates.\n\nGET /styles -- List all (built-in + custom). Query: type (video/image). Returns styles array + count.\nPOST /styles -- Create. Body: name (required, max 200), description (max 1000), type (video/image), aspectRatio (portrait/landscape/square), promptTemplate (max 5000, supports {productName}, {messaging}, {character} placeholders). Returns id.\nGET /styles/:styleId -- Get one.\nPATCH /styles/:styleId -- Update. All fields optional.\nDELETE /styles/:styleId -- Delete.\n\nStyleResponse: _id, name, description, type, aspectRatio, styleId, promptTemplate, isAdmin, isStandard."
      },
      {
        "title": "GET /social/accounts",
        "body": "List connected social accounts (max 3 per org). Returns accounts array + count. Each account: accountId, platform (tiktok/instagram/youtube), username, displayName, profilePicture, isActive."
      },
      {
        "title": "POST /social/accounts",
        "body": "Sync connected accounts from the scheduling provider. Returns { success: boolean }."
      },
      {
        "title": "DELETE /social/accounts/:accountId",
        "body": "Disconnect a social account. Returns { success: boolean }."
      },
      {
        "title": "POST /social/posts",
        "body": "Schedule, draft, or immediately publish a video to social media.\n\nFieldTypeRequiredDescriptionvideoUrlstringYesURL of video to postaccountIdsstring[]YesTarget account IDsmodestringYesschedule, draft, or nowscheduledForintegerFor scheduleUnix timestamp (ms)timezonestringNoIANA timezone (default: UTC)contentstringNoCaption (max 2200 chars)videoIdstringNoRawUGC video ID to linkpublishToInboxbooleanNoSend to TikTok Creator InboxtiktokPrivacyLevelstringNoSELF_ONLY, PUBLIC_TO_EVERYONE, MUTUAL_FOLLOW_FRIENDS, FOLLOWER_OF_CREATORtiktokAllowCommentbooleanNoAllow TikTok commentstiktokAllowDuetbooleanNoAllow TikTok duetstiktokAllowStitchbooleanNoAllow TikTok stitchestiktokCommercialContentTypestringNonone, brand_organic, brand_content\n\nResponse (201): SocialPost object."
      },
      {
        "title": "GET /social/posts",
        "body": "List posts. Query: fromDate (ms), toDate (ms), includeDrafts (boolean). Returns posts array + count."
      },
      {
        "title": "GET /social/posts/:postId",
        "body": "Get a post."
      },
      {
        "title": "PATCH /social/posts/:postId",
        "body": "Update a post. Body: content, scheduledFor, timezone, accountIds (at least one field required)."
      },
      {
        "title": "DELETE /social/posts/:postId",
        "body": "Delete a post. Returns { success: boolean }."
      },
      {
        "title": "POST /social/posts/:postId/reschedule",
        "body": "Reschedule a post. Body: scheduledFor (required, ms), timezone."
      },
      {
        "title": "POST /social/posts/:postId/publish",
        "body": "Immediately publish a draft post.\n\nSocialPost: postId, platforms, status (draft/scheduled/published/failed), scheduledFor, timezone, content, videoUrl, createdAt, publishedAt."
      },
      {
        "title": "GET /viral-library/videos/:videoId",
        "body": "Get a viral library video with full AI analysis (hooks, keyframes, performance insights). Returns ViralLibraryVideo."
      },
      {
        "title": "GET /viral-library/search",
        "body": "Semantic search across analyzed videos. Query: q (required, natural language), limit (1-50, default 20). Returns results (array of { video, score }), query, total."
      },
      {
        "title": "POST /scrape-tiktok",
        "body": "Scrape TikTok videos. Costs 3 credits.\n\nFieldTypeRequiredDescriptionquerystringYesSearch keyword, hashtag, or query (max 500)modestringNokeyword, hashtag, search (default: keyword)limitintegerNo1-10 (default: 10)\n\nResponse (200): scrapeId (use with content-plans), count, videos (array with id, url, author, description, stats, duration, hashtags, thumbnail, videoUrl)."
      },
      {
        "title": "POST /content-plans",
        "body": "Generate a content plan from scraped videos. Costs 3 credits.\n\nFieldTypeRequiredDescriptionscrapeIdstringYesFrom scrape-tiktok responsebriefstringYesContent plan goals (max 5000)\n\nResponse (200): planId, scrapeId, brief, topWins, gapsToTest, blueprints (array with category, strategy, evidence, contentIdeas)."
      },
      {
        "title": "GET /content-plans",
        "body": "List all content plans. Returns plans array + count."
      },
      {
        "title": "POST /analyze-video",
        "body": "Analyze any video URL (social links or direct URLs). Costs 1 credit. Max 150MB.\n\nFieldTypeRequiredDescriptionvideoUrlstringYesVideo URL to analyzepromptstringNoCustom analysis prompt (max 5000)\n\nResponse (200): summary, hook, keyframes (array with timestamp, type, description, visual, audio, text), durationSeconds, tags, whyItPerformed, attributesToCopy, hooksToTest."
      },
      {
        "title": "Errors",
        "body": "All error responses use RFC 7807 Problem Details (JSON): type, title, status, detail, instance, errors.\n\nStatusMeaning400Validation error. Surface detail and errors to user.401Auth error. Check RAWUGC_API_KEY.402Insufficient credits. Add credits in dashboard.403Insufficient scope. API key lacks permissions.404Resource not found.429Rate limit exceeded. Check X-RateLimit-Reset header.500Server error. Retry or contact support."
      },
      {
        "title": "Rate Limits",
        "body": "API Key: 10 req/min. Session: 20 req/min.\nHeaders: X-RateLimit-Limit, X-RateLimit-Remaining, X-RateLimit-Reset (unix timestamp)."
      },
      {
        "title": "Workflow: Generate then poll",
        "body": "Generate: POST to the generation endpoint. Note the returned ID (videoId/imageId/musicId).\nPoll: GET the status endpoint periodically (10-30s). Use exponential backoff.\nFinish: When status === 'completed', use the result URL. When failed, surface error to user.\nEdit (video only): POST to /videos/captions or /videos/overlay.\n\nFor full request/response shapes, see reference.md."
      }
    ],
    "body": "RawUGC API\n\nProcedural knowledge for agents to call the RawUGC API. All requests require an API key from the RawUGC dashboard, passed via environment variable.\n\nAuthentication\nEnvironment variable: Read the API key from RAWUGC_API_KEY. The key is created in the RawUGC dashboard and must be kept secret; do not hardcode or log it.\nHeader: Send on every request: Authorization: Bearer <value of RAWUGC_API_KEY>.\nIf RAWUGC_API_KEY is missing or empty, inform the user they must set it and obtain a key from the RawUGC dashboard.\nBase URL\nProduction: https://rawugc.com/api/v1\nAll paths below are relative to this base.\nAPI Versioning\n\nRawUGC uses date-based API versioning. The current latest version is 2026-03-06.\n\nRawUGC-Version request header: Override the version per-request (recommended).\nAPI key pinned version: Set when creating the key in the dashboard.\nFallback: Latest version (2026-03-06) if neither is set.\n\nAlways send RawUGC-Version: 2026-03-06 in requests to ensure consistent behavior.\n\nVideo Generation\nPOST /videos/generate\n\nInitiate video generation.\n\nRequest body (JSON):\n\nField\tType\tRequired\tDescription\nmodel\tstring\tYes\tsora-2-text-to-video, sora-2-image-to-video, kling-2.6/motion-control, veo3, veo3_fast\nprompt\tstring\tFor text-to-video / veo3\tText description (1-5000 chars)\nimageUrls\tstring[]\tFor image-to-video / kling\tURLs, max 10. Veo3/veo3_fast accept up to 2 optional images.\nvideoUrls\tstring[]\tFor kling\tURLs, max 1. Required for kling-2.6/motion-control\naspectRatio\tstring\tNo\tSora: portrait/landscape. Veo3: 16:9/9:16/Auto\nnFrames\tstring\tNo\t\"10\" or \"15\" (Sora only)\nselectedCharacter\tstring\tNo\tCharacter username (e.g. rawugc.mia)\ncharacterOrientation\tstring\tNo\timage or video (kling only)\nmode\tstring\tNo\t720p or 1080p (kling only)\n\nResponse (201): videoId, model, status, creditsUsed, newBalance, estimatedCompletionTime, createdAt.\n\nGET /videos/:videoId\n\nGet video status. Returns videoId, status, model, prompt, creditsUsed, url (when completed), createdAt, completedAt, failCode, failMessage, versions (edit history array).\n\nGET /videos\n\nList videos. Query: status, limit (1-100, default 50), page. Returns videos array + pagination.\n\nPOST /videos/captions\n\nAdd styled captions to a completed video. Costs 1 credit.\n\nField\tType\tRequired\tDescription\nvideoId\tstring\tYes\tVideo identifier (vid_xxx)\nlanguage\tstring\tNo\tLanguage code (e.g. en). Defaults to auto-detect\n\nResponse (200): videoId, url, version, operation, creditsUsed.\n\nPOST /videos/overlay\n\nAdd text overlay to a completed video.\n\nField\tType\tRequired\tDescription\nvideoId\tstring\tYes\tVideo identifier (vid_xxx)\ntext\tstring\tYes\tOverlay text (1-500 chars)\nposition\tstring\tNo\ttop, center, or bottom\nfontSize\tinteger\tNo\t8-200 pixels\ntopBottomMargin\tinteger\tNo\t0-500 pixels\nstrokeThickness\tnumber\tNo\t0-10\n\nResponse (200): videoId, url, version, operation, creditsUsed.\n\nImage Generation\nPOST /images/generate\n\nGenerate AI images using Nano Banana models. Async -- poll GET /images/:imageId.\n\nField\tType\tRequired\tDescription\nmodel\tstring\tYes\tnano-banana-2 (text-to-image, 4 credits) or google/nano-banana-edit (image editing, 2 credits)\nprompt\tstring\tYes\tText description or edit instruction (1-20000 chars)\nimageUrls\tstring[]\tFor editing\tSource images. Required for google/nano-banana-edit. Optional for nano-banana-2 (reference images, max 14).\naspectRatio\tstring\tNo\tFor nano-banana-2: 1:1, 16:9, 9:16, auto, etc.\nimageSize\tstring\tNo\tFor google/nano-banana-edit: 1:1, 16:9, 9:16, auto, etc.\nresolution\tstring\tNo\tFor nano-banana-2: 1K, 2K, 4K\noutputFormat\tstring\tNo\tpng, jpeg, jpg\ngoogleSearch\tboolean\tNo\tUse Google Web Search grounding (nano-banana-2 only)\n\nResponse (201): imageId, model, status, creditsUsed, newBalance, estimatedCompletionTime, createdAt.\n\nGET /images/:imageId\n\nGet image status. Returns imageId, status, model, prompt, url (when completed), imageSize, resolution, outputFormat, creditsUsed, createdAt, completedAt, failCode, failMessage.\n\nGET /images\n\nList images. Query: status, limit (1-100, default 20), page. Returns images array + pagination.\n\nMusic Generation\nPOST /music/generate\n\nGenerate AI music using Suno models. 3 credits per generation. Async -- poll GET /music/:musicId.\n\nField\tType\tRequired\tDescription\nprompt\tstring\tYes\tMusic description (1-2000 chars)\nmodel\tstring\tNo\tV3_5, V4, V4_5, V4_5PLUS, V4_5ALL, V5 (default: V5)\ninstrumental\tboolean\tNo\tInstrumental only, no vocals (default: true)\ntitle\tstring\tNo\tTrack title (max 200 chars). Enables custom mode with style.\nstyle\tstring\tNo\tStyle descriptor (max 500 chars, e.g. lo-fi hip hop)\n\nResponse (201): musicId, model, status, creditsUsed, newBalance, estimatedCompletionTime, createdAt.\n\nGET /music/:musicId\n\nGet music status. Returns musicId, status, model, prompt, audioUrl (when completed), albumArtUrl, duration, title, creditsUsed, createdAt, completedAt, failCode, failMessage.\n\nGET /music\n\nList music tracks. Query: status, limit (1-100, default 20), page. Returns tracks array + pagination.\n\nUpload\nPOST /upload\n\nUpload a video or image file. Returns a URL for use in generation requests (imageUrls, videoUrls) or analyze-video. Max 100MB.\n\nRequest: multipart/form-data with file field. Accepted types: video/mp4, video/quicktime, video/webm, image/png, image/jpeg, image/webp.\n\nResponse (200): url, contentType, size.\n\nCharacters\nGET /characters\n\nList all available AI characters (built-in + custom). Returns characters array, count, adminCount, userCount.\n\nGET /characters/:characterId\n\nGet a character by ID. Returns _id, username, displayName, description, videoPreviewUrl, type (admin/user), isActive, createdAt, updatedAt.\n\nPersonas (CRUD)\n\nPersonas define target audiences for content plan generation.\n\nGET /personas -- List all. Returns personas array + count.\nPOST /personas -- Create. Body: name (required, max 200), description (required, max 5000). Returns id.\nGET /personas/:personaId -- Get one.\nPATCH /personas/:personaId -- Update. Body: name, description (both optional).\nDELETE /personas/:personaId -- Delete.\n\nPersonaResponse: _id, organizationId, name, description, createdAt, updatedAt.\n\nMessaging (CRUD)\n\nBrand/positioning messaging templates.\n\nGET /messaging -- List all. Returns messages array + count.\nPOST /messaging -- Create. Body: name (required, max 200), body (required, max 5000). Returns id.\nGET /messaging/:messageId -- Get one.\nPATCH /messaging/:messageId -- Update. Body: name, body (both optional).\nDELETE /messaging/:messageId -- Delete.\n\nMessagingResponse: _id, organizationId, name, body, createdAt, updatedAt.\n\nProducts (CRUD)\n\nProducts for video generation.\n\nGET /products -- List all. Returns products array + count.\nPOST /products -- Create. Body: name (required, max 200), photos (required, URL array), description (max 1000), messaging (max 5000). Returns id.\nGET /products/:productId -- Get one.\nPATCH /products/:productId -- Update. Body: name, description, photos, messaging (all optional).\nDELETE /products/:productId -- Delete.\n\nProductResponse: _id, name, description, photos, messaging, createdAt, updatedAt.\n\nStyles (CRUD)\n\nVideo/image creative styles with optional prompt templates.\n\nGET /styles -- List all (built-in + custom). Query: type (video/image). Returns styles array + count.\nPOST /styles -- Create. Body: name (required, max 200), description (max 1000), type (video/image), aspectRatio (portrait/landscape/square), promptTemplate (max 5000, supports {productName}, {messaging}, {character} placeholders). Returns id.\nGET /styles/:styleId -- Get one.\nPATCH /styles/:styleId -- Update. All fields optional.\nDELETE /styles/:styleId -- Delete.\n\nStyleResponse: _id, name, description, type, aspectRatio, styleId, promptTemplate, isAdmin, isStandard.\n\nSocial Scheduling\nGET /social/accounts\n\nList connected social accounts (max 3 per org). Returns accounts array + count. Each account: accountId, platform (tiktok/instagram/youtube), username, displayName, profilePicture, isActive.\n\nPOST /social/accounts\n\nSync connected accounts from the scheduling provider. Returns { success: boolean }.\n\nDELETE /social/accounts/:accountId\n\nDisconnect a social account. Returns { success: boolean }.\n\nPOST /social/posts\n\nSchedule, draft, or immediately publish a video to social media.\n\nField\tType\tRequired\tDescription\nvideoUrl\tstring\tYes\tURL of video to post\naccountIds\tstring[]\tYes\tTarget account IDs\nmode\tstring\tYes\tschedule, draft, or now\nscheduledFor\tinteger\tFor schedule\tUnix timestamp (ms)\ntimezone\tstring\tNo\tIANA timezone (default: UTC)\ncontent\tstring\tNo\tCaption (max 2200 chars)\nvideoId\tstring\tNo\tRawUGC video ID to link\npublishToInbox\tboolean\tNo\tSend to TikTok Creator Inbox\ntiktokPrivacyLevel\tstring\tNo\tSELF_ONLY, PUBLIC_TO_EVERYONE, MUTUAL_FOLLOW_FRIENDS, FOLLOWER_OF_CREATOR\ntiktokAllowComment\tboolean\tNo\tAllow TikTok comments\ntiktokAllowDuet\tboolean\tNo\tAllow TikTok duets\ntiktokAllowStitch\tboolean\tNo\tAllow TikTok stitches\ntiktokCommercialContentType\tstring\tNo\tnone, brand_organic, brand_content\n\nResponse (201): SocialPost object.\n\nGET /social/posts\n\nList posts. Query: fromDate (ms), toDate (ms), includeDrafts (boolean). Returns posts array + count.\n\nGET /social/posts/:postId\n\nGet a post.\n\nPATCH /social/posts/:postId\n\nUpdate a post. Body: content, scheduledFor, timezone, accountIds (at least one field required).\n\nDELETE /social/posts/:postId\n\nDelete a post. Returns { success: boolean }.\n\nPOST /social/posts/:postId/reschedule\n\nReschedule a post. Body: scheduledFor (required, ms), timezone.\n\nPOST /social/posts/:postId/publish\n\nImmediately publish a draft post.\n\nSocialPost: postId, platforms, status (draft/scheduled/published/failed), scheduledFor, timezone, content, videoUrl, createdAt, publishedAt.\n\nViral Library\nGET /viral-library/videos/:videoId\n\nGet a viral library video with full AI analysis (hooks, keyframes, performance insights). Returns ViralLibraryVideo.\n\nGET /viral-library/search\n\nSemantic search across analyzed videos. Query: q (required, natural language), limit (1-50, default 20). Returns results (array of { video, score }), query, total.\n\nResearch\nPOST /scrape-tiktok\n\nScrape TikTok videos. Costs 3 credits.\n\nField\tType\tRequired\tDescription\nquery\tstring\tYes\tSearch keyword, hashtag, or query (max 500)\nmode\tstring\tNo\tkeyword, hashtag, search (default: keyword)\nlimit\tinteger\tNo\t1-10 (default: 10)\n\nResponse (200): scrapeId (use with content-plans), count, videos (array with id, url, author, description, stats, duration, hashtags, thumbnail, videoUrl).\n\nPOST /content-plans\n\nGenerate a content plan from scraped videos. Costs 3 credits.\n\nField\tType\tRequired\tDescription\nscrapeId\tstring\tYes\tFrom scrape-tiktok response\nbrief\tstring\tYes\tContent plan goals (max 5000)\n\nResponse (200): planId, scrapeId, brief, topWins, gapsToTest, blueprints (array with category, strategy, evidence, contentIdeas).\n\nGET /content-plans\n\nList all content plans. Returns plans array + count.\n\nPOST /analyze-video\n\nAnalyze any video URL (social links or direct URLs). Costs 1 credit. Max 150MB.\n\nField\tType\tRequired\tDescription\nvideoUrl\tstring\tYes\tVideo URL to analyze\nprompt\tstring\tNo\tCustom analysis prompt (max 5000)\n\nResponse (200): summary, hook, keyframes (array with timestamp, type, description, visual, audio, text), durationSeconds, tags, whyItPerformed, attributesToCopy, hooksToTest.\n\nErrors\n\nAll error responses use RFC 7807 Problem Details (JSON): type, title, status, detail, instance, errors.\n\nStatus\tMeaning\n400\tValidation error. Surface detail and errors to user.\n401\tAuth error. Check RAWUGC_API_KEY.\n402\tInsufficient credits. Add credits in dashboard.\n403\tInsufficient scope. API key lacks permissions.\n404\tResource not found.\n429\tRate limit exceeded. Check X-RateLimit-Reset header.\n500\tServer error. Retry or contact support.\nRate Limits\nAPI Key: 10 req/min. Session: 20 req/min.\nHeaders: X-RateLimit-Limit, X-RateLimit-Remaining, X-RateLimit-Reset (unix timestamp).\nWorkflow: Generate then poll\nGenerate: POST to the generation endpoint. Note the returned ID (videoId/imageId/musicId).\nPoll: GET the status endpoint periodically (10-30s). Use exponential backoff.\nFinish: When status === 'completed', use the result URL. When failed, surface error to user.\nEdit (video only): POST to /videos/captions or /videos/overlay.\n\nFor full request/response shapes, see reference.md."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/tfcbot/ai-ugc",
    "publisherUrl": "https://clawhub.ai/tfcbot/ai-ugc",
    "owner": "tfcbot",
    "version": "0.0.4",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/ai-ugc",
    "downloadUrl": "https://openagent3.xyz/downloads/ai-ugc",
    "agentUrl": "https://openagent3.xyz/skills/ai-ugc/agent",
    "manifestUrl": "https://openagent3.xyz/skills/ai-ugc/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/ai-ugc/agent.md"
  }
}