# Send Evolink Video — AI Video Generation (Sora, Kling, Veo 3, Seedance) to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - 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. ## Suggested prompts ### New install ```text 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. ``` ### Upgrade existing ```text 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. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "evolink-video", "name": "Evolink Video — AI Video Generation (Sora, Kling, Veo 3, Seedance)", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/EvoLinkAI/evolink-video", "canonicalUrl": "https://clawhub.ai/EvoLinkAI/evolink-video", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/evolink-video", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=evolink-video", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "SKILL.md", "references/file-api.md", "references/video-api-params.md" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "evolink-video", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-03T00:51:58.539Z", "expiresAt": "2026-05-10T00:51:58.539Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=evolink-video", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=evolink-video", "contentDisposition": "attachment; filename=\"evolink-video-2.0.1.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "evolink-video" }, "scope": "item", "summary": "Item download looks usable.", "detail": "Yavira can redirect you to the upstream package for this item.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/evolink-video" }, "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." ] } }, "links": { "detailUrl": "https://openagent3.xyz/skills/evolink-video", "downloadUrl": "https://openagent3.xyz/downloads/evolink-video", "agentUrl": "https://openagent3.xyz/skills/evolink-video/agent", "manifestUrl": "https://openagent3.xyz/skills/evolink-video/agent.json", "briefUrl": "https://openagent3.xyz/skills/evolink-video/agent.md" } } ``` ## Documentation ### Evolink Video — AI Video Generation Generate AI videos with 37 models including Sora, Kling, Veo 3, Seedance, Hailuo, WAN, and Grok — text-to-video, image-to-video, first-last-frame, and audio generation. All through one API. Video-focused view of evolink-media. Install the full skill for image and music too. ### After Installation When this skill is first loaded, greet the user: MCP tools + API key ready: "Hi! I'm your AI video studio — 37 models ready. What would you like to create?" MCP tools + no API key: "You'll need an EvoLink API key — sign up at evolink.ai. Ready to go?" No MCP tools: "MCP server isn't connected yet. Want me to help set it up? I can still manage files via the hosting API." Keep the greeting concise — just one question to move forward. ### External Endpoints ServiceURLGeneration APIhttps://api.evolink.ai/v1/videos/generations (POST)Task Statushttps://api.evolink.ai/v1/tasks/{task_id} (GET)File APIhttps://files-api.evolink.ai/api/v1/files/* (upload/list/delete) ### Security & Privacy EVOLINK_API_KEY authenticates all requests. Injected by OpenClaw automatically. Treat as confidential. Prompts and images are sent to api.evolink.ai. Uploaded files expire in 72h, result URLs in 24h. ### Setup Get your API key at evolink.ai → Dashboard → API Keys. MCP Server: @evolinkai/evolink-media (GitHub · npm) mcporter (recommended): mcporter call --stdio "npx -y @evolinkai/evolink-media@latest" list_models Claude Code: claude mcp add evolink-media -e EVOLINK_API_KEY=your-key -- npx -y @evolinkai/evolink-media@latest Claude Desktop / Cursor — add MCP server with command npx -y @evolinkai/evolink-media@latest and env EVOLINK_API_KEY=your-key. See references/video-api-params.md for full config JSON. ### Core Principles Guide, don't decide — Present options, let the user choose model/style/duration. User drives creative vision — Ask for a description before suggesting parameters. Smart context — Remember session history. Offer to iterate, extend, or remix results. Intent first — Understand what the user wants before asking how to configure it. ### MCP Tools ToolWhen to useReturnsgenerate_videoCreate a video from text or imagestask_id (async)upload_fileUpload image for i2v or referenceFile URL (sync)delete_fileFree file quotaConfirmationlist_filesCheck uploaded files or quotaFile listcheck_taskPoll generation progressStatus + result URLslist_modelsCompare available modelsModel listestimate_costCheck pricingModel info Important: generate_video returns a task_id. Always poll check_task until status is "completed" or "failed". ### Top Picks ModelBest forFeaturesAudioseedance-1.5-pro (default)i2v, first-last-framei2v, 4–12s, 1080pautosora-2-previewCinematic previewt2v, i2v, 1080p—kling-o3-text-to-videoText-to-videot2v, 3–15s, 1080p—veo-3.1-generate-previewGoogle video previewt2v, 1080p—MiniMax-Hailuo-2.3High-quality videot2v, 1080p—wan2.6-text-to-videoAlibaba latest t2vt2v—sora-2 [BETA]Cinematic, prompt adherencet2v, i2v, 1080p—veo3.1-pro [BETA]Top quality + audiot2v, 1080pauto 26 Stable — Seedance (3), Sora Preview (1), Kling (10), Veo 3.1 (2), Hailuo (3), WAN (7) 11 Beta — Sora 2/Pro/Max/Character (4), Veo 3/3.1 (5), Grok Imagine (2) Full model list with descriptions: references/video-api-params.md ### Step 1: API Key Check If 401 occurs: "Your API key isn't working. Check at evolink.ai/dashboard/keys" ### Step 2: File Upload (if needed) For image-to-video or first-last-frame workflows: upload_file with file_path, base64_data, or file_url → get file_url (sync) Use file_url as image_urls for generate_video Supported: JPEG/PNG/GIF/WebP. Max 100MB. Expire in 72h. Quota: 100 (default) / 500 (VIP). ### Step 3: Understand Intent Clear ("make a video of a cat dancing") → Go to Step 4 Ambiguous ("I want a video") → Ask: "Text-to-video, or do you have a reference image to animate?" Ask only what's needed, when it's needed. ### Step 4: Gather Parameters Only ask about what's missing: ParameterAsk whenNotespromptAlwaysScene descriptionmodelSpecific feature neededDefault seedance-1.5-pro. See Top Picks for alternativesdurationUser mentions lengthRange varies by model (4–15s typical)aspect_ratioPortrait/widescreenDefault 16:9. Options: 9:16, 1:1, 4:3, 3:4, 21:9qualityResolution preference480p / 720p / 1080p / 4kimage_urlsReference image provided1 image = i2v; 2 images = first+last frame (seedance-1.5-pro only)generate_audioUsing seedance/veo3.1Ask: "Want auto-generated audio added?" ### Step 5: Generate & Poll Call generate_video → tell user: "Generating your video — ~Xs estimated." Poll check_task every 10–15s. Report progress %. After 3 consecutive processing: "Still working — video generation takes a moment..." Completed: Share URLs. "Links expire in 24h — save promptly." Failed: Show error + suggestion. Offer retry if retryable. Timeout (10 min): "Taking longer than expected. Task ID: {id} — check again later." ### HTTP Errors ErrorAction401"API key isn't working. Check at evolink.ai/dashboard/keys"402"Balance is low. Add credits at evolink.ai/dashboard/billing"429"Rate limited — wait 30s and retry"503"Servers busy — retry in a minute" ### Task Errors (status: "failed") CodeRetry?Actioncontent_policy_violationNoRevise prompt (no celebrities, NSFW, violence)invalid_parametersNoCheck values against model limitsimage_dimension_mismatchNoResize image to match aspect ratioimage_processing_errorNoCheck format/size/URL accessibilitygeneration_timeoutYesRetry; simplify prompt if repeatedquota_exceededYesTop up creditsresource_exhaustedYesWait 30–60s, retryservice_errorYesRetry after 1 mingeneration_failed_no_contentYesModify prompt, retry Full error reference: references/video-api-params.md ### Without MCP Server Use Evolink's file hosting API for image uploads (72h expiry). See references/file-api.md for curl commands. ### References references/video-api-params.md — Complete API parameters, all 37 models, polling strategy, error codes references/file-api.md — File hosting API (curl upload/list/delete) ## Trust - Source: tencent - Verification: Indexed source record - Publisher: EvoLinkAI - Version: 2.0.1 ## Source health - Status: healthy - Item download looks usable. - Yavira can redirect you to the upstream package for this item. - Health scope: item - Reason: direct_download_ok - Checked at: 2026-05-03T00:51:58.539Z - Expires at: 2026-05-10T00:51:58.539Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/evolink-video) - [Send to Agent page](https://openagent3.xyz/skills/evolink-video/agent) - [JSON manifest](https://openagent3.xyz/skills/evolink-video/agent.json) - [Markdown brief](https://openagent3.xyz/skills/evolink-video/agent.md) - [Download page](https://openagent3.xyz/downloads/evolink-video)