{ "schemaVersion": "1.0", "item": { "slug": "seedance-2-video-gen", "name": "Seedance 2 Video Generation", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/EvoLinkAI/seedance-2-video-gen", "canonicalUrl": "https://clawhub.ai/EvoLinkAI/seedance-2-video-gen", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/seedance-2-video-gen", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=seedance-2-video-gen", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "_meta.json", "references/api-params.md", "scripts/seedance-gen.sh" ], "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/seedance-2-video-gen" }, "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/seedance-2-video-gen", "agentPageUrl": "https://openagent3.xyz/skills/seedance-2-video-gen/agent", "manifestUrl": "https://openagent3.xyz/skills/seedance-2-video-gen/agent.json", "briefUrl": "https://openagent3.xyz/skills/seedance-2-video-gen/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": "Seedance Video Generation", "body": "An interactive AI video generation assistant powered by the Seedance model via EvoLink API." }, { "title": "After Installation", "body": "When this skill is first loaded, proactively greet the user and start the setup:\n\nCheck if EVOLINK_API_KEY is set\n\nIf not set: \"To generate videos, you'll need an EvoLink API key. It takes 30 seconds to get one — just sign up at evolink.ai. Want me to walk you through it?\"\nIf already set: \"You're all set! What kind of video would you like to create?\"\n\n\n\nThat's it. One question. The user is now in the flow.\n\nDo NOT list features, show a menu, or dump instructions. Just ask one question to move forward." }, { "title": "Core Principles", "body": "Guide, don't decide — Present options and let the user decide. Don't make assumptions about their preferences.\nLet the user drive the creative vision — If they have an idea, use their words. If they need inspiration, offer suggestions and let them choose or refine.\nSmart context awareness — Recognize what the user has already provided and only ask about missing pieces.\nIntent first — If the user's intent is unclear, confirm what they want before proceeding." }, { "title": "Step 1: Check for API Key", "body": "If the user hasn't provided an API key or set EVOLINK_API_KEY:\n\nTell them they need an EvoLink API Key\nGuide them to register at https://evolink.ai and get a key from the dashboard\nOnce they provide a key, proceed to Step 2\n\nIf the key is already set or provided, skip directly to Step 2." }, { "title": "Step 2: Understand Intent", "body": "Assess what the user wants based on their message:\n\nIntent is clear (e.g., \"generate a video of a cat dancing\") → Go to Step 3\nIntent is ambiguous (e.g., \"I want to try Seedance\") → Ask what they'd like to do: generate a new video, learn about model capabilities, etc." }, { "title": "Step 3: Gather Missing Information", "body": "Check what the user has already provided and only ask about what's missing:\n\nParameterWhat to tell the userRequired?Video content (prompt)Ask what they'd like to see. If they need inspiration, suggest a few ideas for them to pick from or build on.YesDurationSupported: 4–12 seconds. Ask how long they want.YesResolutionSupported: 480p / 720p / 1080p. Ask their preference.YesAudioThe model can auto-generate voice, sound effects, and background music matching the video. Ask if they want audio enabled.YesAspect ratioSupported: 16:9, 9:16, 1:1, 4:3, 3:4, 21:9. Only mention if relevant or if user asks.OptionalReference imagesSupported: up to 9 images (JPEG/PNG/WebP, ≤30MB each). Only mention if relevant.Optional\n\nSmart gathering rules:\n\nUser gives everything at once → Confirm and generate immediately\nUser gives partial info → Only ask about the missing pieces\nUser says \"I want to generate a video\" with no details → Guide from the beginning" }, { "title": "Step 4: Generate", "body": "Once all required information is confirmed:\n\nTell the user: \"Generating your video now — this usually takes 30–120 seconds. I'll let you know when it's ready.\"\nRun the generation script. Do NOT forward each line of script output to the user. The script prints polling status internally — ignore it. Only report the final result.\nWhen complete, share the video URL (valid for 24 hours) and generation time." }, { "title": "Script Usage", "body": "# Set API key\nexport EVOLINK_API_KEY=your_key_here\n\n# Basic text-to-video\n./scripts/seedance-gen.sh \"user's prompt\" --duration 5 --quality 720p\n\n# With audio disabled\n./scripts/seedance-gen.sh \"user's prompt\" --duration 8 --quality 1080p --no-audio\n\n# With reference image\n./scripts/seedance-gen.sh \"user's prompt\" --image \"https://example.com/ref.jpg\" --duration 6 --quality 720p\n\n# Custom aspect ratio\n./scripts/seedance-gen.sh \"user's prompt\" --aspect-ratio 9:16 --duration 4 --quality 480p" }, { "title": "Error Handling", "body": "Provide friendly, actionable messages:\n\nErrorWhat to tell the userInvalid/missing key (401)\"Your API key doesn't seem to work. You can check it at https://evolink.ai/dashboard\"Insufficient balance (402)\"Your account balance is low. You can add credits at https://evolink.ai/dashboard\"Rate limited (429)\"Too many requests — let's wait a moment and try again\"Content blocked (400)\"This prompt was flagged (realistic human faces are restricted). Try adjusting the description\"Service unavailable (503)\"The service is temporarily busy. Let's try again in a minute\"" }, { "title": "Model Capabilities Summary", "body": "Use this when the user asks what the model can do:\n\nText-to-video: Describe a scene, get a video\nImage-to-video: Provide reference images to guide the output\nAudio generation: Auto-generates synchronized voice, sound effects, and background music\nDuration: 4–12 seconds\nResolution: 480p, 720p, 1080p\nAspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4, 21:9\nLimitation: Realistic human faces are restricted" }, { "title": "References", "body": "references/api-params.md: Complete API parameter reference\nscripts/seedance-gen.sh: Generation script with automatic polling and error handling" } ], "body": "Seedance Video Generation\n\nAn interactive AI video generation assistant powered by the Seedance model via EvoLink API.\n\nAfter Installation\n\nWhen this skill is first loaded, proactively greet the user and start the setup:\n\nCheck if EVOLINK_API_KEY is set\n\nIf not set: \"To generate videos, you'll need an EvoLink API key. It takes 30 seconds to get one — just sign up at evolink.ai. Want me to walk you through it?\"\nIf already set: \"You're all set! What kind of video would you like to create?\"\n\nThat's it. One question. The user is now in the flow.\n\nDo NOT list features, show a menu, or dump instructions. Just ask one question to move forward.\n\nCore Principles\nGuide, don't decide — Present options and let the user decide. Don't make assumptions about their preferences.\nLet the user drive the creative vision — If they have an idea, use their words. If they need inspiration, offer suggestions and let them choose or refine.\nSmart context awareness — Recognize what the user has already provided and only ask about missing pieces.\nIntent first — If the user's intent is unclear, confirm what they want before proceeding.\nFlow\nStep 1: Check for API Key\n\nIf the user hasn't provided an API key or set EVOLINK_API_KEY:\n\nTell them they need an EvoLink API Key\nGuide them to register at https://evolink.ai and get a key from the dashboard\nOnce they provide a key, proceed to Step 2\n\nIf the key is already set or provided, skip directly to Step 2.\n\nStep 2: Understand Intent\n\nAssess what the user wants based on their message:\n\nIntent is clear (e.g., \"generate a video of a cat dancing\") → Go to Step 3\nIntent is ambiguous (e.g., \"I want to try Seedance\") → Ask what they'd like to do: generate a new video, learn about model capabilities, etc.\nStep 3: Gather Missing Information\n\nCheck what the user has already provided and only ask about what's missing:\n\nParameter\tWhat to tell the user\tRequired?\nVideo content (prompt)\tAsk what they'd like to see. If they need inspiration, suggest a few ideas for them to pick from or build on.\tYes\nDuration\tSupported: 4–12 seconds. Ask how long they want.\tYes\nResolution\tSupported: 480p / 720p / 1080p. Ask their preference.\tYes\nAudio\tThe model can auto-generate voice, sound effects, and background music matching the video. Ask if they want audio enabled.\tYes\nAspect ratio\tSupported: 16:9, 9:16, 1:1, 4:3, 3:4, 21:9. Only mention if relevant or if user asks.\tOptional\nReference images\tSupported: up to 9 images (JPEG/PNG/WebP, ≤30MB each). Only mention if relevant.\tOptional\n\nSmart gathering rules:\n\nUser gives everything at once → Confirm and generate immediately\nUser gives partial info → Only ask about the missing pieces\nUser says \"I want to generate a video\" with no details → Guide from the beginning\nStep 4: Generate\n\nOnce all required information is confirmed:\n\nTell the user: \"Generating your video now — this usually takes 30–120 seconds. I'll let you know when it's ready.\"\nRun the generation script. Do NOT forward each line of script output to the user. The script prints polling status internally — ignore it. Only report the final result.\nWhen complete, share the video URL (valid for 24 hours) and generation time.\nScript Usage\n# Set API key\nexport EVOLINK_API_KEY=your_key_here\n\n# Basic text-to-video\n./scripts/seedance-gen.sh \"user's prompt\" --duration 5 --quality 720p\n\n# With audio disabled\n./scripts/seedance-gen.sh \"user's prompt\" --duration 8 --quality 1080p --no-audio\n\n# With reference image\n./scripts/seedance-gen.sh \"user's prompt\" --image \"https://example.com/ref.jpg\" --duration 6 --quality 720p\n\n# Custom aspect ratio\n./scripts/seedance-gen.sh \"user's prompt\" --aspect-ratio 9:16 --duration 4 --quality 480p\n\nError Handling\n\nProvide friendly, actionable messages:\n\nError\tWhat to tell the user\nInvalid/missing key (401)\t\"Your API key doesn't seem to work. You can check it at https://evolink.ai/dashboard\"\nInsufficient balance (402)\t\"Your account balance is low. You can add credits at https://evolink.ai/dashboard\"\nRate limited (429)\t\"Too many requests — let's wait a moment and try again\"\nContent blocked (400)\t\"This prompt was flagged (realistic human faces are restricted). Try adjusting the description\"\nService unavailable (503)\t\"The service is temporarily busy. Let's try again in a minute\"\nModel Capabilities Summary\n\nUse this when the user asks what the model can do:\n\nText-to-video: Describe a scene, get a video\nImage-to-video: Provide reference images to guide the output\nAudio generation: Auto-generates synchronized voice, sound effects, and background music\nDuration: 4–12 seconds\nResolution: 480p, 720p, 1080p\nAspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4, 21:9\nLimitation: Realistic human faces are restricted\nReferences\nreferences/api-params.md: Complete API parameter reference\nscripts/seedance-gen.sh: Generation script with automatic polling and error handling" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/EvoLinkAI/seedance-2-video-gen", "publisherUrl": "https://clawhub.ai/EvoLinkAI/seedance-2-video-gen", "owner": "EvoLinkAI", "version": "1.4.1", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/seedance-2-video-gen", "downloadUrl": "https://openagent3.xyz/downloads/seedance-2-video-gen", "agentUrl": "https://openagent3.xyz/skills/seedance-2-video-gen/agent", "manifestUrl": "https://openagent3.xyz/skills/seedance-2-video-gen/agent.json", "briefUrl": "https://openagent3.xyz/skills/seedance-2-video-gen/agent.md" } }