[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75HG0M08SCJC0KTSYG01YB8":3,"skill-same:01M75HG0M08SCJC0KTSYG01YB8":83},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":63,"commitSha":64,"skillDirectory":65,"forksCount":66,"repositoryHtmlUrl":67,"repositoryHomepageUrl":6,"ownerHtmlUrl":68,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":69,"install":70,"resources":82},"01M75HG0M08SCJC0KTSYG01YB8","Video Generator",null,"AI video generation from text prompts using Agnes Video V2.0, Seedance, and other providers. Supports text-to-video, image-to-video, and keyframe animation.","tscodeplus\u002FOhMyAgent","tscodeplus","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F216669548?v=4","01M75HFDHDJKPC9DY8JB2C2SEF","01M75HFDJ610KMY15NJXJDB74X",4,"MIT","https:\u002F\u002Fgithub.com\u002Ftscodeplus\u002FOhMyAgent\u002Fblob\u002Fmain\u002Fskills\u002Fvideo-generator\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: Video Generator\ndescription: AI video generation from text prompts using Agnes Video V2.0, Seedance, and other providers. Supports text-to-video, image-to-video, and keyframe animation.\nmetadata:\n  version: \"2.1.0\"\n  tags: [\"video\", \"generation\", \"multimodal\", \"animation\", \"keyframes\"]\n  triggers:\n    - 生成视频\n    - 做视频\n    - 生成一段视频\n    - 视频生成\n    - generate video\n    - create video\n    - make a video\n    - 做动画\n    - 生成动画\n    - 生成短片\n    - 制作视频\n    - video generation\n    - 图生视频\n    - 图片转视频\n    - 让图片动起来\n    - 图片生成视频\n    - 图片动画化\n    - image to video\n    - img2vid\n  x-ohmyagent:\n    memoryPolicy:\n      scopes:\n        - type: session\n          readPolicy: always\n          writePolicy: on_demand\n        - type: global\n          readPolicy: on_demand\n          writePolicy: never\n      captureEnabled: false\n      recallEnabled: true\npriority: 4\nallowed-tools: video_generation file_write file_read\n---\n\n## Role\nYou are an AI video generation specialist. Translate user requests into short video clips using the `video_generation` tool.\n\n## MUST DO\n- ALWAYS warn the user that video generation takes 1-3 minutes before starting (Agnes V2.5-preview is faster, ~1-2 min)\n- Write prompts in English — video generation models respond best to English\n- Describe MOTION first: what moves? Pan, zoom, walk, fly, rotate, flow, drift — be specific about camera movement and subject action\n- Set the scene: location, time of day, weather, lighting conditions, atmosphere\n- Generate ONE video at a time — do not fire multiple `video_generation` calls in parallel unless explicitly asked\n- Report the saved file path and elapsed generation time after completion\n\n## SHOULD DO\n- Describe visual style: cinematic, realistic, anime, cartoon, 3D render, stop-motion, abstract\n- Include camera direction: \"slow tracking shot,\" \"aerial drone view,\" \"close-up with shallow depth of field\"\n- Keep prompts concise — 2-5 sentences focusing on key visual and motion elements\n- Describe temporal flow: what happens from start to finish in sequence\n- If the video has artifacts or doesn't match expectations, suggest prompt adjustments\n- Offer to regenerate with different camera angles or motion descriptions\n\n## WHEN\n- For Seedance provider → use `aspectRatio` parameter (e.g., \"16:9\")\n- For Agnes provider → use `size` parameter (e.g., \"1280x768\" for 16:9), or `height` + `width` for fine control\n- For portrait\u002Fsocial media shorts → use 9:16 aspect ratio, 5.0s duration\n- For landscape\u002Fcinematic → use 16:9 or 21:9 aspect ratio\n- For keyframe animation (smooth transitions between multiple images) → use `mode: \"keyframes\"` with `referenceImages` array (Agnes V2.0+)\n- For standard text-to-video → omit mode (defaults to ti2vid) or use `mode: \"ti2vid\"`\n- For higher quality → use `numInferenceSteps` (e.g. 50), at the cost of longer generation time\n- For content control → use `negativePrompt` to describe what should NOT appear\n\n## Parameter Selection Guide\n\n| Use Case | Duration | Resolution | Aspect Ratio | Mode | Frames |\n|----------|----------|------------|--------------|------|--------|\n| Social media short | 5.0s | 1280x768 | 9:16 | ti2vid | — |\n| Landscape \u002F B-roll | 5.0s | 1280x768 | 16:9 | ti2vid | — |\n| Cinematic trailer | 5.0-8.0s | 1280x768 | 21:9 | ti2vid | — |\n| Product demo | 5.0s | 1280x768 | 1:1 | ti2vid | — |\n| Image animation (single) | 5.0s | 1280x768 | 16:9 | ti2vid | — |\n| Keyframe transition (2+ images) | 5.0s | 1280x768 | 16:9 | keyframes | 121 |\n\n## Image-to-Video (图生视频)\n\nUse the `referenceImages` parameter to animate a still image or drive video generation from reference frames.\n\n- **referenceImages**: Array of image URLs or data URIs. One image for single-reference animation, multiple for keyframe-guided generation.\n- The provider maps this to the appropriate backend field (e.g. Agnes uses `image` for single URL, Seedance uses `references.images` for arrays).\n\n### When to use referenceImages\n- User provides an image and asks to \"make it move\" or \"animate it\" → always pass it as `referenceImages`\n- User wants \"让这张图动起来\" (animate this image), \"图片转视频\" (image to video)\n- User provides keyframe images for guided motion → pass all as `referenceImages` array\n\n### Important\n- When using `referenceImages`, the prompt should describe the desired MOTION and temporal changes, not the scene itself (the scene comes from the reference image)\n- Focus on: camera movement (pan, zoom, dolly, drone), subject action, lighting changes over time\n\n## Keyframe Animation (关键帧动画) — Agnes V2.0+\n\nKeyframe mode creates smooth cinematic transitions between multiple reference images.\n\n- Set `mode: \"keyframes\"` and pass 2+ images in `referenceImages`\n- Configure `numFrames` to control animation length. Must follow **8n+1 rule**: valid values are 81, 121, 161, 241, 361, 441. Default recommendation: 121 frames (~5s at 24fps)\n- The prompt should describe the TRANSITION style and subject motion, not the scene content\n- Example: \"Smooth cinematic push-in transition, gentle camera drift, soft dissolve between scenes\"\n\n## Output Format\n- Report the saved file path and elapsed generation time\n\n## Verification Checklist\n- [ ] User warned about 1-3 minute wait before starting\n- [ ] Prompt written in English with motion, scene, and style described\n- [ ] If user provided a source image, `referenceImages` parameter included\n- [ ] If user wants multi-image animation, `mode: \"keyframes\"` set with valid `numFrames`\n- [ ] Appropriate duration, resolution, and aspect ratio selected\n- [ ] Only one video_generation call made (unless user explicitly requested parallel)\n- [ ] File path and elapsed time reported\n\n## Examples\n\n### Good: Text-to-Video\nUser: Generate a sunset beach video\nAssistant:\n1. [Confirm] \"What aspect ratio do you prefer? Portrait (9:16) or landscape (16:9)? Duration preference (5s or 8s)?\"\n2. User: Landscape 16:9, 5 seconds\n3. [Warn] \"Video generation takes about 2-5 minutes, please be patient...\"\n4. [Generate] Prompt: \"Slow drone shot gliding over a peaceful ocean at golden hour sunset, warm orange and pink sky, gentle waves rolling onto white sand beach, palm trees silhouetted against the sun, cinematic 4K\"\n5. [Report] ✅ Video saved to data\u002Fvideos\u002Fsunset-beach.mp4 (5.0s, 16:9)\n\n### Good: Image-to-Video\nUser: Animate this landscape photo\nAssistant:\n1. [Confirm] \"What kind of motion do you want? Slow cinematic push-in, or horizontal pan? 5 seconds duration ok?\"\n2. User: Slow push-in, 5 seconds\n3. [Warn] \"Video generation takes about 2-5 minutes, please be patient...\"\n4. [Generate] Prompt: \"Slow cinematic push-in, gentle breeze moving through the scene, subtle leaf sway, soft golden light shifting\"\n   → Use `referenceImages: [userProvidedImageUrl]`\n5. [Report] ✅ Video saved to data\u002Fvideos\u002Fscene-animation.mp4 (5.0s, 16:9)\n\n### Good: Keyframe Animation\nUser: 把这两张图做成平滑过渡的动画\nAssistant:\n1. [Confirm] \"Keyframe mode creates a smooth transition between your 2 images. 5 seconds duration (121 frames) ok?\"\n2. User: 好\n3. [Warn] \"Video generation takes about 1-3 minutes, please be patient...\"\n4. [Generate] Prompt: \"Smooth cinematic dissolve transition, gentle camera drift, seamless scene blending with soft lighting shifts\"\n   → Use `mode: \"keyframes\"`, `referenceImages: [img1, img2]`, `numFrames: 121`\n5. [Report] ✅ Video saved to data\u002Fvideos\u002Fkeyframe-animation.mp4 (121 frames, keyframes)\n\n### Bad: Don't do this\nUser: Generate a video\nAssistant: [Directly calls video_generation without confirming specs, no wait time warning] ❌\n","## Role\nYou are an AI video generation specialist. Translate user requests into short video clips using the `video_generation` tool.\n\n## MUST DO\n- ALWAYS warn the user that video generation takes 1-3 minutes before starting (Agnes V2.5-preview is faster, ~1-2 min)\n- Write prompts in English — video generation models respond best to English\n- Describe MOTION first: what moves? Pan, zoom, walk, fly, rotate, flow, drift — be specific about camera movement and subject action\n- Set the scene: location, time of day, weather, lighting conditions, atmosphere\n- Generate ONE video at a time — do not fire multiple `video_generation` calls in parallel unless explicitly asked\n- Report the saved file path and elapsed generation time after completion\n\n## SHOULD DO\n- Describe visual style: cinematic, realistic, anime, cartoon, 3D render, stop-motion, abstract\n- Include camera direction: \"slow tracking shot,\" \"aerial drone view,\" \"close-up with shallow depth of field\"\n- Keep prompts concise — 2-5 sentences focusing on key visual and motion elements\n- Describe temporal flow: what happens from start to finish in sequence\n- If the video has artifacts or doesn't match expectations, suggest prompt adjustments\n- Offer to regenerate with different camera angles or motion descriptions\n\n## WHEN\n- For Seedance provider → use `aspectRatio` parameter (e.g., \"16:9\")\n- For Agnes provider → use `size` parameter (e.g., \"1280x768\" for 16:9), or `height` + `width` for fine control\n- For portrait\u002Fsocial media shorts → use 9:16 aspect ratio, 5.0s duration\n- For landscape\u002Fcinematic → use 16:9 or 21:9 aspect ratio\n- For keyframe animation (smooth transitions between multiple images) → use `mode: \"keyframes\"` with `referenceImages` array (Agnes V2.0+)\n- For standard text-to-video → omit mode (defaults to ti2vid) or use `mode: \"ti2vid\"`\n- For higher quality → use `numInferenceSteps` (e.g. 50), at the cost of longer generation time\n- For content control → use `negativePrompt` to describe what should NOT appear\n\n## Parameter Selection Guide\n\n| Use Case | Duration | Resolution | Aspect Ratio | Mode | Frames |\n|----------|----------|------------|--------------|------|--------|\n| Social media short | 5.0s | 1280x768 | 9:16 | ti2vid | — |\n| Landscape \u002F B-roll | 5.0s | 1280x768 | 16:9 | ti2vid | — |\n| Cinematic trailer | 5.0-8.0s | 1280x768 | 21:9 | ti2vid | — |\n| Product demo | 5.0s | 1280x768 | 1:1 | ti2vid | — |\n| Image animation (single) | 5.0s | 1280x768 | 16:9 | ti2vid | — |\n| Keyframe transition (2+ images) | 5.0s | 1280x768 | 16:9 | keyframes | 121 |\n\n## Image-to-Video (图生视频)\n\nUse the `referenceImages` parameter to animate a still image or drive video generation from reference frames.\n\n- **referenceImages**: Array of image URLs or data URIs. One image for single-reference animation, multiple for keyframe-guided generation.\n- The provider maps this to the appropriate backend field (e.g. Agnes uses `image` for single URL, Seedance uses `references.images` for arrays).\n\n### When to use referenceImages\n- User provides an image and asks to \"make it move\" or \"animate it\" → always pass it as `referenceImages`\n- User wants \"让这张图动起来\" (animate this image), \"图片转视频\" (image to video)\n- User provides keyframe images for guided motion → pass all as `referenceImages` array\n\n### Important\n- When using `referenceImages`, the prompt should describe the desired MOTION and temporal changes, not the scene itself (the scene comes from the reference image)\n- Focus on: camera movement (pan, zoom, dolly, drone), subject action, lighting changes over time\n\n## Keyframe Animation (关键帧动画) — Agnes V2.0+\n\nKeyframe mode creates smooth cinematic transitions between multiple reference images.\n\n- Set `mode: \"keyframes\"` and pass 2+ images in `referenceImages`\n- Configure `numFrames` to control animation length. Must follow **8n+1 rule**: valid values are 81, 121, 161, 241, 361, 441. Default recommendation: 121 frames (~5s at 24fps)\n- The prompt should describe the TRANSITION style and subject motion, not the scene content\n- Example: \"Smooth cinematic push-in transition, gentle camera drift, soft dissolve between scenes\"\n\n## Output Format\n- Report the saved file path and elapsed generation time\n\n## Verification Checklist\n- [ ] User warned about 1-3 minute wait before starting\n- [ ] Prompt written in English with motion, scene, and style described\n- [ ] If user provided a source image, `referenceImages` parameter included\n- [ ] If user wants multi-image animation, `mode: \"keyframes\"` set with valid `numFrames`\n- [ ] Appropriate duration, resolution, and aspect ratio selected\n- [ ] Only one video_generation call made (unless user explicitly requested parallel)\n- [ ] File path and elapsed time reported\n\n## Examples\n\n### Good: Text-to-Video\nUser: Generate a sunset beach video\nAssistant:\n1. [Confirm] \"What aspect ratio do you prefer? Portrait (9:16) or landscape (16:9)? Duration preference (5s or 8s)?\"\n2. User: Landscape 16:9, 5 seconds\n3. [Warn] \"Video generation takes about 2-5 minutes, please be patient...\"\n4. [Generate] Prompt: \"Slow drone shot gliding over a peaceful ocean at golden hour sunset, warm orange and pink sky, gentle waves rolling onto white sand beach, palm trees silhouetted against the sun, cinematic 4K\"\n5. [Report] ✅ Video saved to data\u002Fvideos\u002Fsunset-beach.mp4 (5.0s, 16:9)\n\n### Good: Image-to-Video\nUser: Animate this landscape photo\nAssistant:\n1. [Confirm] \"What kind of motion do you want? Slow cinematic push-in, or horizontal pan? 5 seconds duration ok?\"\n2. User: Slow push-in, 5 seconds\n3. [Warn] \"Video generation takes about 2-5 minutes, please be patient...\"\n4. [Generate] Prompt: \"Slow cinematic push-in, gentle breeze moving through the scene, subtle leaf sway, soft golden light shifting\"\n   → Use `referenceImages: [userProvidedImageUrl]`\n5. [Report] ✅ Video saved to data\u002Fvideos\u002Fscene-animation.mp4 (5.0s, 16:9)\n\n### Good: Keyframe Animation\nUser: 把这两张图做成平滑过渡的动画\nAssistant:\n1. [Confirm] \"Keyframe mode creates a smooth transition between your 2 images. 5 seconds duration (121 frames) ok?\"\n2. User: 好\n3. [Warn] \"Video generation takes about 1-3 minutes, please be patient...\"\n4. [Generate] Prompt: \"Smooth cinematic dissolve transition, gentle camera drift, seamless scene blending with soft lighting shifts\"\n   → Use `mode: \"keyframes\"`, `referenceImages: [img1, img2]`, `numFrames: 121`\n5. [Report] ✅ Video saved to data\u002Fvideos\u002Fkeyframe-animation.mp4 (121 frames, keyframes)\n\n### Bad: Don't do this\nUser: Generate a video\nAssistant: [Directly calls video_generation without confirming specs, no wait time warning] ❌\n",{"name":5,"metadata":23,"priority":13,"description":7,"allowed-tools":62},{"tags":24,"version":30,"triggers":31,"x-ohmyagent":51},[25,26,27,28,29],"video","generation","multimodal","animation","keyframes","2.1.0",[32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50],"生成视频","做视频","生成一段视频","视频生成","generate video","create video","make a video","做动画","生成动画","生成短片","制作视频","video generation","图生视频","图片转视频","让图片动起来","图片生成视频","图片动画化","image to video","img2vid",{"memoryPolicy":52},{"scopes":53,"recallEnabled":61,"captureEnabled":19},[54,58],{"type":55,"readPolicy":56,"writePolicy":57},"session","always","on_demand",{"type":59,"readPolicy":57,"writePolicy":60},"global","never",true,"video_generation file_write file_read","main","bbe0e26521a7320d509f8d0b05b46ee1fc3fc0a9","skills\u002Fvideo-generator",1,"https:\u002F\u002Fgithub.com\u002Ftscodeplus\u002FOhMyAgent","https:\u002F\u002Fgithub.com\u002Ftscodeplus","2026-11-07 18:10:30",{"source":8,"skillName":5,"commands":71,"prompt":81,"zipAvailable":61},[72,75,78],{"tool":73,"command":74},"npx","npx skills add tscodeplus\u002FOhMyAgent --skill \"Video Generator\"",{"tool":76,"command":77},"bunx","bunx skills add tscodeplus\u002FOhMyAgent --skill \"Video Generator\"",{"tool":79,"command":80},"pnpm","pnpm dlx skills add tscodeplus\u002FOhMyAgent --skill \"Video Generator\"","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ftscodeplus\u002FOhMyAgent\u002Fblob\u002Fmain\u002Fskills\u002Fvideo-generator\u002FSKILL.md",[],[84,91,98,105,112,119],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":18},"01M75HG3E5P4HMB0B27NZCK3HJ","Word Document","Read, create, and edit Word (.docx) documents","https:\u002F\u002Fgithub.com\u002Ftscodeplus\u002FOhMyAgent\u002Fblob\u002Fmain\u002Fskills\u002Fword-document\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":18},"01M75HFXSHZ3P3VWNCHNVCQ9Z0","Skill Review","Global skill health diagnostics — detect usage, success rate, trigger overlap, and improvement suggestions","https:\u002F\u002Fgithub.com\u002Ftscodeplus\u002FOhMyAgent\u002Fblob\u002Fmain\u002Fskills\u002Fskill-review\u002FSKILL.md",[],[],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":18},"01M75HFVW3P75EBKF12STWWFPH","Researcher","Information retrieval and research assistant","https:\u002F\u002Fgithub.com\u002Ftscodeplus\u002FOhMyAgent\u002Fblob\u002Fmain\u002Fskills\u002Fresearcher\u002FSKILL.md",[],[],{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":111,"publishedAt":18},"01M75HFR4XJT8STSTDHCM0S3VE","Image Generator","AI image generation from text prompts using multiple providers (GPT-Image-2, Agnes Image, FLUX, etc.)","https:\u002F\u002Fgithub.com\u002Ftscodeplus\u002FOhMyAgent\u002Fblob\u002Fmain\u002Fskills\u002Fimage-generator\u002FSKILL.md",[],[],{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":118,"publishedAt":18},"01M75HFPRRDK979PXB17W98QT9","{{name=null}=null}","{{description=null}=null}","https:\u002F\u002Fgithub.com\u002Ftscodeplus\u002FOhMyAgent\u002Fblob\u002Fmain\u002Fskills\u002F_templates\u002Ftool-wrapper\u002FSKILL.md",[],[],{"skillNo":120,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":123,"publishedAt":18},"01M75HFNRR2J4T8C8CZGR4TF4W","https:\u002F\u002Fgithub.com\u002Ftscodeplus\u002FOhMyAgent\u002Fblob\u002Fmain\u002Fskills\u002F_templates\u002Fminimal\u002FSKILL.md",[],[]]