[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M70FWH9F81GFRT65BKH4SH0M":3,"skill-same:01M70FWH9F81GFRT65BKH4SH0M":76},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":26,"publishedAt":47,"linkOnly":48,"markdownContent":49,"markdownBody":50,"frontMatter":51,"refName":54,"commitSha":55,"skillDirectory":56,"forksCount":57,"repositoryHtmlUrl":58,"repositoryHomepageUrl":6,"ownerHtmlUrl":59,"ownerBlogUrl":6,"ownerDescription":60,"updatedAt":61,"install":62,"resources":75},"01M70FWH9F81GFRT65BKH4SH0M","fal-ai-media",null,"Unified media generation via fal.ai MCP — image, video, and audio. Covers text-to-image (Nano Banana), text\u002Fimage-to-video (Seedance, Kling, Veo 3), text-to-speech (CSM-1B), and video-to-audio (ThinkSound). Use when the user wants to generate images, videos, or audio with AI.","mdnaimul22\u002Fhuman-skills","mdnaimul22","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F64520358?v=4","01M70FH95MH2H796Q01TYSFZ03","Naimul","01M70FH96798CQR4YHA13F17GA",3,"MIT","https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Faffaan-m_ECC\u002Ffal-ai-media\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46],"fal ai","Media","fal ai media","fal","use","when","veo 3","nano","text-to-speech","image-to-video","seedance","banana","images","MCP","text","Audio","Video","speech","generate","image","2026-11-10 10:12:30",false,"---\nname: fal-ai-media\ndescription: Unified media generation via fal.ai MCP — image, video, and audio. Covers text-to-image (Nano Banana), text\u002Fimage-to-video (Seedance, Kling, Veo 3), text-to-speech (CSM-1B), and video-to-audio (ThinkSound). Use when the user wants to generate images, videos, or audio with AI.\nmetadata:\n  origin: ECC\n---\n\n# fal.ai Media Generation\n\n> **Drift-prone skill.** fal.ai model IDs, pricing, inputs, and MCP tool names\n> change quickly. Search or fetch the current model metadata before promising a\n> specific model, parameter, output format, or cost.\n\nGenerate images, videos, and audio using fal.ai models via MCP.\n\n## When to Activate\n\n- User wants to generate images from text prompts\n- Creating videos from text or images\n- Generating speech, music, or sound effects\n- Any media generation task\n- User says \"generate image\", \"create video\", \"text to speech\", \"make a thumbnail\", or similar\n\n## MCP Requirement\n\nfal.ai MCP server must be configured. Add to `~\u002F.claude.json`:\n\n```json\n\"fal-ai\": {\n  \"command\": \"npx\",\n  \"args\": [\"-y\", \"fal-ai-mcp-server\"],\n  \"env\": { \"FAL_KEY\": \"YOUR_FAL_KEY_HERE\" }\n}\n```\n\nGet an API key at [fal.ai](https:\u002F\u002Ffal.ai).\n\n## MCP Tools\n\nThe fal.ai MCP provides these tools:\n- `search` — Find available models by keyword\n- `find` — Get model details and parameters\n- `generate` — Run a model with parameters\n- `result` — Check async generation status\n- `status` — Check job status\n- `cancel` — Cancel a running job\n- `estimate_cost` — Estimate generation cost\n- `models` — List popular models\n- `upload` — Upload files for use as inputs\n\n---\n\n## Image Generation\n\n### Nano Banana 2 (Fast)\nBest for: quick iterations, drafts, text-to-image, image editing.\n\n```\ngenerate(\n  app_id: \"fal-ai\u002Fnano-banana-2\",\n  input_data: {\n    \"prompt\": \"a futuristic cityscape at sunset, cyberpunk style\",\n    \"image_size\": \"landscape_16_9\",\n    \"num_images\": 1,\n    \"seed\": 42\n  }\n)\n```\n\n### Nano Banana Pro (High Fidelity)\nBest for: production images, realism, typography, detailed prompts.\n\n```\ngenerate(\n  app_id: \"fal-ai\u002Fnano-banana-pro\",\n  input_data: {\n    \"prompt\": \"professional product photo of wireless headphones on marble surface, studio lighting\",\n    \"image_size\": \"square\",\n    \"num_images\": 1,\n    \"guidance_scale\": 7.5\n  }\n)\n```\n\n### Common Image Parameters\n\n| Param | Type | Options | Notes |\n|-------|------|---------|-------|\n| `prompt` | string | required | Describe what you want |\n| `image_size` | string | `square`, `portrait_4_3`, `landscape_16_9`, `portrait_16_9`, `landscape_4_3` | Aspect ratio |\n| `num_images` | number | 1-4 | How many to generate |\n| `seed` | number | any integer | Reproducibility |\n| `guidance_scale` | number | 1-20 | How closely to follow the prompt (higher = more literal) |\n\n### Image Editing\nUse Nano Banana 2 with an input image for inpainting, outpainting, or style transfer:\n\n```\n# First upload the source image\nupload(file_path: \"\u002Fpath\u002Fto\u002Fimage.png\")\n\n# Then generate with image input\ngenerate(\n  app_id: \"fal-ai\u002Fnano-banana-2\",\n  input_data: {\n    \"prompt\": \"same scene but in watercolor style\",\n    \"image_url\": \"\u003Cuploaded_url>\",\n    \"image_size\": \"landscape_16_9\"\n  }\n)\n```\n\n---\n\n## Video Generation\n\n### Seedance 1.0 Pro (ByteDance)\nBest for: text-to-video, image-to-video with high motion quality.\n\n```\ngenerate(\n  app_id: \"fal-ai\u002Fseedance-1-0-pro\",\n  input_data: {\n    \"prompt\": \"a drone flyover of a mountain lake at golden hour, cinematic\",\n    \"duration\": \"5s\",\n    \"aspect_ratio\": \"16:9\",\n    \"seed\": 42\n  }\n)\n```\n\n### Kling Video v3 Pro\nBest for: text\u002Fimage-to-video with native audio generation.\n\n```\ngenerate(\n  app_id: \"fal-ai\u002Fkling-video\u002Fv3\u002Fpro\",\n  input_data: {\n    \"prompt\": \"ocean waves crashing on a rocky coast, dramatic clouds\",\n    \"duration\": \"5s\",\n    \"aspect_ratio\": \"16:9\"\n  }\n)\n```\n\n### Veo 3 (Google DeepMind)\nBest for: video with generated sound, high visual quality.\n\n```\ngenerate(\n  app_id: \"fal-ai\u002Fveo-3\",\n  input_data: {\n    \"prompt\": \"a bustling Tokyo street market at night, neon signs, crowd noise\",\n    \"aspect_ratio\": \"16:9\"\n  }\n)\n```\n\n### Image-to-Video\nStart from an existing image:\n\n```\ngenerate(\n  app_id: \"fal-ai\u002Fseedance-1-0-pro\",\n  input_data: {\n    \"prompt\": \"camera slowly zooms out, gentle wind moves the trees\",\n    \"image_url\": \"\u003Cuploaded_image_url>\",\n    \"duration\": \"5s\"\n  }\n)\n```\n\n### Video Parameters\n\n| Param | Type | Options | Notes |\n|-------|------|---------|-------|\n| `prompt` | string | required | Describe the video |\n| `duration` | string | `\"5s\"`, `\"10s\"` | Video length |\n| `aspect_ratio` | string | `\"16:9\"`, `\"9:16\"`, `\"1:1\"` | Frame ratio |\n| `seed` | number | any integer | Reproducibility |\n| `image_url` | string | URL | Source image for image-to-video |\n\n---\n\n## Audio Generation\n\n### CSM-1B (Conversational Speech)\nText-to-speech with natural, conversational quality.\n\n```\ngenerate(\n  app_id: \"fal-ai\u002Fcsm-1b\",\n  input_data: {\n    \"text\": \"Hello, welcome to the demo. Let me show you how this works.\",\n    \"speaker_id\": 0\n  }\n)\n```\n\n### ThinkSound (Video-to-Audio)\nGenerate matching audio from video content.\n\n```\ngenerate(\n  app_id: \"fal-ai\u002Fthinksound\",\n  input_data: {\n    \"video_url\": \"\u003Cvideo_url>\",\n    \"prompt\": \"ambient forest sounds with birds chirping\"\n  }\n)\n```\n\n### ElevenLabs (via API, no MCP)\nFor professional voice synthesis, use ElevenLabs directly:\n\n```python\nimport os\nimport requests\n\nresp = requests.post(\n    \"https:\u002F\u002Fapi.elevenlabs.io\u002Fv1\u002Ftext-to-speech\u002F\u003Cvoice_id>\",\n    headers={\n        \"xi-api-key\": os.environ[\"ELEVENLABS_API_KEY\"],\n        \"Content-Type\": \"application\u002Fjson\"\n    },\n    json={\n        \"text\": \"Your text here\",\n        \"model_id\": \"eleven_turbo_v2_5\",\n        \"voice_settings\": {\"stability\": 0.5, \"similarity_boost\": 0.75}\n    }\n)\nwith open(\"output.mp3\", \"wb\") as f:\n    f.write(resp.content)\n```\n\n### VideoDB Generative Audio\nIf VideoDB is configured, use its generative audio:\n\n```python\n# Voice generation\naudio = coll.generate_voice(text=\"Your narration here\", voice=\"alloy\")\n\n# Music generation\nmusic = coll.generate_music(prompt=\"upbeat electronic background music\", duration=30)\n\n# Sound effects\nsfx = coll.generate_sound_effect(prompt=\"thunder crack followed by rain\")\n```\n\n---\n\n## Cost Estimation\n\nBefore generating, check estimated cost:\n\n```\nestimate_cost(\n  estimate_type: \"unit_price\",\n  endpoints: {\n    \"fal-ai\u002Fnano-banana-pro\": {\n      \"unit_quantity\": 1\n    }\n  }\n)\n```\n\n## Model Discovery\n\nFind models for specific tasks:\n\n```\nsearch(query: \"text to video\")\nfind(endpoint_ids: [\"fal-ai\u002Fseedance-1-0-pro\"])\nmodels()\n```\n\n## Tips\n\n- Use `seed` for reproducible results when iterating on prompts\n- Start with lower-cost models (Nano Banana 2) for prompt iteration, then switch to Pro for finals\n- For video, keep prompts descriptive but concise — focus on motion and scene\n- Image-to-video produces more controlled results than pure text-to-video\n- Check `estimate_cost` before running expensive video generations\n\n## Related Skills\n\n- `tasteforge-video` — Offline taste distillation and modality planning. Its\n  endpoint candidates and request manifests are reference-only, not submitted\n  jobs or saved Fal workflows. A TasteForge handoff does not authorize upload\n  or generation; use a separately authorized provider workflow and verify its\n  current endpoint schema before executing.\n- `videodb` — Video processing, editing, and streaming\n- `video-editing` — AI-powered video editing workflows\n- `content-engine` — Content creation for social platforms\n","# fal.ai Media Generation\n\n> **Drift-prone skill.** fal.ai model IDs, pricing, inputs, and MCP tool names\n> change quickly. Search or fetch the current model metadata before promising a\n> specific model, parameter, output format, or cost.\n\nGenerate images, videos, and audio using fal.ai models via MCP.\n\n## When to Activate\n\n- User wants to generate images from text prompts\n- Creating videos from text or images\n- Generating speech, music, or sound effects\n- Any media generation task\n- User says \"generate image\", \"create video\", \"text to speech\", \"make a thumbnail\", or similar\n\n## MCP Requirement\n\nfal.ai MCP server must be configured. Add to `~\u002F.claude.json`:\n\n```json\n\"fal-ai\": {\n  \"command\": \"npx\",\n  \"args\": [\"-y\", \"fal-ai-mcp-server\"],\n  \"env\": { \"FAL_KEY\": \"YOUR_FAL_KEY_HERE\" }\n}\n```\n\nGet an API key at [fal.ai](https:\u002F\u002Ffal.ai).\n\n## MCP Tools\n\nThe fal.ai MCP provides these tools:\n- `search` — Find available models by keyword\n- `find` — Get model details and parameters\n- `generate` — Run a model with parameters\n- `result` — Check async generation status\n- `status` — Check job status\n- `cancel` — Cancel a running job\n- `estimate_cost` — Estimate generation cost\n- `models` — List popular models\n- `upload` — Upload files for use as inputs\n\n---\n\n## Image Generation\n\n### Nano Banana 2 (Fast)\nBest for: quick iterations, drafts, text-to-image, image editing.\n\n```\ngenerate(\n  app_id: \"fal-ai\u002Fnano-banana-2\",\n  input_data: {\n    \"prompt\": \"a futuristic cityscape at sunset, cyberpunk style\",\n    \"image_size\": \"landscape_16_9\",\n    \"num_images\": 1,\n    \"seed\": 42\n  }\n)\n```\n\n### Nano Banana Pro (High Fidelity)\nBest for: production images, realism, typography, detailed prompts.\n\n```\ngenerate(\n  app_id: \"fal-ai\u002Fnano-banana-pro\",\n  input_data: {\n    \"prompt\": \"professional product photo of wireless headphones on marble surface, studio lighting\",\n    \"image_size\": \"square\",\n    \"num_images\": 1,\n    \"guidance_scale\": 7.5\n  }\n)\n```\n\n### Common Image Parameters\n\n| Param | Type | Options | Notes |\n|-------|------|---------|-------|\n| `prompt` | string | required | Describe what you want |\n| `image_size` | string | `square`, `portrait_4_3`, `landscape_16_9`, `portrait_16_9`, `landscape_4_3` | Aspect ratio |\n| `num_images` | number | 1-4 | How many to generate |\n| `seed` | number | any integer | Reproducibility |\n| `guidance_scale` | number | 1-20 | How closely to follow the prompt (higher = more literal) |\n\n### Image Editing\nUse Nano Banana 2 with an input image for inpainting, outpainting, or style transfer:\n\n```\n# First upload the source image\nupload(file_path: \"\u002Fpath\u002Fto\u002Fimage.png\")\n\n# Then generate with image input\ngenerate(\n  app_id: \"fal-ai\u002Fnano-banana-2\",\n  input_data: {\n    \"prompt\": \"same scene but in watercolor style\",\n    \"image_url\": \"\u003Cuploaded_url>\",\n    \"image_size\": \"landscape_16_9\"\n  }\n)\n```\n\n---\n\n## Video Generation\n\n### Seedance 1.0 Pro (ByteDance)\nBest for: text-to-video, image-to-video with high motion quality.\n\n```\ngenerate(\n  app_id: \"fal-ai\u002Fseedance-1-0-pro\",\n  input_data: {\n    \"prompt\": \"a drone flyover of a mountain lake at golden hour, cinematic\",\n    \"duration\": \"5s\",\n    \"aspect_ratio\": \"16:9\",\n    \"seed\": 42\n  }\n)\n```\n\n### Kling Video v3 Pro\nBest for: text\u002Fimage-to-video with native audio generation.\n\n```\ngenerate(\n  app_id: \"fal-ai\u002Fkling-video\u002Fv3\u002Fpro\",\n  input_data: {\n    \"prompt\": \"ocean waves crashing on a rocky coast, dramatic clouds\",\n    \"duration\": \"5s\",\n    \"aspect_ratio\": \"16:9\"\n  }\n)\n```\n\n### Veo 3 (Google DeepMind)\nBest for: video with generated sound, high visual quality.\n\n```\ngenerate(\n  app_id: \"fal-ai\u002Fveo-3\",\n  input_data: {\n    \"prompt\": \"a bustling Tokyo street market at night, neon signs, crowd noise\",\n    \"aspect_ratio\": \"16:9\"\n  }\n)\n```\n\n### Image-to-Video\nStart from an existing image:\n\n```\ngenerate(\n  app_id: \"fal-ai\u002Fseedance-1-0-pro\",\n  input_data: {\n    \"prompt\": \"camera slowly zooms out, gentle wind moves the trees\",\n    \"image_url\": \"\u003Cuploaded_image_url>\",\n    \"duration\": \"5s\"\n  }\n)\n```\n\n### Video Parameters\n\n| Param | Type | Options | Notes |\n|-------|------|---------|-------|\n| `prompt` | string | required | Describe the video |\n| `duration` | string | `\"5s\"`, `\"10s\"` | Video length |\n| `aspect_ratio` | string | `\"16:9\"`, `\"9:16\"`, `\"1:1\"` | Frame ratio |\n| `seed` | number | any integer | Reproducibility |\n| `image_url` | string | URL | Source image for image-to-video |\n\n---\n\n## Audio Generation\n\n### CSM-1B (Conversational Speech)\nText-to-speech with natural, conversational quality.\n\n```\ngenerate(\n  app_id: \"fal-ai\u002Fcsm-1b\",\n  input_data: {\n    \"text\": \"Hello, welcome to the demo. Let me show you how this works.\",\n    \"speaker_id\": 0\n  }\n)\n```\n\n### ThinkSound (Video-to-Audio)\nGenerate matching audio from video content.\n\n```\ngenerate(\n  app_id: \"fal-ai\u002Fthinksound\",\n  input_data: {\n    \"video_url\": \"\u003Cvideo_url>\",\n    \"prompt\": \"ambient forest sounds with birds chirping\"\n  }\n)\n```\n\n### ElevenLabs (via API, no MCP)\nFor professional voice synthesis, use ElevenLabs directly:\n\n```python\nimport os\nimport requests\n\nresp = requests.post(\n    \"https:\u002F\u002Fapi.elevenlabs.io\u002Fv1\u002Ftext-to-speech\u002F\u003Cvoice_id>\",\n    headers={\n        \"xi-api-key\": os.environ[\"ELEVENLABS_API_KEY\"],\n        \"Content-Type\": \"application\u002Fjson\"\n    },\n    json={\n        \"text\": \"Your text here\",\n        \"model_id\": \"eleven_turbo_v2_5\",\n        \"voice_settings\": {\"stability\": 0.5, \"similarity_boost\": 0.75}\n    }\n)\nwith open(\"output.mp3\", \"wb\") as f:\n    f.write(resp.content)\n```\n\n### VideoDB Generative Audio\nIf VideoDB is configured, use its generative audio:\n\n```python\n# Voice generation\naudio = coll.generate_voice(text=\"Your narration here\", voice=\"alloy\")\n\n# Music generation\nmusic = coll.generate_music(prompt=\"upbeat electronic background music\", duration=30)\n\n# Sound effects\nsfx = coll.generate_sound_effect(prompt=\"thunder crack followed by rain\")\n```\n\n---\n\n## Cost Estimation\n\nBefore generating, check estimated cost:\n\n```\nestimate_cost(\n  estimate_type: \"unit_price\",\n  endpoints: {\n    \"fal-ai\u002Fnano-banana-pro\": {\n      \"unit_quantity\": 1\n    }\n  }\n)\n```\n\n## Model Discovery\n\nFind models for specific tasks:\n\n```\nsearch(query: \"text to video\")\nfind(endpoint_ids: [\"fal-ai\u002Fseedance-1-0-pro\"])\nmodels()\n```\n\n## Tips\n\n- Use `seed` for reproducible results when iterating on prompts\n- Start with lower-cost models (Nano Banana 2) for prompt iteration, then switch to Pro for finals\n- For video, keep prompts descriptive but concise — focus on motion and scene\n- Image-to-video produces more controlled results than pure text-to-video\n- Check `estimate_cost` before running expensive video generations\n\n## Related Skills\n\n- `tasteforge-video` — Offline taste distillation and modality planning. Its\n  endpoint candidates and request manifests are reference-only, not submitted\n  jobs or saved Fal workflows. A TasteForge handoff does not authorize upload\n  or generation; use a separately authorized provider workflow and verify its\n  current endpoint schema before executing.\n- `videodb` — Video processing, editing, and streaming\n- `video-editing` — AI-powered video editing workflows\n- `content-engine` — Content creation for social platforms\n",{"name":5,"metadata":52,"description":7},{"origin":53},"ECC","main","74715deacdc69119d739f38916f8ee4f0f979ebf","skills\u002Fstorage\u002Faffaan-m_ECC\u002Ffal-ai-media",0,"https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills","https:\u002F\u002Fgithub.com\u002Fmdnaimul22","AI Agents Workflows Automation | Specializing in Python, FastAPI, MCP Agents & Custom ERP.","2026-11-11 21:16:57",{"source":8,"skillName":5,"commands":63,"prompt":73,"zipAvailable":74},[64,67,70],{"tool":65,"command":66},"npx","npx skills add mdnaimul22\u002Fhuman-skills --skill fal-ai-media",{"tool":68,"command":69},"bunx","bunx skills add mdnaimul22\u002Fhuman-skills --skill fal-ai-media",{"tool":71,"command":72},"pnpm","pnpm dlx skills add mdnaimul22\u002Fhuman-skills --skill fal-ai-media","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Faffaan-m_ECC\u002Ffal-ai-media\u002FSKILL.md",true,[],[77,85,111,133,152,167],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":84},"01M72JT3YP1SQHD0MANGDXQ4RT","higgsfield-websites","Build, edit, and deploy full-stack websites, apps and games via the Higgsfield CLI (`higgsfield website …`). Each is a React 19 + TanStack Start SSR app in one Cloudflare Worker (D1\u002FR2\u002FKV\u002FDO\u002FContainers). THREE product types, picked via `--type` on create: `website` (standalone, no Higgsfield integration — references\u002Fwebsite-flow.md), `app` (Sign in with Higgsfield + fnf SDK, Quanta — references\u002Fapp-flow.md), `game` (realtime multiplayer rooms — references\u002Fgame-flow.md). Routes to the right flow; each carries its own rules and deploy\u002Fpublish gates.\nUse when: \"build me a website\", \"make a landing page\", \"create a web app\", \"build a SaaS dashboard \u002F portfolio\", \"make me a game\", \"deploy this site\", \"publish\". Also owns GAME ART: \"make a spritesheet\", \"tileable texture\", \"animate a 3D character\", game music\u002FSFX — see the game-* references.\nNOT for: single image\u002Fvideo\u002Faudio generation (higgsfield-generate), product photos (higgsfield-product-photoshoot), marketplace cards (higgsfield-marketplace-cards).","https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Fhiggsfield-ai_skills\u002Fhiggsfield-websites\u002FSKILL.md",[],[],"2026-11-10 22:39:42",{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":103,"publishedAt":47},"01M70JPK8HAXXA85P7Q8NKZZYG","writing-skills","Use when creating new skills, editing existing skills, or verifying skills work before deployment","https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Fobra_superpowers\u002Fwriting-skills\u002FSKILL.md",[91,94,99,100],{"categoryNo":92,"categoryName":93,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":95,"categoryName":96,"taxonomyType":97,"taxonomyTypeDesc":98},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":101,"categoryName":102,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",[104,105,106,107,31,108,109,32,110],"writing","writing skills","editing","deployment","Existing","new","work",{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":122,"publishedAt":47},"01M70JP4PHBH1CQVVDWZ94W159","writing-plans","Use when you have a spec or requirements for a multi-step task, before touching code","https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Fobra_superpowers\u002Fwriting-plans\u002FSKILL.md",[117,118,119],{"categoryNo":92,"categoryName":93,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":95,"categoryName":96,"taxonomyType":97,"taxonomyTypeDesc":98},{"categoryNo":120,"categoryName":121,"taxonomyType":97,"taxonomyTypeDesc":98},"01JBSEEDCAT000000000000030","开发工程师",[104,123,124,125,32,126,127,31,128,129,130,131,132],"writing plans","plans","you","code","for","requirements","task","multi","spec","multi-step task",{"skillNo":134,"name":135,"nameZh":6,"description":136,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":137,"categories":138,"keywords":139,"publishedAt":47},"01M70JNTYVGXFZT8PASZ844TH8","verification-before-completion","Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always","https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Fobra_superpowers\u002Fverification-before-completion\u002FSKILL.md",[],[140,141,142,143,144,145,31,146,147,148,32,149,110,150,151],"verification","verification before completion","complete","about","output","assertions","prs","evidence","claim","claims","commands","running",{"skillNo":153,"name":154,"nameZh":6,"description":155,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":156,"categories":157,"keywords":159,"publishedAt":47},"01M70JNGVSQDESWN0Q5BPJ875V","using-superpowers","Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions","https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Fobra_superpowers\u002Fusing-superpowers\u002FSKILL.md",[158],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[160,161,162,163,31,32,164,165,166],"using superpowers","superpowers","conversation","how to","how","find","questions",{"skillNo":168,"name":169,"nameZh":6,"description":170,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":171,"categories":172,"keywords":173,"publishedAt":47},"01M70JN57CE588NPYPYTWH1DWG","using-git-worktrees","Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback","https:\u002F\u002Fgithub.com\u002Fmdnaimul22\u002Fhuman-skills\u002Fblob\u002Fmain\u002Fskills\u002Fstorage\u002Fobra_superpowers\u002Fusing-git-worktrees\u002FSKILL.md",[],[174,175,176,177,178,179,32,110,180,181,182,183,184,185,186,124,31,187,188],"using git worktrees","Using git","git","worktrees","git worktrees","implementation","git worktree","worktree","native","Tools","isolation","fallback","feature","via","workspace"]