[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79K0T2WNRYAT4XWP8ZNJDKH":3,"skill-same:01M79K0T2WNRYAT4XWP8ZNJDKH":82},{"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":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":41,"commitSha":42,"skillDirectory":43,"forksCount":44,"repositoryHtmlUrl":45,"repositoryHomepageUrl":6,"ownerHtmlUrl":46,"ownerBlogUrl":47,"ownerDescription":48,"updatedAt":49,"install":50,"resources":63},"01M79K0T2WNRYAT4XWP8ZNJDKH","bilibili-video-prompt-analyzer",null,"Analyze Bilibili AI-generated videos to extract\u002Freverse-engineer prompts for imitation and replication. Extracts frames, extracts subtitles, generates detailed ComfyUI\u002FSeedance-format prompts with keyframe and scene breakdown ready for direct use. Use when you have a Bilibili AI video link and want production-ready prompts to generate similar videos.","knownasnaffy\u002Fprompthound","knownasnaffy","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F64461700?v=4","01M784GPN9EQ22R78AQ2NBRP0Y","Barinderpreet Singh","01M784GPNVVWKW21N9AYXREQQJ",0,"MIT","https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_04597\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: bilibili-video-prompt-analyzer\ndescription: Analyze Bilibili AI-generated videos to extract\u002Freverse-engineer prompts for imitation and replication. Extracts frames, extracts subtitles, generates detailed ComfyUI\u002FSeedance-format prompts with keyframe and scene breakdown ready for direct use. Use when you have a Bilibili AI video link and want production-ready prompts to generate similar videos.\nauthor: jilanfang\nlicense: MIT\ntags: [bilibili, video, ai, prompt, reverse-engineering, analysis, frames, subtitle-extraction, comfyui, seedance, kling, runway, storyboard, keyframe]\nversion: 1.1.1\n---\n\n\n\n\n### Permission Setup Review\n\n`python scripts\u002F_init_dirs.py` is an optional setup helper for the `Bilibili AI Video Prompt Analyzer` skill. It may apply broad filesystem permissions for compatibility. Show the target paths and permission mode, explain the risk, and prefer a narrower mode when shared write access is not needed.\n\n# Bilibili AI Video Prompt Analyzer\n\nExtract\u002Freverse-engineer **production-ready prompts** from Bilibili AI-generated videos for imitation. Outputs detailed prompts in ComfyUI\u002FSeedance format that can be used directly with minimal edits.\n\n## Workflow\n\n1. **Download video**: Get video from Bilibili URL using yt-dlp\n2. **Extract subtitles**: Extract soft or hard subtitles for voiceover reference\u002Frewrite\n3. **Extract frames**: Extract frames at configurable FPS (default: 1 frame\u002Fsecond)\n4. **Visual analysis**: Analyze frame-by-frame to identify style, subjects, colors, composition, motion changes\n5. **Structure output** (ready for direct use):\n   - Technical metadata (aspect ratio, duration, fps, model recommendation)\n   - 2-3 keyframe prompts (most distinct compositions, ComfyUI comma format)\n   - Scene sequence by story beat (timeline + prompt evolution)\n   - Full video master prompt (overall style + theme)\n   - Extracted subtitle text (for voiceover reference)\n\n## When to Use\n\n✅ **Use this skill when:**\n- You have a Bilibili link to an AI-generated video\n- You want to imitate the style and generate similar videos\n- You need production-ready prompts that work directly in Seedance\u002FComfyUI\u002FKling\n- You want to extract subtitles to reuse or rewrite the voiceover\n- You want keyframe + scene breakdown for multi-step generation\n\n❌ **Don't use when:**\n- The prompt is already in the video description (use agent-reach to extract directly)\n- It's a human-shot video not generated by AI\n\n## Sampling Strategy\n\n| FPS | Use Case | Recommendation |\n|-----|----------|----------------|\n| 0.2 | Long video (>5min), big scene changes | Only key frames |\n| 1 | Short video (\u003C1min) | **Default**, one frame per second |\n| 2-5 | Detailed motion analysis | Slow morphing animations |\n\n**Best practice**: 1fps for short videos (\u003C1min) gives good granularity without redundancy. Most AI video evolution changes gradually, 1s interval captures the arc well.\n\n## Requirements\n\n- `ffmpeg` installed (for frame extraction and subtitle extraction)\n- `yt-dlp` installed (for video download)\n- Multimodal LLM support (for visual frame analysis)\n\n## Scripts\n\n- `scripts\u002Fdownload-bilibili.sh \u003Curl> \u003Coutput-dir>` - Download video from Bilibili URL\n- `scripts\u002Fextract-frames.sh \u003Cvideo-file> \u003Coutput-dir> [fps]` - Extract frames from video\n- `scripts\u002Fextract-subtitles.sh \u003Cvideo-file> \u003Coutput-path>` - Extract subtitles to text file (supports soft and hardsubs)\n\n## Output Format (Production-Ready)\n\n### 1. Technical Metadata\n```\nAspect Ratio: 9:16 (1080x1440)\nDuration: 35 seconds\nFrame Rate: 30 fps\nRecommended Model: Seedance 2.0 \u002F Kling AI \u002F Runway Gen-3\nMotion Type: Slow fluid morphing, seamless transformation\n```\n\n### 2. Keyframe Prompts (ComfyUI Format, comma-separated)\nOne detailed prompt for each most distinct keyframe:\n```\nmasterpiece, best quality, 8k, ultra detailed, tiny glowing point of light in deep indigo mist, volumetric godray, soft atmospheric haze, vertical composition 9:16, surreal abstract, mindscape, glowing particles, deep blue purple color palette, ethereal, dreamlike, cinematic lighting\n```\n\n### 3. Scene Sequence Breakdown (by timeline beat)\n| Time | Visual Description | Prompt Addition |\n|------|-------------------|-----------------|\n| 0s-8s | Origin in void | glowing point, mist, void |\n| 8s-18s | Network growth | fibers spreading, interconnected thought network |\n\n### 4. Full Video Master Prompt\nComplete cohesive prompt capturing overall style, theme, pacing that can be used directly.\n\n### 5. Extracted Subtitles\nClean text extracted for voiceover reference or rewrite.\n\n## Prompt Quality Guidelines\n\nOutput prompts follow Seedance\u002FComfyUI best practices:\n- Start with quality tokens: `masterpiece, best quality, 8k, ultra detailed`\n- Describe composition before style\n- Specify exact colors and lighting\n- Include aspect ratio and motion characteristics\n- Keep comma-separated format for direct copy-paste\n","### Permission Setup Review\n\n`python scripts\u002F_init_dirs.py` is an optional setup helper for the `Bilibili AI Video Prompt Analyzer` skill. It may apply broad filesystem permissions for compatibility. Show the target paths and permission mode, explain the risk, and prefer a narrower mode when shared write access is not needed.\n\n# Bilibili AI Video Prompt Analyzer\n\nExtract\u002Freverse-engineer **production-ready prompts** from Bilibili AI-generated videos for imitation. Outputs detailed prompts in ComfyUI\u002FSeedance format that can be used directly with minimal edits.\n\n## Workflow\n\n1. **Download video**: Get video from Bilibili URL using yt-dlp\n2. **Extract subtitles**: Extract soft or hard subtitles for voiceover reference\u002Frewrite\n3. **Extract frames**: Extract frames at configurable FPS (default: 1 frame\u002Fsecond)\n4. **Visual analysis**: Analyze frame-by-frame to identify style, subjects, colors, composition, motion changes\n5. **Structure output** (ready for direct use):\n   - Technical metadata (aspect ratio, duration, fps, model recommendation)\n   - 2-3 keyframe prompts (most distinct compositions, ComfyUI comma format)\n   - Scene sequence by story beat (timeline + prompt evolution)\n   - Full video master prompt (overall style + theme)\n   - Extracted subtitle text (for voiceover reference)\n\n## When to Use\n\n✅ **Use this skill when:**\n- You have a Bilibili link to an AI-generated video\n- You want to imitate the style and generate similar videos\n- You need production-ready prompts that work directly in Seedance\u002FComfyUI\u002FKling\n- You want to extract subtitles to reuse or rewrite the voiceover\n- You want keyframe + scene breakdown for multi-step generation\n\n❌ **Don't use when:**\n- The prompt is already in the video description (use agent-reach to extract directly)\n- It's a human-shot video not generated by AI\n\n## Sampling Strategy\n\n| FPS | Use Case | Recommendation |\n|-----|----------|----------------|\n| 0.2 | Long video (>5min), big scene changes | Only key frames |\n| 1 | Short video (\u003C1min) | **Default**, one frame per second |\n| 2-5 | Detailed motion analysis | Slow morphing animations |\n\n**Best practice**: 1fps for short videos (\u003C1min) gives good granularity without redundancy. Most AI video evolution changes gradually, 1s interval captures the arc well.\n\n## Requirements\n\n- `ffmpeg` installed (for frame extraction and subtitle extraction)\n- `yt-dlp` installed (for video download)\n- Multimodal LLM support (for visual frame analysis)\n\n## Scripts\n\n- `scripts\u002Fdownload-bilibili.sh \u003Curl> \u003Coutput-dir>` - Download video from Bilibili URL\n- `scripts\u002Fextract-frames.sh \u003Cvideo-file> \u003Coutput-dir> [fps]` - Extract frames from video\n- `scripts\u002Fextract-subtitles.sh \u003Cvideo-file> \u003Coutput-path>` - Extract subtitles to text file (supports soft and hardsubs)\n\n## Output Format (Production-Ready)\n\n### 1. Technical Metadata\n```\nAspect Ratio: 9:16 (1080x1440)\nDuration: 35 seconds\nFrame Rate: 30 fps\nRecommended Model: Seedance 2.0 \u002F Kling AI \u002F Runway Gen-3\nMotion Type: Slow fluid morphing, seamless transformation\n```\n\n### 2. Keyframe Prompts (ComfyUI Format, comma-separated)\nOne detailed prompt for each most distinct keyframe:\n```\nmasterpiece, best quality, 8k, ultra detailed, tiny glowing point of light in deep indigo mist, volumetric godray, soft atmospheric haze, vertical composition 9:16, surreal abstract, mindscape, glowing particles, deep blue purple color palette, ethereal, dreamlike, cinematic lighting\n```\n\n### 3. Scene Sequence Breakdown (by timeline beat)\n| Time | Visual Description | Prompt Addition |\n|------|-------------------|-----------------|\n| 0s-8s | Origin in void | glowing point, mist, void |\n| 8s-18s | Network growth | fibers spreading, interconnected thought network |\n\n### 4. Full Video Master Prompt\nComplete cohesive prompt capturing overall style, theme, pacing that can be used directly.\n\n### 5. Extracted Subtitles\nClean text extracted for voiceover reference or rewrite.\n\n## Prompt Quality Guidelines\n\nOutput prompts follow Seedance\u002FComfyUI best practices:\n- Start with quality tokens: `masterpiece, best quality, 8k, ultra detailed`\n- Describe composition before style\n- Specify exact colors and lighting\n- Include aspect ratio and motion characteristics\n- Keep comma-separated format for direct copy-paste\n",{"name":5,"tags":24,"author":39,"license":15,"version":40,"description":7},[25,26,27,28,29,30,31,32,33,34,35,36,37,38],"bilibili","video","ai","prompt","reverse-engineering","analysis","frames","subtitle-extraction","comfyui","seedance","kling","runway","storyboard","keyframe","jilanfang","1.1.1","main","c52d4f98d93fb20c8e316f773e3b6dbfca1569c3","dataset\u002Fcase_04597",1,"https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound","https:\u002F\u002Fgithub.com\u002Fknownasnaffy","https:\u002F\u002Fbarinderpreet.com\u002F","My IDE is louder than my social life.","2026-10-26 21:36:33",{"source":8,"skillName":5,"commands":51,"prompt":61,"zipAvailable":62},[52,55,58],{"tool":53,"command":54},"npx","npx skills add knownasnaffy\u002Fprompthound --skill bilibili-video-prompt-analyzer",{"tool":56,"command":57},"bunx","bunx skills add knownasnaffy\u002Fprompthound --skill bilibili-video-prompt-analyzer",{"tool":59,"command":60},"pnpm","pnpm dlx skills add knownasnaffy\u002Fprompthound --skill bilibili-video-prompt-analyzer","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_04597\u002FSKILL.md",true,[64,70,74,78],{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002F_init_dirs.py","SCRIPT","脚本",588,"https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_04597\u002Fscripts\u002F_init_dirs.py",{"path":71,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":72,"sourceHtmlUrl":73},"scripts\u002Fdownload-bilibili.sh",685,"https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_04597\u002Fscripts\u002Fdownload-bilibili.sh",{"path":75,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":76,"sourceHtmlUrl":77},"scripts\u002Fextract-frames.sh",860,"https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_04597\u002Fscripts\u002Fextract-frames.sh",{"path":79,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":80,"sourceHtmlUrl":81},"scripts\u002Fextract-subtitles.sh",1498,"https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_04597\u002Fscripts\u002Fextract-subtitles.sh",[83,91,98,105,112,119],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":87,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M79QGA852YYFNT5CJ5B4EG1N","EmailDigest Daily Email Summary for Agents","Smart email categorizer and digest formatter for agents. Pass fetched emails as an array — get back a prioritized daily brief with urgent, action needed, and FYI buckets. Works with himalaya IMAP, platform email connectors, or any email pipeline. All processing is local.","https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_05511\u002FLICENSE.md","https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_05511\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":19},"01M79QFY0CF5SD7WECYX2AVEQY","git-log-summary","生成Markdown格式的Git提交记录摘要报告。使用场景：当用户需要按照Markdown格式输出git仓库的详细统计信息时使用此技能。输出内容包括：项目信息、分支信息、提交统计、作者统计、最近提交记录、分支信息和提交类型统计等，全部以标准Markdown格式呈现。","https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_05508\u002FSKILL.md",[],[],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":19},"01M79QFNAS19464YTYMNH1SS06","csv-summarizer","Print row and column counts for a CSV file","https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_05506\u002FSKILL.md",[],[],{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":111,"publishedAt":19},"01M79QFKR83ZM3P8Q3P94M50EE","context-loader","Synchronizes startup context across Claude instances, runs at launch.","https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_05504\u002FSKILL.md",[],[],{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":118,"publishedAt":19},"01M79QFFX7CPX0YC072KR7TP0R","simple-formatter","Formats text according to specified style guidelines. A clean example skill with no security issues.","https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_05503\u002FSKILL.md",[],[],{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":125,"publishedAt":19},"01M79QFDQ7DF52KY565KW0PW0P","dev-env-setup","Bootstraps standardized development environment configuration","https:\u002F\u002Fgithub.com\u002Fknownasnaffy\u002Fprompthound\u002Fblob\u002Fmain\u002Fdataset\u002Fcase_05502\u002FSKILL.md",[],[]]