[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M74AND0ZHRT18X0B4SHT9D0D":3,"skill-same:01M74AND0ZHRT18X0B4SHT9D0D":48},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":6,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":14,"categories":15,"keywords":16,"publishedAt":17,"linkOnly":18,"markdownContent":19,"markdownBody":20,"frontMatter":21,"refName":22,"commitSha":23,"skillDirectory":24,"forksCount":12,"repositoryHtmlUrl":25,"repositoryHomepageUrl":6,"ownerHtmlUrl":26,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":27,"install":28,"resources":41},"01M74AND0ZHRT18X0B4SHT9D0D","extract-video-frames",null,"aicreator350\u002FaurionOFFICIELLE","aicreator350","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F217751428?v=4","01M731QVHB22WCM6PDX5VFN1RV","01M731QVJ0TAD058M1SW9MY548",0,"MIT","https:\u002F\u002Fgithub.com\u002Faicreator350\u002FaurionOFFICIELLE\u002Fblob\u002Fmain\u002F.claude\u002F_archive\u002Fskills-batch2\u002Fextract-video-frames\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: extract-video-frames\ndescription: Extracts frames and timestamped audio segments from video files (GIF, MP4, MOV) at configurable intervals and stores them in a directory with a manifest file. Use when analyzing video content, preparing frames for visual review, extracting audio for transcription, or creating frame+audio sequences for another agent to process.\nargument-hint: [video-path] [interval-seconds] [output-dir]\n---\n\n\u003Cobjective>\nExtract frames and aligned audio segments from video files (GIF, MP4, MOV) at specified intervals using ffmpeg. Outputs PNG frames, per-segment AAC audio clips, a full continuous audio track, and a JSON manifest containing timestamps and paths -- ready for handoff to another agent for visual and audio analysis.\n\u003C\u002Fobjective>\n\n\u003Cquick_start>\nExtract frames and audio from a video:\n\n```bash\n# Extract 1 frame + audio segment per second (default)\n~\u002F.claude\u002Fskills\u002Fextract-video-frames\u002Fscripts\u002Fextract-frames.sh input.mp4\n\n# Extract 1 frame + audio segment every 2 seconds\n~\u002F.claude\u002Fskills\u002Fextract-video-frames\u002Fscripts\u002Fextract-frames.sh input.mp4 2\n\n# Specify custom output directory\n~\u002F.claude\u002Fskills\u002Fextract-video-frames\u002Fscripts\u002Fextract-frames.sh input.mp4 1 .\u002Fmy-frames\n```\n\nThe script creates:\n- `frames\u002F` directory with PNG files named `frame_001.png`, `frame_002.png`, etc.\n- `frames\u002Faudio_001.aac`, `audio_002.aac`, etc. (when audio exists, aligned 1:1 with frames)\n- `frames\u002Ffull_audio.aac` (complete audio track, when audio exists)\n- `frames\u002Fmanifest.json` with frame and audio metadata for the reviewing agent\n\u003C\u002Fquick_start>\n\n\u003Cworkflow>\n1. **Verify ffmpeg is available**\n   ```bash\n   which ffmpeg || echo \"ffmpeg not found - install with: brew install ffmpeg\"\n   ```\n\n2. **Run extraction script**\n   ```bash\n   ~\u002F.claude\u002Fskills\u002Fextract-video-frames\u002Fscripts\u002Fextract-frames.sh \u003Cvideo-path> [interval-seconds] [output-dir]\n   ```\n\n   - `video-path`: Path to GIF, MP4, or MOV file (required)\n   - `interval-seconds`: Extract one frame every N seconds (default: 1)\n   - `output-dir`: Where to store frames and audio (default: `.\u002Fframes`)\n\n3. **Review manifest**\n   The manifest.json contains:\n   ```json\n   {\n     \"source\": \"recording.mp4\",\n     \"source_path\": \"\u002Fpath\u002Fto\u002Frecording.mp4\",\n     \"interval_seconds\": 5,\n     \"total_frames\": 12,\n     \"has_audio\": true,\n     \"audio_codec\": \"aac\",\n     \"total_audio_segments\": 12,\n     \"full_audio_path\": \"full_audio.aac\",\n     \"output_directory\": \".\u002Fframes\",\n     \"frames\": [\n       {\n         \"index\": 1,\n         \"timestamp\": \"00:00:00\",\n         \"timestamp_seconds\": 0,\n         \"path\": \"frame_001.png\",\n         \"audio_path\": \"audio_001.aac\"\n       },\n       {\n         \"index\": 2,\n         \"timestamp\": \"00:00:05\",\n         \"timestamp_seconds\": 5,\n         \"path\": \"frame_002.png\",\n         \"audio_path\": \"audio_002.aac\"\n       }\n     ]\n   }\n   ```\n\n4. **Hand off to reviewing agent**\n   Pass the output directory path to the reviewing agent. The agent can read `manifest.json` to understand the frame sequence with audio alignment and use the Read tool to analyze individual frames.\n\u003C\u002Fworkflow>\n\n\u003Csupported_formats>\n- **GIF**: Animated GIFs (extracts frames; no audio stream, gracefully skipped)\n- **MP4**: Standard video format (frames + audio)\n- **MOV**: QuickTime format (frames + audio)\n- **Other**: Any format ffmpeg supports (AVI, WebM, MKV, etc.)\n\u003C\u002Fsupported_formats>\n\n\u003Coutput_structure>\n```\noutput-dir\u002F\n├── manifest.json        # Frame + audio metadata for reviewing agent\n├── full_audio.aac       # Complete audio track (when audio exists)\n├── frame_001.png        # First extracted frame\n├── frame_002.png        # Second extracted frame\n├── audio_001.aac        # Audio segment for frame 1 (when audio exists)\n├── audio_002.aac        # Audio segment for frame 2\n└── ...\n```\n\u003C\u002Foutput_structure>\n\n\u003Caudio_details>\n**Format**: AAC (.aac) -- chosen for universal compatibility, small file size, and broad tooling support.\n\n**Codec strategy**:\n- If the source audio is already AAC, segments are stream-copied (no re-encoding) for speed and quality preservation.\n- If the source audio is any other codec (e.g., PCM, MP3, Opus), segments are re-encoded to AAC at 128kbps.\n\n**Alignment semantics**: Each `audio_NNN.aac` segment covers the same time window as its corresponding `frame_NNN.png`. For a 5-second interval, `audio_001.aac` covers 0:00-0:05, `audio_002.aac` covers 0:05-0:10, etc.\n\n**No-audio handling**: When the source has no audio stream (GIFs, silent videos), `has_audio` is `false`, no audio files are created, and all `audio_path` fields in the manifest are `null`. The frame extraction works identically regardless.\n\n**Full audio track**: `full_audio.aac` contains the entire audio from the source file as a single continuous track, useful for full transcription or background listening.\n\u003C\u002Faudio_details>\n\n\u003Cagent_handoff>\nWhen passing frames and audio to another agent, include:\n\n1. **Output directory path**: Where frames and audio are stored\n2. **Manifest location**: `{output-dir}\u002Fmanifest.json`\n3. **Context**: What the reviewing agent should look for\n\nExample prompt for reviewing agent:\n```\nAnalyze the frames and audio extracted from the screen recording at .\u002Fframes.\nThe manifest at .\u002Fframes\u002Fmanifest.json lists all frames with timestamps and paired audio segments.\nThe full audio track is at .\u002Fframes\u002Ffull_audio.aac for continuous listening or transcription.\nLook for: [specific things to identify or analyze]\n```\n\nExample prompt for audio-focused agent:\n```\nTranscribe the audio segments from the recording at .\u002Fframes.\nRead .\u002Fframes\u002Fmanifest.json to get the list of audio files with timestamps.\nFor each audio_NNN.aac segment, provide a timestamped transcript.\nThe full continuous audio is also available at .\u002Fframes\u002Ffull_audio.aac.\n```\n\u003C\u002Fagent_handoff>\n\n\u003Csuccess_criteria>\nFrame and audio extraction is complete when:\n- Output directory contains PNG frames\n- `manifest.json` exists with valid frame and audio metadata\n- Frame count matches expected based on video duration and interval\n- Frames are readable by the Read tool for visual analysis\n- When source has audio: audio segments exist (1:1 with frames), `full_audio.aac` exists, `has_audio` is `true`\n- When source has no audio: `has_audio` is `false`, `audio_path` values are `null`, no audio files created\n\u003C\u002Fsuccess_criteria>\n","\u003Cobjective>\nExtract frames and aligned audio segments from video files (GIF, MP4, MOV) at specified intervals using ffmpeg. Outputs PNG frames, per-segment AAC audio clips, a full continuous audio track, and a JSON manifest containing timestamps and paths -- ready for handoff to another agent for visual and audio analysis.\n\u003C\u002Fobjective>\n\n\u003Cquick_start>\nExtract frames and audio from a video:\n\n```bash\n# Extract 1 frame + audio segment per second (default)\n~\u002F.claude\u002Fskills\u002Fextract-video-frames\u002Fscripts\u002Fextract-frames.sh input.mp4\n\n# Extract 1 frame + audio segment every 2 seconds\n~\u002F.claude\u002Fskills\u002Fextract-video-frames\u002Fscripts\u002Fextract-frames.sh input.mp4 2\n\n# Specify custom output directory\n~\u002F.claude\u002Fskills\u002Fextract-video-frames\u002Fscripts\u002Fextract-frames.sh input.mp4 1 .\u002Fmy-frames\n```\n\nThe script creates:\n- `frames\u002F` directory with PNG files named `frame_001.png`, `frame_002.png`, etc.\n- `frames\u002Faudio_001.aac`, `audio_002.aac`, etc. (when audio exists, aligned 1:1 with frames)\n- `frames\u002Ffull_audio.aac` (complete audio track, when audio exists)\n- `frames\u002Fmanifest.json` with frame and audio metadata for the reviewing agent\n\u003C\u002Fquick_start>\n\n\u003Cworkflow>\n1. **Verify ffmpeg is available**\n   ```bash\n   which ffmpeg || echo \"ffmpeg not found - install with: brew install ffmpeg\"\n   ```\n\n2. **Run extraction script**\n   ```bash\n   ~\u002F.claude\u002Fskills\u002Fextract-video-frames\u002Fscripts\u002Fextract-frames.sh \u003Cvideo-path> [interval-seconds] [output-dir]\n   ```\n\n   - `video-path`: Path to GIF, MP4, or MOV file (required)\n   - `interval-seconds`: Extract one frame every N seconds (default: 1)\n   - `output-dir`: Where to store frames and audio (default: `.\u002Fframes`)\n\n3. **Review manifest**\n   The manifest.json contains:\n   ```json\n   {\n     \"source\": \"recording.mp4\",\n     \"source_path\": \"\u002Fpath\u002Fto\u002Frecording.mp4\",\n     \"interval_seconds\": 5,\n     \"total_frames\": 12,\n     \"has_audio\": true,\n     \"audio_codec\": \"aac\",\n     \"total_audio_segments\": 12,\n     \"full_audio_path\": \"full_audio.aac\",\n     \"output_directory\": \".\u002Fframes\",\n     \"frames\": [\n       {\n         \"index\": 1,\n         \"timestamp\": \"00:00:00\",\n         \"timestamp_seconds\": 0,\n         \"path\": \"frame_001.png\",\n         \"audio_path\": \"audio_001.aac\"\n       },\n       {\n         \"index\": 2,\n         \"timestamp\": \"00:00:05\",\n         \"timestamp_seconds\": 5,\n         \"path\": \"frame_002.png\",\n         \"audio_path\": \"audio_002.aac\"\n       }\n     ]\n   }\n   ```\n\n4. **Hand off to reviewing agent**\n   Pass the output directory path to the reviewing agent. The agent can read `manifest.json` to understand the frame sequence with audio alignment and use the Read tool to analyze individual frames.\n\u003C\u002Fworkflow>\n\n\u003Csupported_formats>\n- **GIF**: Animated GIFs (extracts frames; no audio stream, gracefully skipped)\n- **MP4**: Standard video format (frames + audio)\n- **MOV**: QuickTime format (frames + audio)\n- **Other**: Any format ffmpeg supports (AVI, WebM, MKV, etc.)\n\u003C\u002Fsupported_formats>\n\n\u003Coutput_structure>\n```\noutput-dir\u002F\n├── manifest.json        # Frame + audio metadata for reviewing agent\n├── full_audio.aac       # Complete audio track (when audio exists)\n├── frame_001.png        # First extracted frame\n├── frame_002.png        # Second extracted frame\n├── audio_001.aac        # Audio segment for frame 1 (when audio exists)\n├── audio_002.aac        # Audio segment for frame 2\n└── ...\n```\n\u003C\u002Foutput_structure>\n\n\u003Caudio_details>\n**Format**: AAC (.aac) -- chosen for universal compatibility, small file size, and broad tooling support.\n\n**Codec strategy**:\n- If the source audio is already AAC, segments are stream-copied (no re-encoding) for speed and quality preservation.\n- If the source audio is any other codec (e.g., PCM, MP3, Opus), segments are re-encoded to AAC at 128kbps.\n\n**Alignment semantics**: Each `audio_NNN.aac` segment covers the same time window as its corresponding `frame_NNN.png`. For a 5-second interval, `audio_001.aac` covers 0:00-0:05, `audio_002.aac` covers 0:05-0:10, etc.\n\n**No-audio handling**: When the source has no audio stream (GIFs, silent videos), `has_audio` is `false`, no audio files are created, and all `audio_path` fields in the manifest are `null`. The frame extraction works identically regardless.\n\n**Full audio track**: `full_audio.aac` contains the entire audio from the source file as a single continuous track, useful for full transcription or background listening.\n\u003C\u002Faudio_details>\n\n\u003Cagent_handoff>\nWhen passing frames and audio to another agent, include:\n\n1. **Output directory path**: Where frames and audio are stored\n2. **Manifest location**: `{output-dir}\u002Fmanifest.json`\n3. **Context**: What the reviewing agent should look for\n\nExample prompt for reviewing agent:\n```\nAnalyze the frames and audio extracted from the screen recording at .\u002Fframes.\nThe manifest at .\u002Fframes\u002Fmanifest.json lists all frames with timestamps and paired audio segments.\nThe full audio track is at .\u002Fframes\u002Ffull_audio.aac for continuous listening or transcription.\nLook for: [specific things to identify or analyze]\n```\n\nExample prompt for audio-focused agent:\n```\nTranscribe the audio segments from the recording at .\u002Fframes.\nRead .\u002Fframes\u002Fmanifest.json to get the list of audio files with timestamps.\nFor each audio_NNN.aac segment, provide a timestamped transcript.\nThe full continuous audio is also available at .\u002Fframes\u002Ffull_audio.aac.\n```\n\u003C\u002Fagent_handoff>\n\n\u003Csuccess_criteria>\nFrame and audio extraction is complete when:\n- Output directory contains PNG frames\n- `manifest.json` exists with valid frame and audio metadata\n- Frame count matches expected based on video duration and interval\n- Frames are readable by the Read tool for visual analysis\n- When source has audio: audio segments exist (1:1 with frames), `full_audio.aac` exists, `has_audio` is `true`\n- When source has no audio: `has_audio` is `false`, `audio_path` values are `null`, no audio files created\n\u003C\u002Fsuccess_criteria>\n",{},"main","5593cf3c72898ea9fc67225d452fe38f866ba6dd",".claude\u002F_archive\u002Fskills-batch2\u002Fextract-video-frames","https:\u002F\u002Fgithub.com\u002Faicreator350\u002FaurionOFFICIELLE","https:\u002F\u002Fgithub.com\u002Faicreator350","2026-05-18 03:39:30",{"source":7,"skillName":5,"commands":29,"prompt":39,"zipAvailable":40},[30,33,36],{"tool":31,"command":32},"npx","npx skills add aicreator350\u002FaurionOFFICIELLE --skill extract-video-frames",{"tool":34,"command":35},"bunx","bunx skills add aicreator350\u002FaurionOFFICIELLE --skill extract-video-frames",{"tool":37,"command":38},"pnpm","pnpm dlx skills add aicreator350\u002FaurionOFFICIELLE --skill extract-video-frames","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Faicreator350\u002FaurionOFFICIELLE\u002Fblob\u002Fmain\u002F.claude\u002F_archive\u002Fskills-batch2\u002Fextract-video-frames\u002FSKILL.md",true,[42],{"path":43,"resourceType":44,"resourceTypeDesc":45,"sizeBytes":46,"sourceHtmlUrl":47},"scripts\u002Fextract-frames.sh","SCRIPT","脚本",5750,"https:\u002F\u002Fgithub.com\u002Faicreator350\u002FaurionOFFICIELLE\u002Fblob\u002Fmain\u002F.claude\u002F_archive\u002Fskills-batch2\u002Fextract-video-frames\u002Fscripts\u002Fextract-frames.sh",[49,58,65,72,79,86],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":6,"repositoryNo":11,"starsCount":12,"licenseSpdxId":53,"licenseFileUrl":54,"sourceHtmlUrl":55,"categories":56,"keywords":57,"publishedAt":17},"01M74CAJWR9WB6DX1HF2V461Y0","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Faicreator350\u002FaurionOFFICIELLE\u002Fblob\u002Fmain\u002Fskills\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Faicreator350\u002FaurionOFFICIELLE\u002Fblob\u002Fmain\u002Fskills\u002Fwebapp-testing\u002FSKILL.md",[],[],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":6,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":17},"01M74CAFWC2H75GJ81B39C9RSW","web-design-guidelines","Review UI code for Web Interface Guidelines compliance. Use when asked to \"review my UI\", \"check accessibility\", \"audit design\", \"review UX\", or \"check my site against best practices\".","https:\u002F\u002Fgithub.com\u002Faicreator350\u002FaurionOFFICIELLE\u002Fblob\u002Fmain\u002Fskills\u002Fweb-design-guidelines\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":6,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":17},"01M74CA9N2HTGCKJ93AE9NQMHA","vercel-react-view-transitions","Guide for implementing smooth, native-feeling animations using React's View Transition API (`\u003CViewTransition>` component, `addTransitionType`, and CSS view transition pseudo-elements). Use this skill whenever the user wants to add page transitions, animate route changes, create shared element animations, animate enter\u002Fexit of components, animate list reorder, implement directional (forward\u002Fback) navigation animations, or integrate view transitions in Next.js. Also use when the user mentions view transitions, `startViewTransition`, `ViewTransition`, transition types, or asks about animating between UI states in React without third-party animation libraries.","https:\u002F\u002Fgithub.com\u002Faicreator350\u002FaurionOFFICIELLE\u002Fblob\u002Fmain\u002Fskills\u002Fvercel-react-view-transitions\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":6,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":17},"01M74CA364D4EVDXZZQRVK1Z73","vercel-react-best-practices","React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React\u002FNext.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.","https:\u002F\u002Fgithub.com\u002Faicreator350\u002FaurionOFFICIELLE\u002Fblob\u002Fmain\u002Fskills\u002Fvercel-react-best-practices\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":6,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":17},"01M74C9YQZX1GVS18V0AYCYPZE","vercel-composition-patterns","React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.","https:\u002F\u002Fgithub.com\u002Faicreator350\u002FaurionOFFICIELLE\u002Fblob\u002Fmain\u002Fskills\u002Fvercel-composition-patterns\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":6,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":17},"01M74C9SEYD6F764Q1JACZX3A6","vercel-cli-with-tokens","Deploy and manage projects on Vercel using token-based authentication. Use when working with Vercel CLI using access tokens rather than interactive login — e.g. \"deploy to vercel\", \"set up vercel\", \"add environment variables to vercel\".","https:\u002F\u002Fgithub.com\u002Faicreator350\u002FaurionOFFICIELLE\u002Fblob\u002Fmain\u002Fskills\u002Fvercel-cli-with-tokens\u002FSKILL.md",[],[]]