[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-136":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":9,"language":10,"languages":9,"totalLinesOfCode":9,"stars":11,"forks":12,"watchers":4,"openIssues":13,"contributorsCount":14,"subscribersCount":14,"size":14,"stars1d":15,"stars7d":16,"stars30d":17,"stars90d":14,"forks30d":14,"starsTrendScore":18,"compositeScore":19,"rankGlobal":9,"rankLanguage":9,"license":20,"archived":21,"fork":21,"defaultBranch":22,"hasWiki":23,"hasPages":21,"topics":24,"createdAt":9,"pushedAt":9,"updatedAt":25,"readmeContent":26,"aiSummary":27,"trendingCount":14,"starSnapshotCount":14,"syncStatus":28,"lastSyncTime":29,"discoverSource":30},136,"clipify","louisedesadeleer\u002Fclipify","louisedesadeleer","Claude Code skill: turn long videos into social-ready clips. Auto-find funny moments, cut, reframe to 9:16 with face-tracking, and burn opus-style captions.",null,"Python",422,40,1,0,11,18,106,33,4.84,"MIT License",false,"main",true,[],"2026-06-12 02:00:08","# Clipify\n\nA [Claude Code](https:\u002F\u002Fclaude.com\u002Fclaude-code) skill that turns long videos into social-ready clips.\n\n![Clipify turns long videos into 9:16 social clips](assets\u002Fpreview.png)\n\nPoint it at any video file and it will:\n\n1. **Find clip-worthy segments** — transcribes the video with [Whisper](https:\u002F\u002Fgithub.com\u002Fopenai\u002Fwhisper) and scans the transcript for punchlines, reversals, awkward pauses, and audio peaks to propose 3–5 candidates.\n2. **Create a 9:16 clip** — cuts your chosen moment, then reframes 16:9 → 9:16 with hard-cut pans that follow whoever is speaking (or split-screen if you'd rather see both faces).\n3. **Add subtitles** — burns opus-style word-by-word captions (big bold white, yellow active-word highlight).\n\nNo cloud APIs. Runs entirely on your machine. No OpenCV. ~20s of work for a 20s clip on Apple Silicon.\n\n## Why this exists\n\nMost \"auto-clip\" tools are either expensive SaaS, slow, or produce slop. This skill is what I actually use to clip my long-form videos for LinkedIn and TikTok. Built for talking-head dialogue (interviews, podcasts, two-person setups).\n\n## Requirements\n\n- macOS (uses VideoToolbox for hardware-accelerated decode — works on Linux\u002FWindows if you remove `-hwaccel videotoolbox` flags)\n- [Claude Code](https:\u002F\u002Fclaude.com\u002Fclaude-code)\n- `ffmpeg` with `libx264` (`brew install ffmpeg`)\n- [`whisper`](https:\u002F\u002Fgithub.com\u002Fopenai\u002Fwhisper) (`pip install openai-whisper`)\n- Python 3 with `numpy` (`pip install numpy`)\n\n## Install\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Flouisedesadeleer\u002Fclipify.git ~\u002F.claude\u002Fskills\u002Fclipify\n```\n\nThat's it. Restart Claude Code and `\u002Fclipify` is available as a slash command.\n\n## Usage\n\nIn Claude Code:\n\n```\n\u002Fclipify\n```\n\nThen paste a video file path when asked. The skill will:\n\n1. Transcribe → propose 3–5 funny candidate clips with timestamps and titles\n2. Ask which to cut\n3. Ask 9:16 \u002F 16:9 \u002F 1:1\n4. If 9:16 from 16:9 with two faces: ask pan vs split-screen\n5. Ask subtitle style (opus \u002F karaoke \u002F minimal — or paste a reference image to match)\n6. Render and open the result\n\nFinal clips land in `\u003Csource-video-dir>\u002Fclipify_out\u002F`.\n\n## How the face-pan works\n\nNo face detection model. Camera is static within a single clip, so:\n\n1. Eyeball each face's mouth+chin area as a rectangle on one sample frame.\n2. ffmpeg computes per-frame motion energy in each rectangle using frame differencing.\n3. Whichever rectangle has more motion at a given moment = that's the speaker.\n4. Build a hard-cut x-coordinate expression from the speaker timeline.\n5. Crop a vertical strip from the source that follows whoever's talking.\n\nTotal cost: a few seconds of ffmpeg per clip. Works surprisingly well.\n\n## Repo structure\n\n```\nclipify\u002F\n├── SKILL.md           # the skill prompt Claude Code reads\n├── scripts\u002F\n│   ├── analyze.py     # speaker timeline from two ROI motion files\n│   ├── build_pan.py   # ffmpeg crop x-expression with hard cuts\n│   ├── build_ass.py   # opus\u002Fkaraoke\u002Fminimal ASS captions from whisper JSON\n│   └── audio_align.py # find offset of a sub-clip in a longer source\n└── README.md\n```\n\n## License\n\nMIT — see [LICENSE](LICENSE).\n\nBuilt by [Louise de Sadeleer](https:\u002F\u002Fgithub.com\u002Flouisedesadeleer), Growth at [Tella](https:\u002F\u002Ftella.tv).\n","Clipify 是一个将长视频转换为适合社交媒体发布的短片的工具。它通过自动识别有趣片段、剪辑并重新构图至9:16格式，并添加字幕来实现这一功能，过程中使用了Whisper进行语音转文字以识别潜在的精彩时刻。该工具特别适用于对话类内容如访谈或播客的剪辑工作，能够智能地追踪说话者的面部，确保视频始终聚焦于当前发言者。整个处理流程完全在本地运行，无需调用云端API，保证了数据的安全性和处理速度。对于希望高效制作高质量短视频内容发布到平台如LinkedIn和TikTok的内容创作者来说，Clipify是一个非常实用的选择。",2,"2026-06-11 02:31:03","CREATED_QUERY"]