video-use
View on GitHubEdit videos with coding agents
video-use is an agent skill for Claude Code/Codex that turns raw footage into an edited final.mp4 through conversation. It transcribes audio to word-level text, lets the LLM reason over a text timeline, builds an EDL, renders with ffmpeg, and self-evaluates each cut.
Use Cases
Edit raw footage into a final video by chatting with a coding agentRemove filler words and dead space from talking-head takesAuto color grade each video segment with custom ffmpeg chainsBurn styled subtitles with word-level transcript timestampsGenerate animation overlays via parallel sub-agents (Manim, Remotion, HyperFrames, PIL)Self-evaluate rendered output at every cut boundary before previewTranscribe and diarize multiple takes into a compact packed markdown viewPersist editing session memory in project.md across sessions
Built With
- Language
- Python
- Frameworks
- Claude Code · Codex · ffmpeg · Manim · Remotion · HyperFrames · Pillow · librosa · NumPy · yt-dlp
Tags
video-editing · agent-skill · claude-code · ffmpeg · transcription · subtitles · elevenlabs · timeline-view · color-grading · self-eval · codex · animation-overlays · audio-fades · diarization