Ffmpeg Analyse Video

This takes a video file and gives you a timestamped breakdown of what happens in it. The clever bit is the sub-agent architecture: instead of jamming dozens of frame images into your main context window, it spawns disposable agents that each analyze a batch of 8-10 frames and write text descriptions to markdown files. The main agent only reads those lightweight text files and synthesizes the final timeline, cutting context usage by roughly 90%. Works for screen recordings, tutorials, presentations, whatever. It handles duration intelligently, using scene detection for short videos and keyframe extraction for longer ones, with fallbacks when strategies fail. You need ffmpeg installed locally.

skills.sh installs: 1.7K
GitHub stars: 37
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add fabriqaai/ffmpeg-analyse-video-skill --skill ffmpeg-analyse-video --agent claude-code

Installs into .claude/skills of the current project.

Files

FFmpeg Video Analysis

Extract frames from video files with ffmpeg. Delegate frame reading to sub-agents to preserve the main context window. Synthesise a structured timestamped summary from text-only sub-agent reports.

Architecture: Context-Efficient Sub-Agent Pipeline

Problem: Reading dozens of images into the main conversation context consumes most of the context window, leaving little room for synthesis and follow-up.

Solution: A 3-phase pipeline:

Main Agent                          Sub-Agents (disposable context)
──────────                          ──────────────────────────────
1. ffprobe metadata        ───►
2. ffmpeg frame extraction ───►
3. Split frames into batches ──►   4. Read images (vision)
                                      Write text descriptions
                                      to batch_N_analysis.md
5. Read text files only    ◄───    (context discarded)
6. Synthesise final output

Images only ever exist inside sub-agent contexts. The main agent only reads lightweight text files. This cuts context usage by ~90%.