Discover the toolingbehind modern intelligence
The operating system for AI infrastructure discovery. Search a live map of MCP servers, AI agents, LLM tools, automation systems, and developer infrastructure.
ffmpeg-analyse-video-skill
Claude Code skill: analyse video content by extracting frames with ffmpeg and using AI vision to generate timestamped summaries
10stars
1forks
Quality signals
StaleNo testsNo CIThin docsNo licenseNew
AI summary
Auto-generated overview of what this skill does and when to reach for it.
Extract frames from videos with ffmpeg and generate AI-powered timestamped summaries of visual content.
Use this when
- Need to index or search video files by visual content
- Building AI tools that process raw video data
- Creating automated video summaries or transcripts
- Debugging computer vision pipelines with real footage
- Extracting keyframes for training datasets
Don't use when
- Working with audio-only files
- Need real-time video processing
- Requiring exact frame-perfect accuracy
Capabilities
- Extracts frames from videos using ffmpeg
- Generates AI vision summaries of visual content
- Produces timestamped summaries of video frames
- Handles common video formats (MP4, AVI, etc.)
- Outputs structured JSON with frame timestamps and descriptions
InstallSKILLInstall as a Claude Code skill
Universal installANY TOOL
$ npx skillcity@latest fabriqaai/ffmpeg-analyse-video-skillAuto-detects the skill or MCP server in this repo and installs it for Claude Code, Codex, Cursor, Cline, OpenCode, Gemini CLI, Anti-Gravity, OpenClaw and Hermes.
Requires Node.js 18+ (ships with npx).
Or install manually
# Install into ~/.claude/skills/ mkdir -p ~/.claude/skills/ffmpeg-analyse-video-skill curl -fsSL https://raw.githubusercontent.com/fabriqaai/ffmpeg-analyse-video-skill/main/SKILL.md -o ~/.claude/skills/ffmpeg-analyse-video-skill/SKILL.md
Loading README…
Ask a simulated agent to run this skill. It loads the real SKILL.md and reasons over your task with NVIDIA.
ffmpeg-analyse-video-skill — sandboxAI sandbox
Pick a quick prompt below or type your own — watch the agent execute this skill step by step.
guest@skillcity:~$Try a prompt