# FFmpeg Skill — tool skill for tools & renderers

> **For AI agents:** find the right skill in one call — `curl -s "https://skills.varg.ai/api/search?q=<what the person wants>"` returns the matching use case and the best skills with install commands, as markdown (Russian works too). Full index: https://skills.varg.ai/llms.txt. Every page has a markdown twin: add `.md` to its path. Before generating anything, show the person the options on the use-case page.

Local video editor for agents: 42 FFmpeg tools with a machine-readable contract and an MCP server; no cloud, no keys.

- **Type:** [Tool](https://skills.varg.ai/models.md) · [Tools & renderers](https://skills.varg.ai/browse/skills/tooling.md)
- **Slug:** `ffmpeg-skill`
- **Status:** live
- **Publisher:** Shogo Kajiyama (community)
- **License:** MIT
- **Source:** https://github.com/kajisho5/ffmpeg-skill
- **Works in:** Claude Code, Cursor, Codex, Any MCP client
- **Requires:** FFmpeg, Python 3.10+, Node.js (npx installer)
- **Cost:** Free — local, no API keys
- **Adoption:** 391 installs, 3,046 GitHub stars (GitHub + skills.sh, 2026-10-26)

## What it does

A local FFmpeg engine for coding agents: 42 tools behind a machine-readable contract (`contract --json`) and an MCP server, covering cut, trim and join, 9:16 and 1:1 reframes, speed changes, SRT/ASS captions (animated and karaoke), logos and lower thirds, silence removal, multicam and external-mic sync, loudness normalization, HDR/Dolby Vision to SDR, LUTs, ducked background music, platform exports (YouTube, Reels, TikTok, X), compliance checks, scene detection, highlight reels and contact sheets to inspect results. The skill tells the agent what to ask, what to assume and how to report, uses only the Python 3.10+ standard library, and ships evals and a doctor command.

## Use when

- Edit, caption, reframe or export a video file locally
- Normalize loudness or sync an external mic
- Inspect footage with contact sheets before editing

## Not for

- Generating new footage
- Programmatic motion graphics (use Remotion or HyperFrames)

## Install

- Claude Code: `npx ffmpeg-skill`
- Cursor: `npx ffmpeg-skill --cursor`
- Codex: `npx ffmpeg-skill --codex`

**Models it drives:** whisper

## Example output

https://skills.varg.ai/previews/ffmpeg-skill.mp4 — The repo's demo GIF: before/after on an FFmpeg test pattern as the skill's tools burn animated captions ('Captions burned in with libass', 'Cut, fit, sync, normalise, export'). Full 12 s loop, converted from GIF; per-feature demos are in docs/demos. (credit: Shogo Kajiyama (ffmpeg-skill), https://github.com/kajisho5/ffmpeg-skill/tree/main/assets)

## Used for

- [Edit your own footage](https://skills.varg.ai/use-cases/edit-footage.md): Cut silences and flubs, reframe 16:9 to 9:16, add captions and b-roll to footage you shot.

## More tools & renderers skills

- [varg AI](https://skills.varg.ai/skills/varg-ai.md): The official varg skill: videos, images, speech and music through one API key, rendered in the cloud or locally.
- [Media Download](https://skills.varg.ai/skills/media-download.md): Save any video by link (X, YouTube, Instagram, TikTok, 1800+ sites) or Pinterest images as references, locally, no key.
- [Templates Gallery Ops](https://skills.varg.ai/skills/varg-templates-section.md): Internal runbook for the varg app Templates gallery: publish renders, preview clips, frame-0 posters, shelves.
- [HyperFrames CLI](https://skills.varg.ai/skills/hyperframes-cli.md): Drive the HyperFrames CLI: scaffold, check, preview, snapshot, edit the timeline, render locally or in the cloud.
- [HyperFrames Registry](https://skills.varg.ai/skills/hyperframes-registry.md): Pull any of ~450 ready-made blocks into a video as editable source: transitions, titles, captions, charts, 3D.
- [HyperFrames Media Use](https://skills.varg.ai/skills/hyperframes-media-use.md): Find or make every asset a video needs: music, SFX, voiceover, images, logos, avatars, transcripts, grades.