kajisho5

    kajisho5/ffmpeg-skill

    Local video editor for coding agents: 42 FFmpeg tools with a machine-readable contract and an MCP server, for Claude Code, Cursor and Codex. Cut, captions, reframe, loudness, platform exports. No cloud, no API keys.

    ai-agents
    agent-skills
    audio-processing
    captions
    claude-code
    codex
    Python
    MIT
    4.5K stars
    361 forks
    4.5K GitHub watchers
    Updated Nov 5, 2026
    View on GitHub

    Build with Backblaze B2

    SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.

    Explore Backblaze Labs

    Loading star history...

    Where it stands

    Rank, growth pace and release cadence relative to everything GStars tracks.

    5 releases in the last 90 days, the latest 4 days ago, with 9 contributors on GitHub.

    Use Cases & Benefits

    • Provides a local video editing toolkit with 42 FFmpeg-based tools and a machine-readable contract for AI coding agents to cut, caption, reframe, normalize loudness, and export videos without cloud dependencies.
    • Ensures precise, lossless editing workflows with automatic probing, verification, and no reliance on cloud or API keys, enabling fully offline, agent-driven video processing with structured JSON outputs.
    • Use for integrating video editing capabilities into AI agents like Claude Code, Cursor, or Codex to automate complex video workflows locally without manual FFmpeg scripting.
    • Use for producing platform-specific video exports with built-in templates for TikTok, YouTube Shorts, Reels, and others, ensuring compliance with each platform's format and loudness requirements.
    • Use for batch processing and verifying edits on sensitive or private footage where uploading to cloud services is not an option, maintaining full control over local media assets.

    Should you depend on it?

    License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.

    License

    MIT

    Permissive: commercial use, modification and redistribution are allowed with attribution.

    Community files

    • README: present
    • Contributing guide: present
    • Code of conduct: present

    Watch-outs

    No watch-outs from GStars' checks.

    General guidance from repository metadata, not legal advice. How we score

    From the README

    Give your coding agent a video editor.

    Claude Code, Cursor, Codex or any MCP client edits your footage with local FFmpeg, then checks its own output.

    No cloud · No API keys · Python standard library

    Left half is the input, right half is what the command produced. Every before/after demo, with the exact command under each one → — all of it generated from synthetic footage by python3 demos/build.py, so you can rebuild every frame of it yourself.

    ffmpeg-skill is an Agent Skill for Claude Code, Cursor, Codex and any agent that reads SKILL.md. It teaches the agent a fixed workflow (probe → edit losslessly where possible → check → verify) and ships 42 tools that do the actual work with ffmpeg / ffprobe: cut, join, silence removal, fit to duration and aspect, captions and karaoke, overlays and motion graphics, HDR → SDR and LUTs, audio clean-up and typed dynamics, sync with drift correction, multicam, loudness, delivery checks, whole-edit project rendering, batch folders. Every tool is also callable as an MCP tool (tools/list advertises a core 12 by default to keep client context small, with FFMPEG_SKILL_MCP_FULL=1 listing all 42; every tool is reachable by name through tools/call either way), and the whole set is described by a machine-readable contract.

    If ffmpeg and python3 are on your PATH, it works: offline, on footage you would rather not upload.

    Excerpt from the kajisho5/ffmpeg-skill README on GitHub (MIT license). © its authors.Read the full README on GitHub

    Daily snapshots

    Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots

    Nov 5: +69

    +69 stars over 1 day across 2 snapshot days; best day +69 on Nov 5.

    Forks

    361+8

    Open issues

    10+5

    Compared with peers in AI Agents

    Fastest-growing repositories GStars tracks in this cohort for the week of Nov 1, by 7-day star growth

    kajisho5/ffmpeg-skill compared with AI Agents repositories by stars, 7-day star growth, health score and last release
    RepositoryStars+7dHealthLast release
    vercel-labs/agent-desktop17.0K+13.3K33today
    thedotmack/claude-mem113.6K+8.8K35today
    stablyai/orca116.8K+6.6K40today
    milind-soni/OpenMausBot13.5K+6.0K45today
    HKUDS/DeepTutor55.5K+5.5K655 days ago
    kajisho5/ffmpeg-skill4.5K—584 days ago
    Category median55.5K+6.6K40—

    Discover Repositories

    Search across tracked repositories by name or description