A comprehensive media processing toolset for automated video transcoding, editing, and manipulation via the command line.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install ffmpeg-cli
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install ffmpeg-cli using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
The FFmpeg CLI skill provides a robust suite of scripts designed to handle complex video and audio processing tasks directly within your AI agent environment. Built on the industry-standard FFmpeg engine, this collection of Openclaw Skills simplifies tasks like format conversion, clip merging, and watermark application, making high-quality media manipulation accessible through simple commands.
Whether you need to extract frames for thumbnails or transcode large batches of video, this skill abstracts the complexity of raw FFmpeg syntax into repeatable, script-based workflows. It ensures that output quality is optimized for a balance between file size and clarity, fitting perfectly into automated content creation pipelines.
To use this skill, ensure that the FFmpeg binary is installed on your host system.
# Install FFmpeg using Homebrew (macOS)
brew install ffmpeg
# Ensure all scripts in the skill directory are executable
chmod +x {baseDir}/scripts/*.sh
The skill organizes its operations through a structured script directory and standardized parameter flags.
| Component | Description |
|---|---|
/scripts/ |
Contains specialized bash scripts for cut, merge, convert, etc. |
| Input Formats | Supports mp4, avi, mov, mkv, webm, and more. |
| Script Flags | Uses -i (input), -o (output), -s (start), -e (end), and -t (timestamp). |
| Metadata | Integrated with the clawdbot configuration for dependency tracking. |
Loading
A GraphQL-based skill for AI agents to query and manage personal reading libraries and book metadata from Hardcover.app.

A local, high-performance hybrid search and memory engine designed to eliminate API embedding costs for AI agents.

A high-performance local search engine designed for indexing and retrieving Markdown notes and documents using keyword, vector, and hybrid search methods.

A high-performance tweet engine for builders that generates sharp, human-sounding X content without the AI fluff.

A self-hosted long-term memory and cognition layer for OpenClaw agents utilizing 3-signal retrieval and knowledge graphs.

A secure skill for AI agents to perform USD1 (USDC on Wormhole) transfers across wallets using the Wormhole Liquidity Facility.








































