A powerful macOS command-line utility for capturing audio, screen recordings, screenshots, and camera input, optimized for terminal-based AI agents.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install record
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 record using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
The record CLI is a specialized macOS tool designed to bridge the gap between terminal environments and media capture hardware. It allows users and autonomous agents to record high-quality audio, video, and still images directly from the command line without interacting with a GUI. Built with automation in mind, it provides structured output and granular control, making it an essential addition to any developer's toolkit or Openclaw Skills collection. It handles everything from simple screenshots to complex multi-source audio/video recordings while maintaining a pipeline-friendly architecture.
Install the tool via Homebrew on macOS using the following command:
brew install atacan/tap/record
After installation, ensure that your terminal application (e.g., iTerm2, Terminal.app) has the required permissions enabled in System Settings > Privacy & Security for Microphone, Camera, and Screen Recording to enable full functionality for your Openclaw Skills workflow.
The record CLI follows a predictable output pattern to ensure interoperability with scripts and Openclaw Skills. It primarily outputs file paths to stdout and status messages to stderr.
| Data Type | Description | Default Format |
|---|---|---|
| Audio | Microphone recordings | .m4a |
| Video | Screen or Camera recordings | .mp4 |
| Image | Screenshots or Photos | .png / .jpg |
| Metadata | JSON structured info | .json (via --json flag) |
Output files are stored in a temporary directory by default unless the --output flag is specified to define a custom path.
Loading
A multi-modal search engine for AI agents to discover, match, and load specialized capabilities through keyword, semantic, or LLM-powered matching.

An intelligent model dispatching system that uses multi-dimensional analysis to route requests to the most efficient AI model based on complexity and cost.

A complete technical reference for managing OpenClaw configurations, CLI operations, and multi-channel AI agent deployments.

A sovereign document intelligence and archival system that extracts structured data from files 100% locally using AI.

A cross-platform command-line tool for professional speech-to-text transcription powered by multiple leading AI providers.

A robust command-line interface for translating text, files, and code catalogs using various AI providers and custom prompt templates.








































