A robust macOS screen capture utility that uses short video recordings to extract high-quality PNG snapshots, bypassing traditional permission hurdles.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install mac-node-snapshot
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 mac-node-snapshot using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
This skill provides a permission-friendly method for capturing macOS screen content within the OpenClaw ecosystem. By utilizing the screen record node capability to generate a brief 1-second video clip and then extracting a specific frame with ffmpeg, it ensures reliable image returns even in complex or headless environments where standard screencapture tools might fail. It is a critical component for users of Openclaw Skills who need visual context from their remote or local Mac machines for agent-led troubleshooting and analysis.
To use this within the Openclaw Skills framework, ensure that ffmpeg is installed on the host machine. You can initialize a capture with the following command sequence:
mkdir -p "{skill}/tmp" && openclaw nodes screen record --node "<node>" --duration 1000 --fps 10 --no-audio --out "{skill}/tmp/snap.mp4" && ffmpeg -hide_banner -loglevel error -y -ss 00:00:00 -i "{skill}/tmp/snap.mp4" -frames:v 1 "{skill}/tmp/snap.png"
The skill manages temporary visual assets and logs during the capture lifecycle:
| File Path | Description | Format |
|---|---|---|
{skill}/tmp/snap.mp4 |
Temporary video buffer used for frame extraction. | MP4 |
{skill}/tmp/snap.png |
The final high-resolution screen snapshot. | PNG |
Note: All paths are relative to the skill directory within Openclaw Skills.
Loading
A high-performance validation layer ensuring consistency and state verification for autonomous agents on the Polygon PoS network.

A comprehensive cryptocurrency AML and security analysis tool for AI agents to track transactions and assess address risks across multiple blockchains.

An automated pipeline for transcribing iMessage voice memos and analyzing images within Openclaw Skills.

An official MiniMax Model Context Protocol server providing AI-powered web search and sophisticated image understanding capabilities.

A dual-platform content automation tool that transforms technical updates into high-engagement Twitter and LinkedIn posts simultaneously.

An intelligent educational curriculum generation system featuring automated resource discovery and strict human-in-the-loop escalation policies.








































