Camera Capture Skill for Openclaw

A specialized skill for capturing high-quality snapshots from MacBook webcams using FFmpeg and AVFoundation.

therohitdas
v1.0.0
Feb 11, 2026
0
2.9k
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install camera

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install camera using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is Camera Capture Skill?

The Camera Capture Skill is a technical utility designed for AI agents to interface directly with macOS camera hardware. It allows for the programmatic capture of still images from both external USB cameras like the Brio 100 and built-in FaceTime HD cameras. By leveraging FFmpeg, this skill manages hardware-specific requirements such as pixel formatting and exposure warmup periods, making it a reliable component of the Openclaw Skills ecosystem for visual data acquisition.

Camera Capture Skill Use Cases

  • Automating workspace snapshots for remote status updates.
  • Capturing multi-angle profile and front-facing photos for identity verification workflows.
  • Visual debugging and environment state logging during automated agent tasks.
  • Integrating real-world visual context into AI agent decision-making processes.

How Camera Capture Skill Works

  1. The agent selects the target camera index based on the desired view (Index 0 for Brio, Index 1 for FaceTime).
  2. A 5-second warmup video is recorded to the temporary directory to ensure the camera hardware adjusts exposure and white balance correctly.
  3. For FaceTime cameras, the skill applies a specific nv12 pixel format to ensure compatibility with macOS buffer requirements.
  4. FFmpeg extracts the final frame from the warmup video to produce a crisp, well-exposed JPEG image.
  5. The skill outputs the final image to a defined path for the agent to process or display.

Camera Capture Skill Setup

To use this within the Openclaw Skills framework, ensure FFmpeg is installed on your macOS system:

brew install ffmpeg

Ensure that your terminal or IDE has been granted Camera permissions in System Settings > Privacy & Security > Camera. To capture from the Brio camera, use:

ffmpeg -loglevel error -f avfoundation -framerate 30 -i "0" -t 5 -y /tmp/brio_warmup.mp4 && ffmpeg -loglevel error -sseof -0.5 -i /tmp/brio_warmup.mp4 -frames:v 1 -update 1 -y /tmp/brio.jpg

Camera Capture Skill Data Schema & Taxonomy

The skill organizes its output in the system temporary directory. Below is the structure of the generated metadata and files:

File Name Description Size
/tmp/brio.jpg Front-facing image from external monitor camera ~80-100KB
/tmp/facetime.jpg Side-angle image from built-in MacBook camera ~80-100KB
/tmp/*_warmup.mp4 Temporary video used for exposure calibration Varies

Camera Capture Skill Advanced Features

  • Multi-camera parallel execution for synchronized multi-angle photography.
  • Hardware-specific pixel format optimization (nv12) to prevent FaceTime buffer errors.
  • Automated exposure adjustment logic via buffered warmup sequences.
  • Low-overhead image extraction that suppresses FFmpeg log spam for cleaner agent execution.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*