osworld-observe
CommunityCapture OSWorld environment state.
Authorbdambrosio
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill captures the current state of the OSWorld environment, providing visual and structural information for agentic decision-making.
Core Features & Use Cases
- Screenshot Capture: Obtains a base64 encoded PNG image of the current screen.
- Accessibility Tree: Retrieves a JSON representation of the UI's accessibility tree.
- Use Case: An agent needs to understand the current UI to interact with it; this skill provides the necessary visual and structural data.
Quick Start
Get the current observation from the OSWorld environment, including screenshot and accessibility tree.
Dependency Matrix
Required Modules
requests
Components
scripts
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: osworld-observe Download link: https://github.com/bdambrosio/Cognitive_workbench/archive/main.zip#osworld-observe Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.