Os Use
This is a comprehensive cross-platform automation toolkit that gives Claude direct control over your desktop. It handles screenshots, visual recognition with OpenCV, mouse and keyboard control via pyautogui, and window management through AppleScript on macOS or pywinauto on Windows. You'd reach for this when you need to automate repetitive UI tasks, run automated testing without Selenium, or extract data from applications without APIs. The implementation is mature with proper error handling patterns and retry logic built in. Fair warning: you'll need to grant Accessibility and Screen Recording permissions on macOS, and some operations require admin rights on Windows. It's genuinely useful for desktop automation but expect to do some permission wrangling on first setup.
- skills.sh installs
- 272
- GitHub stars
- 13
- last updated
- Aug 21, 2026
Install
$ npx -y skills add zrong/skills --skill os-use --agent claude-codeInstalls into .claude/skills of the current project.
Files
OS Use - Cross-Platform OS Automation
A comprehensive cross-platform toolkit for OS automation, screenshot capture, visual recognition, mouse/keyboard control, and window management. Supports macOS 12+ and Windows 10+.
Platform Support Matrix
| Feature | macOS Implementation | Windows Implementation |
|---|---|---|
| Screenshot | pyautogui + PIL | pyautogui + PIL |
| Visual Recognition | opencv-python + pyautogui | opencv-python + pyautogui |
| Mouse/Keyboard | pyautogui | pyautogui |
| Window Management | AppleScript (native) | pywinauto / pygetwindow |
| Application Control | AppleScript / subprocess | subprocess / pywinauto |
| Browser Automation | Chrome DevTools MCP | Chrome DevTools MCP |
Capabilities
1. Screenshot Capture 📸
Universal (macOS & Windows):
- Full screen capture
- Region capture (specified coordinates)
- Window capture (specific application window)
- Clipboard screenshot access
Implementation: pyautogui.screenshot() + PIL.Image
2. Visual Recognition 👁️
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/zrong/skills
- Categories
- Automation & Workflows, Design & UI/UX, CLI & Terminal
- First seen
- Jun 3, 2026
More from zrong/skills
All 4Recommended
More Automation & Workflows
webperf-interactionnucliweb/webperf-snippetsIntelligent interaction performance analysis with automated workflows for INP debugging, scroll jank investigation, and main thread blocking. Includes decision 267skills.sh installswebperf-loadingnucliweb/webperf-snippetsIntelligent loading performance analysis with automated workflows for TTFB investigation (DNS/connection/server breakdown), render-blocking detection, script pe267skills.sh installs
fastapi-expertmartinholovsky/claude-skills-generatorExpert FastAPI developer specializing in production-ready async REST APIs with Pydantic v2, SQLAlchemy 2.0, OAuth2/JWT authentication, and comprehensive securit265skills.sh installs
symphony-setupodysseus0/symphonySet up Symphony (OpenAI's Codex orchestrator) for a user's repo. Use when the user mentions Symphony setup, configuring Symphony, getting Symphony running, or w262skills.sh installs
testing-agentforcesalesforceairesearch/agentforce-adlcWrite, run, and analyze structured test suites for Agentforce agents. TRIGGER when: user writes or modifies test spec YAML (AiEvaluationDefinition); runs sf age258skills.sh installsapi-expertmartinholovsky/claude-skills-generatorExpert API architect specializing in RESTful API design, GraphQL, gRPC, and API security. Deep expertise in OpenAPI 3.1, authentication patterns (OAuth2, JWT), 257skills.sh installs