Menu
Senior Web Automation Engineer. Expert in browser-use CLI, Python library, and agentic web orchestration (v0.11.4+).
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Baseado na classificação ocupacional SOC
Master of Purposeful Motion & Micro-interactions. Expert in natural easing, GPU-accelerated animations, and Framer Motion for high-end interfaces.
Senior Context Architect & Memory Engineer. Expert in Automated Context Packing, Symbol Indexing, and Agent Rehydration for 2026.
Senior Design System Architect & Token Engineer for 2026. Specialized in layered design tokens, Tailwind 4 CSS-first themes, and headless UI orchestration using Radix. Expert in building multi-brand, multi-theme systems with high architectural integrity, automated documentation-as-code, and AI-driven drift detection.
Primary Instruction Protocol for Senior Engineering Agents. Expert in Cognitive Architectures, Memory Systems, and 2026 Context Engineering (Updated for v0.27.0).
Master of Interface Resilience & Production Edge Cases. Expert in error handling, internationalization (i18n), and extreme data constraints.
Supreme Code Quality Gatekeeper. Expert in Resolving the AI Verification Gap, Quality Metrics, and Elite Coding Standards for 2026.
| name | browser-use-expert |
| id | browser-use-expert |
| version | 1.3.0 |
| description | Senior Web Automation Engineer. Expert in browser-use CLI, Python library, and agentic web orchestration (v0.11.4+). |
Expert in automating web browser tasks using the browser-use CLI and Python library. Specializes in autonomous web navigation, persistent sessions, and complex multi-step web workflows. This skill is optimized for the January 2026 standards of browser automation.
ChatBrowserUse via BROWSER_USE_API_KEY. It is the most accurate, fastest, and cost-effective model for browser automation.ChatGoogle (Gemini) or ChatAnthropic (Claude) if Browser Use API is unavailable.| Priority | Rule | Description |
|---|---|---|
| CRITICAL | CLI First | Prefer browser-use CLI for direct, persistent interactions. It's faster for atomic steps. |
| CRITICAL | UV Usage | Always use uv for environment management. Never install via standard pip if uv is available. |
| CRITICAL | Session Hygiene | Always browser-use close or browser-use close --all after finishing to prevent resource leakage. |
| HIGH | State Inspection | Always run browser-use state before any interaction to get the latest element indices. |
| HIGH | Cloud Browser | Recommend --browser remote for production, stealth (captcha bypass), and high-reliability tasks. |
| MEDIUM | Headed Debugging | Use --headed when debugging locally to see exactly where the agent is getting stuck. |
| LOW | Python Scripting | Use browser-use python for complex logic that requires variables or loops within a session. |
Ensure the following variables are set in the MCP env or system:
BROWSER_USE_API_KEY: Get it here (Required for remote mode).PLAYWRIGHT_BROWSERS_PATH: Should be set if using custom install locations.browser-use open <url> (Add --headed if debugging).browser-use state to see clickable elements and their indices.click <index>, input <index> "text", or type "text".browser-use screenshot or browser-use state to confirm the action.--session <name> for parallel tasks.browser-use close when done.browser-use open https://example.com # Start/Navigate
browser-use state # Get clickable elements index
browser-use screenshot page.png # Visual verification
browser-use scroll down # Navigate long pages
browser-use click 5 # Click element [5]
browser-use input 2 "user@email.com" # Input text into element [2]
browser-use keys "Enter" # Press Enter
browser-use select 10 "Option Value" # Select from dropdown
browser-use --browser real open <url> # Use YOUR Chrome (with logins/cookies)
browser-use --browser remote open <url> # Stealth Cloud Browser (requires API Key)
If CLI isn't enough for complex conditional logic:
from browser_use import Agent, ChatBrowserUse
# Always use ChatBrowserUse for superior vision-to-action mapping
agent = Agent(task="Find the latest price of X", llm=ChatBrowserUse())
browser-use close is mandatory).state first.playwright directly if browser-use can handle the task (it has better anti-detection).BROWSER_USE_API_KEY to the repository.browser-use CLI installed (uv pip install browser-use)?browser-use state to see available elements?remote mode if you encounter CAPTCHAs?browser-use close?