Agent skill

buse

Enhancement module for browser-use, allowing AI to control browsers using natural language. Core Scenario: When the user wants an AI agent to perform tasks in a browser (e.g., searching docs, taking screenshots) via terminal.

View SKILL.md on GitHub Repository
Stars 19
Forks 4

Install this agent skill to your Project

npx add-skill https://github.com/x-cmd/skill/tree/main/data/x-cmd/buse

SKILL.md

buse - Natural Language Browser Automation

The buse module enables users to control a web browser using natural language through the browser-use framework. It automates complex browser actions without requiring manual coding.

When to Activate

  • When the user wants an AI to navigate websites or interact with web elements.
  • When performing automated browser tasks like documentation search or visual verification (screenshots).
  • When using a terminal UI to interactively guide a browser agent.
  • When running headless browser tasks for data extraction or testing.

Core Principles & Rules

  • Safety & Permissions: AI-generated browser actions should be monitored; use caution with sensitive sites.
  • Model Requirement: Requires an AI model API key (OpenAI, Gemini, etc.) configured via respective x-cmd modules.
  • Context Handling: Supports custom browser windows, user data directories, and CDP connections.

Additional Scenarios

  • Visual Evidence: Automatically take screenshots during a browser task using specific prompts.
  • MCP Mode: Run as a Model Context Protocol server for integration with other AI tools.

Patterns & Examples

Interactive Browser Control

bash
# Launch the interactive terminal UI for browser control
x buse

Direct Task Execution

bash
# Run a specific browser task non-interactively
x buse -p "Search for OpenAI documentation and take a screenshot of the homepage"

Headless Mode

bash
# Run a task in the background without a visible window
x buse --headless -p "Check the stock status of an item on ExampleStore.com"

Checklist

  • Ensure browser-use and Chromium are installed via x buse --install.
  • Confirm that at least one AI model API key is set up.
  • Verify if the task requires a visible window or can run headless.

Recommended Agent Skills

Expand your agent's capabilities with these related and highly-rated skills.

x-cmd/skill

pufferlib

High-performance reinforcement learning framework optimized for speed and scale. Use when you need fast parallel training, vectorized environments, multi-agent systems, or integration with game environments (Atari, Procgen, NetHack). Achieves 2-10x speedups over standard implementations. For quick prototyping or standard algorithm implementations with extensive documentation, use stable-baselines3 instead.

19 4
Explore
x-cmd/skill

fluidsim

Framework for computational fluid dynamics simulations using Python. Use when running fluid dynamics simulations including Navier-Stokes equations (2D/3D), shallow water equations, stratified flows, or when analyzing turbulence, vortex dynamics, or geophysical flows. Provides pseudospectral methods with FFT, HPC support, and comprehensive output analysis.

19 4
Explore
x-cmd/skill

metabolomics-workbench-database

Access NIH Metabolomics Workbench via REST API (4,200+ studies). Query metabolites, RefMet nomenclature, MS/NMR data, m/z searches, study metadata, for metabolomics and biomarker discovery.

19 4
Explore
x-cmd/skill

geniml

This skill should be used when working with genomic interval data (BED files) for machine learning tasks. Use for training region embeddings (Region2Vec, BEDspace), single-cell ATAC-seq analysis (scEmbed), building consensus peaks (universes), or any ML-based analysis of genomic regions. Applies to BED file collections, scATAC-seq data, chromatin accessibility datasets, and region-based genomic feature learning.

19 4
Explore
x-cmd/skill

zinc-database

Access ZINC (230M+ purchasable compounds). Search by ZINC ID/SMILES, similarity searches, 3D-ready structures for docking, analog discovery, for virtual screening and drug discovery.

19 4
Explore
x-cmd/skill

astropy

Comprehensive Python library for astronomy and astrophysics. This skill should be used when working with astronomical data including celestial coordinates, physical units, FITS files, cosmological calculations, time systems, tables, world coordinate systems (WCS), and astronomical data analysis. Use when tasks involve coordinate transformations, unit conversions, FITS file manipulation, cosmological distance calculations, time scale conversions, or astronomical data processing.

19 4
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results