browser-assistant

Search the web and extract evidence from target pages via browser operations.

1|Updated Mar 6, 2026
One-click install
npx skills add https://github.com/pycode4micro/bushserver --skill browser-assistant
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: browser-assistant
Source: https://github.com/pycode4micro/bushserver/tree/main/src/bushserver/seeds/skills/package/browser-assistant
Command: npx skills add https://github.com/pycode4micro/bushserver --skill browser-assistant

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps users perform web search and browsing to find relevant information online, while extracting evidence from target pages rather than relying on search snippets.

Core Features & Use Cases

  • Region-aware search selection: Chooses a search provider based on explicit user preference, host locale/region, and provider availability instead of language alone (e.g., defaulting to Baidu for mainland-China/Chinese public-web tasks unless the user requests Google).
  • Multi-page exploration & result evaluation: Explores multiple pages of results, prioritizes high-signal organic areas, and deprioritizes ads and low-quality sources.
  • Public-web browser operations with safe handling: Uses browser-based navigation via browser operations, stops when verification gates appear, and avoids prohibited actions like clicking ads or suspicious download/code links.
  • Content-first extraction for evidence: Jumps to candidate URLs and extracts content from destination pages, then hands off a fact table mapped to successful extractions for downstream writing.

Quick Start

Use the browser-assistant skill to research "how to configure BushServer for local deployment" and extract verified facts from the relevant official pages.

Frequently Asked Questions about browser-assistant

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract web content from target pages instead of relying on search snippets?

Content-first extraction navigates to candidate URLs and pulls information directly from destination pages, producing a fact table mapped to successful extractions for downstream writing.

How does region-aware search provider selection work for web browsing automation?

Region-aware search selection chooses a provider based on explicit user preference, host locale, and provider availability, defaulting to Baidu for mainland-China tasks unless Google is requested.

How do I handle verification gates and avoid ads during automated web research?

Safe navigation stops when verification gates appear and deprioritizes ads, avoiding prohibited actions like clicking suspicious links during multi-page search exploration.

Can I use browser operations for multi-page search exploration and result evaluation?

Yes, browser operations support multi-page exploration, prioritizing high-signal organic areas while deprioritizing low-quality sources for reliable internet research.

What are the limitations of safe browsing when encountering prohibited actions?

Safe browsing avoids clicking ads or suspicious download and code links, and stops at verification gates, limiting navigation to approved browser operations for target-page extraction.