Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of recent attention, adoption, and active maintenance.
This skill provides a graduated set of tools for AI agents to perform web research, ranging from multi-engine search via SearXNG to deep browsing with Camofox. It is designed for automation builders who need their agents to retrieve current information or navigate the web autonomously.
For more complex environments, the inclusion of CloakBrowser allows agents to handle protected sites using stealth configurations and proxies, making it suitable for data extraction tasks that encounter bot protections.
WHO IT'S FOR
AI agent / automation builders
integrating web search and scraping capabilities
Data scraping engineers
bypassing bot protections on protected sites
Self-hosted infrastructure admins
deploying private search and browsing stacks
AI research power users
conducting exhaustive, cross-verified web research
Compatible AgentsThe repository documents support for these agents. The skills may also work with other agents that can load SKILL.md files, but they may need some setup or small changes.
A specific research question in place of [question]
Any desired freshness window or date constraints
Check the repository for this skill’s setup.
Use the browser-search skill to research [question]. Start with SearXNG, use smart-extract on the most relevant result pages, cross-verify the key claims across multiple sources, and return a sourced answer. Do not browse login-required social-media pages; use only useful search-result snippets from those sites.
Claude
Cursor
OpenClaw
Copilot
OpenCode