Web Search

web-search

Compatibility: browser_use tool required; optional login for Perplexity; no API key required.

Use browser automation to search the web through a fixed engine chain, then fall back automatically when one engine is blocked, logged out, or returns poor results.

When to use

Activate this skill when the user wants:

• real-time web search
• search engine results instead of model memory
• official site lookup
• original page lookup
• fallback behavior across the fixed search engines

Search engines

Default priority chain

Google -> Perplexity -> Bing

Fallback rules

Immediately switch to the next engine when any of these happens:

• login expired
• captcha / verification / blocked / robot / abnormal traffic
• empty result page
• redirected back to the home page
• page structure is broken and no useful text can be extracted
• only input box is visible with no actual results

Success criteria

Treat a search as successful when at least two of these are true:

• the page title or URL clearly indicates a result page
• extracted text is non-empty and contains meaningful results
• there are structured answers, result lists, citations, or related questions
• the content is clearly not just the search homepage

Execution flow

1. Use Google first.
2. If unavailable or poor, switch to Perplexity.
3. If unavailable or poor, switch to Bing.
4. Return the first good result, and optionally add a second source for comparison.

Scripts

• scripts/browser_search.py — generate the fixed priority plan
• evals/evals.json — prompt coverage for the routing scenario

Notes

• Google is the default first engine.
• Perplexity is the second choice when Google is blocked or poor.
• Bing is the final fallback.
• Do not use any other search engine.