universal-web-adaptation

Universal web adaptation skill

Use this skill when the user wants a general solution across many websites, not a one-by-one manual integration first.

This skill is especially suitable for:

• unfamiliar public websites
• search-oriented workflows
• result-page collection and lightweight summaries
• deciding whether a site needs a dedicated profile or can stay generic

For the 99idea Playwright project, this skill should work together with:

• src\run-demo.js
• src\planner.js
• src\llm-planner.js
• src\site-profiles.js
• scenarios\site-profiles.json

Core principle

Always try this order:

1. Capability discovery — check if opencli already supports the site (opencli list)
2. Auth cascade — classify: PUBLIC → COOKIE/SESSION → HEADER → LOGIN-GATED
3. Generic adaptation — probe UI controls and try heuristic strategies
4. Temporary scenario tuning — adjust runtime before assuming selectors are wrong
5. Popup / opener / alternate-submit handling
6. Site profile only if generic adaptation still fails

The goal is to minimize per-site handwork.

Execution path decision (inspired by opencli)

Before touching the DOM, first determine which execution layer to use:

if opencli has an adapter for this site:
    use opencli (zero LLM cost, deterministic)
elif the site has a public API:
    use fetch (structured data, no rendering)
elif the site renders server-side (SSR):
    use web_fetch or Playwright (metadata extraction)
else:
    use Browser Agent with login-state or mark blocked

This avoids wasting time on SPA shells that will never yield results via scraping.

What “generic adaptation” means

When facing a new site, do not immediately create a profile. First try to discover:

• likely search inputs
• likely opener buttons or icons
• likely submit controls
• whether Enter works
• whether a click opens a popup or new tab
• whether the site verifies best by URL, title, or visible text

Standard workflow