Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Walk through a UI flow once manually and capture a durable interaction map — which DOM elements to click, which network requests they trigger, and what field shapes they expose. Produces a reusable selector+endpoint reference for automation scripts. Use before writing any browser automation block for a JS-heavy SPA, design app, productivity app, or internal portal where selectors and API paths are not obvious from source inspection alone. Modes include Agent Browser for low-token interactive rec
.claude/skills/zhixiangluo-discover-ui-surface/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-08 | ✗→✓ | ▲ Improved | -57% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -33% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -71% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -55% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -52% | 0% |
> Canonical: workflows/discover-ui-surface/discover-ui-surface.md (in this repo). This file is a thin pointer for Cursor skill discovery — load the canonical workflow doc for the full methodology, Agent Browser guide, modes, and the assets/observe_session.py + assets/har_to_map.py scripts.
Read workflows/discover-ui-surface/discover-ui-surface.md and follow it. Companion guides:
workflows/discover-ui-surface/agent-browser.mdworkflows/discover-ui-surface/chrome-recorder.mdOther measured skills in the registry, with their headline benchmark lift.