ux-audit

Installation
Summary

Real-user dogfooding with emotional friction tracking, click efficiency counting, and resilience testing to produce ranked audit reports.

  • Supports three operating modes: UX Walkthrough (persona-based task completion), QA Sweep (systematic feature testing), and Targeted Check (focused area validation)
  • Tracks emotional friction signals (trust, anxiety, confusion), click efficiency, form resilience (mid-navigation, back button, refresh), and asks "would I come back?"
  • Three depth levels (quick 5–10 min, standard 20–40 min, thorough 1–3 hours overnight) with autonomy scaling; thorough mode includes multi-persona testing, responsive breakpoint screenshots, automated layout detection, and six scenario tests
  • Auto-detects Chrome MCP (for authenticated sessions) or Playwright; resolves URLs from wrangler.jsonc, deployed endpoints, or local dev servers; produces structured markdown reports with findings ranked by severity
SKILL.md

UX Audit

Walk through a live web app AS a real user. The audit is interaction-first — typing, clicking, sending, watching, screenshotting. A static DOM sweep cannot produce a verdict.

Verdict states

The audit ends in exactly one of:

  • Pass — Critical = 0, High = 0, all hard gates green, Interaction Manifest complete.
  • Conditional Pass — Critical = 0, High = 0, all hard gates green, but Medium/Low present.
  • Fail — at least one Critical or High finding, OR a hard gate red.
  • Incomplete — Interaction Manifest missing required entries, a phase wasn't run, OR the audit-the-audit meta-check fires (manifest timestamps clustered < 0.5s apart, screenshots fewer than 2 × routes, console reads fewer than 1 × routes, Phase 3 took < 1m for an exhaustive audit). Not legal to upgrade to Pass even if everything observed looked fine.

If the work doesn't include a complete Interaction Manifest, the only legal verdict is Incomplete. "It looked OK" is not Pass. A clean Pass with implausible timings is rejected — the agent must redo the audit with real interaction.

Hard gates

These auto-fail the audit. They cannot be downgraded.

Related skills
Installs
1.3K
GitHub Stars
780
First Seen
Feb 18, 2026