Ui neuro ergo
Agent Skills collection — Reusable capabilities for AI coding agents. Install: npx skills add TheWatcher01/skills
npx -y skills add TheWatcher01/skills --skill ui-neuro-ergoAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Autonomous neuro-ergonomic + a11y UI audit and iteration skill. Combines WCAG 2.2 AA standards, cognitive science principles (Fitts Law, CLT, Gestalt), and a Chrome DevTools MCP screenshot loop for production-ready delivery. Triggers on neuro ergo, a11y, accessibility audit, cognitive load, UX review, WCAG, ergonomie, accessibilite.
SKILL.md
5.4 KB, as published. Nobody here has run it
UI Neuro-Ergo Skill
Autonomous workflow for neuro-ergonomic + accessible UI work with visual iteration via Chrome DevTools MCP. Delivers production-ready results without requiring human intervention between iterations.
Overview
This skill combines:
- Neuro-ergonomics — cognitive science applied to UI: reduce friction, lower cognitive load, amplify signal
- Accessibility (WCAG 2.2 AA) — inclusive design, screen reader support, keyboard navigation, contrast
- Visual Iteration Loop — Chrome DevTools MCP screenshots for autonomous see→fix→verify cycles
When to load references
- Neuro-ergonomic principles → load
references/neuro-ergo-principles.md - WCAG 2.2 AA checklist → load
references/a11y-checklist.md - Chrome MCP iteration protocol → load
references/iteration-protocol.md
Workflow
Phase 1 — Audit
- Open Chrome DevTools MCP → navigate to the target page
- Take screenshot → capture current state (full page)
- Take a11y tree snapshot (
take_snapshot) → see ARIA roles, labels, structure - Read the source code → analyze component structure
- Run axe audit via
evaluate_script:() => { // Check for basic a11y violations visible without axe const issues = []; // Missing alt on images document .querySelectorAll("img:not([alt])") .forEach((el) => issues.push({ type: "img-no-alt", el: el.outerHTML.slice(0, 80) }), ); // Buttons without accessible name document .querySelectorAll("button:not([aria-label]):not([aria-labelledby])") .forEach((b) => { if (!b.textContent.trim()) issues.push({ type: "button-no-name", el: b.outerHTML.slice(0, 80), }); }); // Inputs without label document .querySelectorAll("input:not([aria-label]):not([id])") .forEach((i) => issues.push({ type: "input-no-label", el: i.outerHTML.slice(0, 80) }), ); // animate-pulse without reduced motion guard document .querySelectorAll('[class*="animate-"]') .forEach((el) => issues.push({ type: "animation-check", cls: el.className }), ); return issues; }; - Compile audit report with findings in 4 categories:
- 🔴 Critical (WCAG A violations, blocking keyboard/SR users)
- 🟠 Ergonomic (cognitive load, Fitts' Law, visual hierarchy)
- 🟡 WCAG AA (contrast, live regions, target sizes)
- 🟢 Polish (micro-interactions, motion, progressive disclosure)
Phase 2 — Plan Fixes
Load references/neuro-ergo-principles.md and references/a11y-checklist.md.
For each finding, define the specific fix with exact code changes.
Prioritize: Critical → WCAG AA → Ergonomic → Polish.
Phase 3 — Implement
Apply all changes to the source file(s). Stagger changes in logical groups if file is large:
- Structure & ARIA (landmarks, roles, labels, live regions)
- Keyboard & Focus (skip link, focus ring, tab order)
- Cognitive load (chunking, visual hierarchy, reduced noise)
- Motion & animation (
prefers-reduced-motion, remove unnecessary pulse) - Contrast & sizing (text contrast, touch targets min 44×44px)
Phase 4 — Visual Iteration
Reload the page and take before/after screenshots. Fix any regressions:
take_screenshot → analyze → find issues → fix code → navigate/reload → take_screenshot → ...
Iterate until:
- No critical a11y violations visible
- Visual hierarchy is clear (1 primary action per view, clear F-pattern scan path)
- All interactive elements have visible focus indicators
- Motion respects
prefers-reduced-motion - Skip navigation link present
- Live region announces filter results to screen readers
- Touch targets ≥ 44×44px on mobile viewport
- Headings form a logical outline (h1 → h2 → h3, no skips)
Phase 5 — Production Checklist
Before declaring done, verify:
- TypeScript compiles without errors (
pnpm buildor check editor diagnostics) - No arbitrary Tailwind values (
w-[...],text-[...]) — unless using CSS vars - All
<button>have accessible names - All
<input>have<label>oraria-label -
<article>elements havearia-labelledbypointing to their heading - Dynamic count updates use
role="status"oraria-live="polite" - Animations wrapped in
motion-safe:or@media (prefers-reduced-motion: no-preference) - Color is not the only differentiator (icon+color, not color alone)
Reference Files
Load these on demand:
references/neuro-ergo-principles.md— cognitive science principles (CLT, Fitts' Law, Gestalt, Miller's Law, F-pattern)references/a11y-checklist.md— WCAG 2.2 AA checklist + JS audit script for React/Next.jsreferences/react-a11y-patterns.md— copy-paste fix patterns (skip link, live region, article+aria-labelledby, radiogroup, motion guard, touch target)references/iteration-protocol.md— Chrome DevTools MCP tool sequence and iteration exit criteria
Gives 0 of the 12 instructions most accessibility skills give
Counted across 384 of the 385 authors here whose files we hold, read 2026-08-06
- maintain visible focus indicatorsin 46 of 384, across 33 files
- run automated accessibility scansin 44 of 384, across 32 files
- make all interactive elements keyboard reachablein 39 of 384, across 32 files
- use semantic HTML before ARIAin 38 of 384
- respect reduced motion preferencesin 35 of 384, across 27 files
- Associate labels programmatically with inputsin 33 of 384, across 26 files
- Use native elements over ARIAin 30 of 384, across 18 files
- test with a screen readerin 26 of 384, across 22 files
- map findings to WCAG criteriain 24 of 384, across 14 files
- meet minimum color contrast ratiosin 24 of 384, across 16 files
- Provide text alternatives for imagesin 24 of 384, across 18 files
- trap focus inside open modalsin 23 of 384, across 18 files
Said here and by no other author read
- take full page screenshots
- evaluate script to run an axe audit
- load reference files on demand
- apply source code changes in logical groups
- verify visual regressions via screenshots
- run the production checklist
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once.