impeccable

Designs, audits, and refines production-grade frontend interfaces through structured commands.

Updated Jan 4, 2026
One-click install
npx skills add https://github.com/quinc-dev/qt2026 --skill impeccable-quinc-dev
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: impeccable
Source: https://github.com/quinc-dev/qt2026/tree/main/.agents/skills/impeccable
Command: npx skills add https://github.com/quinc-dev/qt2026 --skill impeccable-quinc-dev

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve? Frontend interfaces built quickly often suffer from generic AI-generated aesthetics, weak visual hierarchy, accessibility failures, and inconsistent design systems. This Skill provides a structured workflow for designing, critiquing, auditing, and polishing UI so the result looks intentional and ships at production quality. ## Core Features & Use Cases - Command-driven design workflow: 20+ sub-commands (craft, shape, audit, polish, bolder, quieter, distill, harden, animate, colorize, typeset, layout, clarify, adapt, optimize, live) each with a dedicated reference file defining its flow. - Anti-AI-slop rules: Enforces concrete bans (gradient text, side-stripe borders, glassmorphism, hero-metric templates, cream/sand backgrounds) plus contrast, typography, motion, and responsive guidelines. - Project context awareness: Scripts detect PRODUCT.md/DESIGN.md, generate brand seed palettes in OKLCH, and route work to brand or product registers. - Use Case: A developer asks to audit a dashboard; the Skill runs technical checks across accessibility, performance, theming, responsive design, and anti-patterns, then produces a scored report with prioritized fix commands. ## Quick Start Ask the AI to use the impeccable skill to critique your landing page or run the audit command on a UI component.

Frequently Asked Questions about impeccable

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I audit a frontend UI for accessibility and performance issues?▼

Run the audit command, which scores five dimensions (accessibility, performance, theming, responsive design, anti-patterns) from 0-4 each and produces a report with P0-P3 severity-tagged findings. Each finding includes location, impact, and a recommended follow-up command.

How to make a bland AI-generated landing page look more distinctive?▼

Use the bolder command to amplify hierarchy, scale contrast, and typographic voice while rejecting saturated AI defaults like purple-blue gradients and glassmorphism. The brand register reference guides font selection away from training-data defaults like Inter and Fraunces.

What design anti-patterns does this skill ban?▼

It bans gradient text, side-stripe borders over 1px, decorative glassmorphism, hero-metric templates, identical card grids, tiny uppercase eyebrows on every section, and cream/sand body backgrounds. It also rejects bounce easing, gray text on colored backgrounds, and contrast below 4.5:1.

Does the skill work on existing projects with an established design system?▼

Yes. Setup requires reading existing CSS tokens, themes, and components first, and committed brand colors take precedence over generating new palettes. The palette generation script only runs for brand-new projects with no existing tokens.

When should I use the critique command versus the audit command?▼

Use critique for a UX design review with heuristic scoring of visual and interaction decisions. Use audit for technical, measurable checks like contrast ratios, touch target sizes, lazy loading, and hard-coded colors. Audit documents issues without fixing them.

Can I iterate on UI elements visually in the browser?▼

Yes, the live command enables visual variant mode where you pick elements in the browser and generate alternatives. It requires a running dev server, which the context-signals script detects before recommending it.