impeccable

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

Updated Jun 28, 2026
One-click install
npx skills add https://github.com/jason23452/my-skill --skill impeccable-jason23452
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: impeccable
Source: https://github.com/jason23452/my-skill/tree/main/flow/impeccable
Command: npx skills add https://github.com/jason23452/my-skill --skill impeccable-jason23452

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? Frontend interfaces built quickly often end up generic, inconsistent, or inaccessible. This Skill provides a structured design workflow that turns vague requests like "make it look better" into concrete, verifiable UI improvements grounded in the project's existing design system. ## Core Features & Use Cases - Command-driven design workflow: 23 commands covering build (craft, shape, init), evaluate (critique, audit), refine (polish, bolder, distill, harden), enhance (animate, colorize, typeset, layout), and fix (clarify, adapt, optimize) phases. - Context-aware setup: Loads PRODUCT.md and DESIGN.md, detects brand vs product register, platform (web/iOS/Android), and existing design tokens before making any change. - Quality enforcement: Built-in rules for contrast ratios, typography scales, motion timing, responsive behavior, and detection of common AI-generated design anti-patterns. - Use Case: A user says their dashboard looks generic and the mobile layout is broken. The agent runs the context script, reads the audit and adapt references, scores the UI across accessibility and responsive dimensions, then applies concrete fixes to spacing, hierarchy, and touch targets. ## Quick Start Ask the agent to run the impeccable audit command on your main page to get a scored UI quality report with prioritized fixes.

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 performs a code-level review of semantic HTML, contrast, keyboard navigation, layout thrashing, responsive breakpoints, and interaction states. It outputs a health score out of 20 with P0-P3 severity findings and recommended follow-up commands.

How to make a generic AI-generated design look more distinctive?▼

Use the bolder command to amplify safe or bland designs within your existing design system, or the delight command to add signature moments. The skill explicitly flags common AI patterns like gradient text, glassmorphism cards, and eyebrow labels so they get replaced with product-specific composition.

Does this design workflow support native iOS and Android apps?▼

Yes. When PRODUCT.md declares the platform as ios, android, or adaptive, the workflow loads platform-specific references covering Material Design 3, size classes, safe areas, VoiceOver/TalkBack, and native audit criteria instead of web tooling.

What is the difference between the critique and audit commands?▼

Critique evaluates design quality from a UX perspective: visual hierarchy, information architecture, emotional resonance, and cognitive load. Audit is a technical code-level check of accessibility, performance, responsive behavior, and implementation risks with severity-rated findings.

When should I not use this UI design workflow?▼

Do not use it for framework scaffolding, API client work, testing setup, backend, database, DevOps, CLI tasks, or business logic that does not affect the visible interface. It is scoped strictly to visible UI/UX design decisions.