impeccable

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

1|Updated May 15, 2026
One-click install
npx skills add https://github.com/Hammad-006/Lemma --skill impeccable-hammad-006
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: impeccable
Source: https://github.com/Hammad-006/Lemma/tree/main/.github/skills/impeccable
Command: npx skills add https://github.com/Hammad-006/Lemma --skill impeccable-hammad-006

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, and polishing UI so the output looks intentional and ships at production quality. ## Core Features & Use Cases - 23 sub-commands across five categories: Build (craft, shape, init, document, extract), Evaluate (critique, audit), Refine (polish, bolder, quieter, distill, harden, onboard), Enhance (animate, colorize, typeset, layout, delight, overdrive), and Fix (clarify, adapt, optimize), plus a live browser iteration mode. - Register-aware guidance: Separate brand and product design references, with anti-pattern bans (gradient text, side-stripe borders, glassmorphism, hero-metric templates) and an AI-slop detection checklist. - Project context integration: Scripts read PRODUCT.md and DESIGN.md, generate brand palette seeds in OKLCH, detect design issues in changed files, and manage pinned shortcuts and detector hooks. - Use Case: Run an audit on a dashboard to get a scored report across accessibility, performance, theming, responsive design, and anti-patterns, then apply the recommended polish, colorize, or layout commands to fix the findings. ## Quick Start Ask the assistant to use the impeccable skill to critique your landing page, then follow the recommended sub-commands it suggests.

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 sub-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 maps to a recommended follow-up command like polish, adapt, or optimize.

How do I make a bland AI-generated design look more distinctive?

Use the bolder command to amplify hierarchy, scale, and typography, or colorize to introduce a strategic OKLCH palette. The skill explicitly bans common AI tells like purple-blue gradients, gradient text, glassmorphism, and cream-tinted backgrounds.

What is the difference between the critique and audit commands?

Critique performs a UX design review with heuristic scoring of the visual and interaction design. Audit runs technical, code-level checks across accessibility, performance, theming, and responsive behavior without fixing anything, producing a documented report instead.

Does this skill work on a brand-new project with no existing design system?

Yes. The init command sets up PRODUCT.md and DESIGN.md project context, and a palette script generates a brand seed color with OKLCH composition guidance when no committed brand colors exist in the codebase.

When should I not use this skill?

Do not use it for backend-only or non-UI tasks. It is scoped to frontend interfaces such as websites, landing pages, dashboards, components, forms, and onboarding flows, and its guidance assumes a visual surface to design or evaluate.