impeccable

Generates production-grade frontend interfaces with distinctive typography, color, and layout guidelines.

Updated Mar 22, 2026
One-click install
npx skills add https://github.com/serguei9090/LogLensAi --skill impeccable-serguei9090
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: impeccable
Source: https://github.com/serguei9090/LogLensAi/tree/main/.agents/skills/impeccable
Command: npx skills add https://github.com/serguei9090/LogLensAi --skill impeccable-serguei9090

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? AI-generated frontend code tends to converge on generic, recognizable aesthetics—default fonts, gradient text, side-stripe cards, and templated layouts. This Skill enforces a disciplined design process with explicit anti-pattern bans and project-specific design context so interfaces look intentionally designed rather than machine-produced. ## Core Features & Use Cases - Design Context Protocol: Gathers target audience, use cases, and brand personality via a teach mode that writes a persistent .impeccable.md context file before any design work begins. - Opinionated Design Rules: Provides concrete guidelines for typography (font selection procedure, modular scales), color (OKLCH palettes, tinted neutrals), spatial rhythm, motion, interaction, and UX writing, plus absolute bans on AI-tell CSS patterns. - Three Invocation Modes: craft runs a shape-then-build flow with visual iteration, teach sets up project design context, and extract consolidates repeated components and tokens into a design system. - Use Case: When asked to build a dashboard or landing page, the Skill first loads the project's design context, commits to a bold aesthetic direction, then implements working code while avoiding banned patterns like gradient text and border-left accent stripes. ## Quick Start Ask the AI to craft a new settings page for your app using the impeccable skill with your project's design context.

Frequently Asked Questions about impeccable

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

FAQPage Schema
How do I make AI-generated frontend design look less generic?▼

Use a structured design process: gather brand context first, commit to a bold aesthetic direction, and enforce explicit bans on common AI tells like gradient text, side-stripe borders, and overused fonts such as Inter or Space Grotesk.

How do I choose fonts for a web project without defaulting to Inter?▼

Define three concrete brand voice words, reject a reflex list of overused fonts, then browse font catalogs imagining the typeface as a physical brand object. Cross-check that your final pick does not match your usual reflex pattern.

What is the difference between craft, teach, and extract modes?▼

Teach gathers project design context into a .impeccable.md file, craft builds a feature through a shape-then-build flow with visual iteration, and extract consolidates repeated components and hard-coded values into reusable design system tokens.

Why should I use OKLCH instead of HSL for CSS colors?▼

OKLCH is perceptually uniform, so equal lightness steps look equal across hues, unlike HSL. It also lets you reduce chroma near white or black to avoid garish extremes and tint neutrals toward your brand hue.

Does this design approach work with existing component libraries?▼

Yes, the extract mode is designed to work with an existing design system or component library, identifying repeated patterns and hard-coded values to consolidate into shared components and tokens following existing conventions.

What CSS patterns are banned as AI design tells?▼

Two absolute bans: border-left or border-right wider than 1px as accent stripes on cards or callouts, and gradient text via background-clip. The guidelines also discourage glassmorphism overuse, decorative sparklines, and identical card grids.