impeccable

Design, critique, audit, and refine frontend interfaces across web and native platforms.

3|Updated Jul 28, 2026
One-click install
npx skills add https://github.com/marcmarti9/agentit --skill impeccable-marcmarti9
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: impeccable
Source: https://github.com/marcmarti9/agentit/tree/main/skills/impeccable
Command: npx skills add https://github.com/marcmarti9/agentit --skill impeccable-marcmarti9

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? Frontend interfaces often ship bland, inconsistent, or technically weak because design work lacks a structured process. This Skill gives an AI agent a complete design-director workflow: it loads project context (PRODUCT.md, DESIGN.md), routes requests to 20+ specialized commands, and enforces a measurable craft floor covering contrast, spacing, typography, motion, and platform conformance. ## Core Features & Use Cases - Command-based design operations: Build (init, document, extract, shape), Evaluate (critique, audit), Refine (polish, bolder, quieter, distill, harden, onboard), Enhance (animate, colorize, typeset, layout, delight, overdrive), Fix (clarify, adapt, optimize), and Iterate (live, generate) commands each backed by a dedicated reference playbook. - Dual-agent design critique: Runs an independent design review and a deterministic detector scan as isolated sub-agents, then synthesizes a scored report using Nielsen's 10 heuristics, cognitive-load checks, and persona red flags, persisted to .impeccable/critique/ for trend tracking. - Web and native platform support: Separate references for iOS (SwiftUI/UIKit) and Android (Compose/Material 3) enforce platform conventions, safe-area insets, touch targets, and slop tests, with adb-based screenshot verification. - Use Case: Ask the agent to audit a dashboard page; it scores accessibility, performance, theming, responsive design, and implementation integrity out of 20, lists P0-P3 findings, and recommends the exact follow-up commands to fix them. ## Quick Start Ask the agent to run the impeccable audit command on your main page or component to get a scored 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 web page for accessibility and performance issues?▼

Run the audit command on a target page or component. It scores accessibility, performance, theming, responsive design, and implementation integrity from 0-4 each, then reports P0-P3 findings with concrete fixes and suggested follow-up commands.

How to get a UX design critique of an existing interface?▼

Run the critique command with a file path or URL. It runs two independent assessments, a design review and a deterministic detector scan, then produces Nielsen heuristic scores, persona red flags, priority issues, and a persisted snapshot for trend tracking.

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

Yes. Native projects route to dedicated iOS and Android references covering SwiftUI, UIKit, Jetpack Compose, and Material 3 conventions. Verification uses emulator or device screenshots via adb rather than browser tooling.

What design commands are available for improving an existing UI?▼

Refinement commands include polish, bolder, quieter, distill, harden, and onboard; enhancement commands include animate, colorize, typeset, layout, delight, and overdrive; fix commands include clarify, adapt, and optimize. Each loads a dedicated reference playbook.

When should I not use this frontend design skill?▼

Do not use it for backend-only or non-UI tasks; its scope is frontend interfaces and native app surfaces. It also avoids open-ended self-QA loops, relying on bounded inspection passes and finish handoffs instead.