teach-impeccable

Scan project files and write design context to CLAUDE.md.

59|14|Updated Mar 1, 2026
One-click install
npx skills add https://github.com/vobase/vobase --skill teach-impeccable-vobase
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: teach-impeccable
Source: https://github.com/vobase/vobase/tree/main/.agents/skills/teach-impeccable
Command: npx skills add https://github.com/vobase/vobase --skill teach-impeccable-vobase

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill captures scattered design knowledge from a project and persists it so AI agents and future work follow consistent brand, UX, and visual rules, preventing inconsistent interfaces and repeated design questions.

Core Features & Use Cases

  • Repository Discovery: Inspect README, package files, components, style tokens, and assets to infer tech stack, typography, spacing, and color usage.
  • Targeted UX Interrogation: Pause to ask focused questions about users, brand personality, aesthetics, and accessibility when the codebase lacks clear answers.
  • Persisted Design Context: Synthesize findings and user answers into a Design Context section written to CLAUDE.md so future agent sessions inherit consistent guidelines.
  • Use Cases: Initial project onboarding for AI agents, establishing a single source of truth for UI generation, and ensuring design consistency across generated components.

Quick Start

Run the teach-impeccable skill, answer the guided UX questions, and allow it to generate or update the Design Context in CLAUDE.md.

Frequently Asked Questions about teach-impeccable

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

FAQPage Schema
How do I create persistent design guidelines for an AI coding agent?

To create persistent design guidelines, you can use a skill that scans your codebase and writes a Design Context section to CLAUDE.md. This ensures AI agents inherit consistent brand, UI, and visual rules for future sessions.

How do I onboard an AI agent to follow my project's brand and UX rules?

Onboarding an AI agent to your brand and UX rules involves scanning documentation and project files to infer design tokens, then asking targeted questions about brand personality. The synthesized context is persisted for consistent UI generation.

Can I extract design tokens and UI patterns from an existing codebase automatically?

Yes, you can extract design tokens and UI patterns by inspecting README files, package files, components, and style assets. This repository discovery process infers typography, spacing, and color usage directly from your codebase.

What is the best way to establish a single source of truth for UI generation?

The best way to establish a single source of truth for UI generation is to synthesize inferred design context and user answers into a persistent config file like CLAUDE.md. This prevents inconsistent interfaces and repeated design questions.

Does setting up design context require answering UX questions manually?

Setting up design context does pause to ask focused UX questions about users, aesthetics, and accessibility, but only when the codebase lacks clear answers. This targeted interrogation fills gaps that automated file scanning cannot resolve.

Why does my AI agent generate UI components that ignore my project's design system?

AI agents generate inconsistent UI when they lack persistent design context. By writing inferred brand guidelines, UI patterns, and design tokens to CLAUDE.md, you ensure future agent sessions inherit and follow consistent visual rules.