teach-impeccable

Scan repository design tokens and write UX context to .impeccable.md.

Updated Mar 7, 2026
One-click install
npx skills add https://github.com/jcdiv47/cool-paper --skill teach-impeccable-jcdiv47
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: teach-impeccable
Source: https://github.com/jcdiv47/cool-paper/tree/main/.agents/skills/teach-impeccable
Command: npx skills add https://github.com/jcdiv47/cool-paper --skill teach-impeccable-jcdiv47

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Many projects lack a persistent, machine-readable design context, which leads to inconsistent UI decisions, onboarding friction, and repeated design questions across sessions. This Skill automates gathering visual and UX context from the repository and saves a concise Design Context to the project's AI config so future sessions reuse the same guidelines.

Core Features & Use Cases

  • Repository exploration: Scans README, docs, components, styles, and brand assets to extract existing design tokens, typography, and patterns.
  • Targeted UX clarification: Pauses to ask focused UX and brand questions where the codebase is ambiguous, ensuring human-aligned decisions.
  • Persisted design rules: Writes or updates a ## Design Context section in .impeccable.md (and optionally appends to CLAUDE.md) so design guidance is available to all future AI sessions.
  • Use case: Onboarding a new designer or generating consistent UI changes across features by applying the same documented design principles stored in the repo.

Quick Start

Persist project design guidelines by scanning the repository, asking the UX questions listed in the skill, and writing a Design Context section to .impeccable.md.

Frequently Asked Questions about teach-impeccable

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

FAQPage Schema
How do I establish persistent design guidelines for my front-end repository?

To establish persistent design guidelines, you can scan your repository's README, docs, components, and style tokens, then save the extracted design context to an AI config file like .impeccable.md. This ensures consistent UI and branding decisions across future sessions.

What is a machine-readable design context and how does it solve UI inconsistency?

A machine-readable design context is a concise set of design rules and tokens saved to an AI config file. It solves UI inconsistency by providing future AI sessions with persistent guidance on typography, branding, and patterns, eliminating repeated design questions.

How do I onboard a new designer to an existing project's UI and branding patterns?

You can onboard a new designer by scanning the codebase for brand assets and style tokens, asking targeted UX questions to resolve ambiguities, and writing a Design Context section to .impeccable.md. This documents existing design principles for consistent UI generation.

Can I use automatic repository analysis to document design tokens without manual input?

Automatic repository analysis extracts existing design tokens and patterns, but it pauses to ask focused UX and brand questions where the codebase is ambiguous. This ensures human-aligned decisions before writing the final design guidelines to your AI config.

Does writing design context to CLAUDE.md work for front-end project onboarding?

Writing design context to CLAUDE.md works for front-end onboarding by appending persistent UI and branding guidelines. The skill optionally adds the documented design rules there, ensuring all future AI sessions reuse the same visual standards.

What are the limitations of relying on a repository scan for UX design context?

A repository scan cannot infer unwritten UX intent, so it limits accuracy when code is ambiguous. It requires targeted UX questions to fill gaps before writing to .impeccable.md, meaning incomplete repos may yield partial design guidelines.