teach-impeccable

Gathers project design context through codebase exploration and saves it to a persistent config file.

Updated Jul 21, 2026
One-click install
npx skills add https://github.com/masakinihirota/2026src-ni --skill teach-impeccable-masakinihirota
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: teach-impeccable
Source: https://github.com/masakinihirota/2026src-ni/tree/main/.agents/skills/teach-impeccable
Command: npx skills add https://github.com/masakinihirota/2026src-ni --skill teach-impeccable-masakinihirota

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? AI assistants start every session without knowledge of your project's design direction, leading to inconsistent UI decisions. This Skill runs a one-time setup that captures your brand personality, aesthetic preferences, and accessibility requirements, then persists them so all future sessions follow the same design guidelines. ## Core Features & Use Cases - Codebase Discovery: Scans README files, package configs, existing components, brand assets, and CSS variables to infer design context before asking questions. - Targeted UX Questioning: Asks only about what cannot be inferred, covering users, brand personality, aesthetic direction, and accessibility needs. - Persistent Design Context: Writes a structured Design Context section to .impeccable.md and optionally to .github/copilot-instructions.md. - Use Case: A developer starting a new web app runs this once; every later AI session then generates UI code aligned with the established brand personality and design principles. ## Quick Start Ask the AI to run the teach-impeccable setup to establish persistent design guidelines for this project.

Frequently Asked Questions about teach-impeccable

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

FAQPage Schema
How do I set up persistent design guidelines for AI coding assistants?▼

Run this one-time setup skill, which explores your codebase for existing design signals, asks targeted UX questions, and writes a Design Context section to .impeccable.md. Future AI sessions read this file to stay consistent.

What questions does the design context setup ask?▼

It asks about users and their goals, brand personality in three words, reference and anti-reference sites, visual direction preferences, light or dark mode, color constraints, and accessibility requirements such as WCAG level or reduced motion.

Does this work with GitHub Copilot instructions?▼

Yes. After writing the Design Context to .impeccable.md, the skill optionally appends the same section to .github/copilot-instructions.md so Copilot sessions also follow the established guidelines.

When should I run the design context setup?▼

Run it once at the start of a project or when design direction changes. It is a one-time setup; if .impeccable.md already exists, the Design Context section is updated in place rather than duplicated.

What does the skill infer from the codebase automatically?▼

It scans the README, package.json, existing components, brand assets like logos and favicons, CSS variables, and design tokens to learn the tech stack, color palettes, typography, and spacing already in use before asking questions.