Brand Context Injector
Apply your project's design system to UI, styling, and copy decisions automatically.
Installation
- Make sure Claude is on your device and in your terminal.
Skills load from
~/.claude/skills/when Claude Code starts up — so you need it on your machine first. If you don't have it yet, install it once with the command below, then runclaudein any terminal to verify.One-time setupnpm i -g @anthropic-ai/claude-codeAlready have it? Skip ahead.
- Paste into Claude Code or into your terminal.
This copies the whole skill folder into
~/.claude/skills/omd-apply-kwakseongjae/— the SKILL.md plus any scripts, reference docs, or templates the skill ships with. Safe default: works for every skill.Faster alternative (instruction-only skills)
Skips the clone and grabs only the SKILL.md file. Don't use this if the skill ships Python scripts, reference markdowns, or asset templates — they won't be downloaded and the skill will fail when it tries to load them.
Quick install (SKILL.md only)Sign up to copy - Restart Claude Code.
Quit and reopen Claude Code (or any other agent that loads from
~/.claude/skills/). New skills are picked up on startup. - Just ask Claude.
Skills auto-activate when your request matches the skill's description — no slash command needed. Trigger phrases live in the skill's own frontmatter; you can read them in the “What this skill does” section above.
Prefer to read the source first? Open on GitHub.
When Claude uses it
Use when building UI, styling, writing microcopy, or tuning motion in a project that has a DESIGN.md — applies that file as the authoritative brand context for every design decision, and learns from your corrections.
What this skill does
This skill applies your project's design system file (DESIGN.md) as the authoritative reference for every UI, styling, microcopy, and motion decision you make. It reads your design tokens, component rules, and voice guidelines—then learns from your corrections by automatically logging them to a preferences file for future consistency.
What it does
- Loads and enforces DESIGN.md rules across component creation, CSS changes, microcopy, animations, and color/typography/spacing adjustments—without inventing missing tokens.
- Prioritizes pending corrections from
.omd/preferences.mdover the base design file, so your latest feedback always takes precedence. - Applies voice guidelines to all microcopy (button labels, error messages, tooltips) by matching sentence length, vocabulary register, and tone to your documented brand voice.
- Automatically captures design corrections when you override a choice, revert a token, or state a design principle—logging them via the
omd remembercommand without asking first. - Reports logged corrections with a single-line confirmation so you can review or fold them into DESIGN.md later using
omd learn --apply.
How to use it
Trigger the skill whenever you're building a UI component, modifying styles, writing microcopy, tuning animations, or asking design-system questions in a project with a DESIGN.md file. The skill reads that file and your .omd/preferences.md (if present), then applies those rules to every decision. When you correct a choice—by saying "no, use X instead," reverting a token value, or stating a design principle—the skill automatically logs it for learning.
Related skills
Generative Code Art
anthropics
Create algorithmic art with p5.js using randomness and interactive parameters.
UI/UX Pro Max
anthropics
Build production-grade web components and interfaces with distinctive, polished design.
Artifact Theme Toolkit
anthropics
Apply professional color and font themes to slides, docs, and web pages.
Multi-Component Web Artifacts
anthropics
Build complex React artifacts with Tailwind CSS and shadcn/ui components.