skills/brand-generate/SKILL.md
Generate complete brand design systems with design tokens, CSS variables, React components, and example pages. Use when the user wants to create a new brand identity, design system, brand guidelines, or needs design tokens/component libraries. Also trigger when they mention brand colors, typography systems, or want to scaffold a design system project. Supports interactive generation, JSON config files, or quick one-line commands.
npx skillsauth add irismaker/ai-agent-skills-hub brand-generateInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Generate complete, production-ready brand design systems using the @irismaker/brand-design-system-template toolkit. This skill helps create comprehensive design systems including semantic color naming, design tokens, CSS variables, React components, and brand identity guidelines.
When invoked, this skill will:
Use this skill when the user wants to:
Automatically detect which mode the user wants:
Interactive Mode - When the user:
Config File Mode - When the user:
Quick Mode - When the user provides all info in one message:
Gather the following information (adapt based on mode):
Required:
Recommended:
Optional:
./brands/{brand-name-slug}/)Color Format Validation: Primary color must be a valid hex code (e.g., #FF5733, #0066CC). If the user provides a color name like "blue" or "corporate blue", ask them to specify the exact hex code or suggest finding their brand color first.
Before generating, check the project setup:
# Check if the package is installed globally
npm list -g @irismaker/brand-design-system-template
# Check if it's in the current project
npm list @irismaker/brand-design-system-template
# Check if we're in a cloned repo
ls -la generate-brand.js build.js 2>/dev/null
If not installed:
npm install -g @irismaker/brand-design-system-templategit clone https://github.com/irismaker/design-system-starter.gitBased on available tools and user preference:
Method A: Interactive Generator (npx brand-generate)
npx brand-generate
This will prompt for each field interactively. Use this when the user wants a guided experience.
Method B: Config File Build (npx brand-build)
First, create the config file at a sensible location (e.g., ./brand-config.json):
{
"brandName": "Brand Name",
"domain": "example.com",
"slogan": "Your brand slogan",
"primaryColor": "#0066CC",
"fontFamily": "Inter",
"colorNamingStyle": "tech"
}
Then build:
npx brand-build ./brand-config.json ./brands/brand-name
Method C: Programmatic (if in a Node.js project)
const { build } = require('@irismaker/brand-design-system-template');
await build('./brand-config.json', './brands/brand-name');
Smart Default for Output Path:
Use ./brands/{brand-name-slug}/ where {brand-name-slug} is the lowercase, hyphenated version of the brand name (e.g., "Acme Inc" → "acme-inc"). This keeps multiple brands organized. The user can always override this.
Run the chosen method. For interactive mode, the tool will handle the prompts. For config-based generation, create the config file first, then run the build command.
Important: The generation should create these files in the output directory:
config.json - Brand configurationdesign-tokens.json - Design token definitionsdesign-system.css - CSS variables and utilitiescomponents.tsx - React component library (if applicable)example.html - Example page demonstrating the systembrand-identity-outline.md - Brand guidelines and documentationAfter generation:
ls -la ./brands/brand-name/
Show a summary of what was generated:
Preview the design system (optional):
example.html in a browserSuggest relevant next steps:
For developers:
<link rel="stylesheet" href="./brands/brand-name/design-system.css">For designers:
For teams:
If the package isn't installed and the user doesn't want to install it globally, guide them to:
git clone https://github.com/irismaker/design-system-starter.gitcd design-system-starternode generate-brand.jsIf the user provides an invalid color (like "blue" instead of "#0066FF"), explain that you need a hex code and help them:
If the output directory already exists, inform the user and ask:
brand-name-v2)?If the user provides partial information (e.g., only brand name), gather the remaining required fields before proceeding. At minimum, you need:
Domain, slogan, and font can be optional or use sensible defaults.
Example 1: Quick generation
User: "Create a design system for Stellar Labs, primary color #6B4FBB, domain stellar-labs.io"
Response:
- Detect: Quick mode with all required info
- Create config with provided details
- Use default font (Inter) and output path (./brands/stellar-labs/)
- Run: npx brand-build ./stellar-labs-config.json ./brands/stellar-labs
- Preview: Show generated files and design tokens
Example 2: Interactive generation
User: "I want to create a brand design system"
Response:
- Detect: Interactive mode
- Check if package is installed
- Run: npx brand-generate
- Guide the user through the prompts
- Preview results after generation
Example 3: Config file mode
User: "Use this config file to generate my design system: ./my-brand.json"
Response:
- Detect: Config file mode
- Read the config file to understand the brand
- Ask for output path if not specified
- Run: npx brand-build ./my-brand.json ./brands/output-dir
- Verify and show results
Color selection matters: Help users choose accessible, on-brand colors. If they're unsure, suggest looking at their existing brand materials or website.
Typography: If the user doesn't specify a font, recommend Inter as a modern, versatile default. Other good options: Roboto (safe, readable), Poppins (friendly), Montserrat (geometric).
Naming style: The color naming style affects how semantic colors are named. "tech" is safe for most projects. "nature" works for eco/wellness brands, "finance" for professional services, "creative" for agencies.
Organization: Encourage using the ./brands/ directory structure to keep design systems organized, especially if they manage multiple brands.
Iteration: Design systems evolve. If the user needs to regenerate or tweak their system, they can edit the config file and rebuild quickly.
tools
When the user wants to create, generate, or produce video content using AI tools or programmatic frameworks. Also use when the user mentions 'video production,' 'AI video,' 'Remotion,' 'Hyperframes,' 'HeyGen,' 'Synthesia,' 'Veo,' 'Runway,' 'Kling,' 'Pika,' 'video generation,' 'AI avatar,' 'talking head video,' 'programmatic video,' 'video template,' 'explainer video,' 'product demo video,' 'video pipeline,' or 'make me a video.' Use this for video creation, generation, and production workflows. For video content strategy and what to post, see social-content. For paid video ad creative, see ad-creative.
tools
When the user wants to create, plan, or optimize a lead magnet for email capture or lead generation. Also use when the user mentions "lead magnet," "gated content," "content upgrade," "downloadable," "ebook," "cheat sheet," "checklist," "template download," "opt-in," "freebie," "PDF download," "resource library," "content offer," "email capture content," "Notion template," "spreadsheet template," or "what should I give away for emails." Use this for planning what to create and how to distribute it. For interactive tools as lead magnets, see free-tool-strategy. For writing the actual content, see copywriting. For the email sequence after capture, see email-sequence.
development
When the user wants to create, generate, edit, or optimize images for marketing — blog heroes, social graphics, product mockups, profile banners, listing visuals, or brand assets. Also use when the user mentions 'AI image generation,' 'generate an image,' 'create a graphic,' 'product mockup,' 'hero image,' 'social media graphic,' 'banner image,' 'cover photo,' 'profile banner,' 'listing screenshot,' 'Flux,' 'Midjourney,' 'DALL-E,' 'GPT Image,' 'Ideogram,' 'Gemini image,' 'Canva,' 'Figma,' 'image optimization,' 'compress images,' 'WebP,' or 'OG image.' Use this for general-purpose marketing image creation and optimization. For paid ad image creative and platform-specific ad specs, see ad-creative. For video production, see video.
testing
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases. Credits: Original skill by @blader - https://github.com/blader/humanizer