excrtx-brandkit-generator

Extract color palettes from logos and campaign assets to generate WCAG-compliant DESIGN.md token files.

1|Updated May 26, 2026
One-click install
npx skills add https://github.com/elderbernardi/exocortex.saas --skill excrtx-brandkit-generator-elderbernardi
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: excrtx-brandkit-generator
Source: https://github.com/elderbernardi/exocortex.saas/tree/main/skills/excrtx-brandkit-generator
Command: npx skills add https://github.com/elderbernardi/exocortex.saas --skill excrtx-brandkit-generator-elderbernardi

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires Pillow, scikit-learn, numpy, cairosvg, @google/design.md, and includes scripts (resource) and references (resource) components.

What problem does it solve? Translating a visual brand identity (a logo, a multi-asset campaign, or a technical ASCII/CLI brand) into a structured, accessible design token system is manual and error-prone. This Skill automates palette extraction, WCAG AA contrast validation, and DESIGN.md generation in the correct scope. ## Core Features & Use Cases - Logo Palette Extraction: Extract dominant colors from PNG/JPG via K-Means clustering or parse explicit fill/stroke colors from SVG, then classify them into primary, secondary, tertiary, accent, neutral, and dark roles. - WCAG AA Validation: Automatically compute contrast ratios and adjust on-primary/on-tertiary colors to meet the 4.5:1 threshold, then lint the output with the Google design.md CLI. - Three Source Modes: Handle single logos, multi-asset campaigns (flat pieces plus photography plus brand manuals), and editorial book covers derived from technical or developer-facing brands. - Use Case: Given a client logo at /tmp/acme-logo.png and a microverso slug, generate a complete DESIGN.md with derived semantic colors, validated contrast, and a passing lint result written to the Acervo cascade. ## Quick Start Ask the assistant to generate a visual identity for client Acme Inc from the logo file /tmp/acme-logo.png using the microverso slug acme.

Frequently Asked Questions about excrtx-brandkit-generator

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

FAQPage Schema
How do I extract a color palette from a logo image in Python?▼

Run the brandkit-extract.py script with --logo pointing to a PNG, JPG, or SVG file. Raster images are processed with K-Means clustering (n=5) via scikit-learn, while SVGs are parsed directly for explicit fill and stroke colors.

How do I generate a DESIGN.md design token file from brand assets?▼

Provide a logo path and microverso slug, or a set of campaign assets with a project root. The Skill extracts colors, classifies them into system roles, validates WCAG contrast, writes the DESIGN.md, and lints it with the Google design.md CLI.

Does the palette extraction support SVG files?▼

Yes, SVG fill and stroke colors are extracted directly without rasterization. If an SVG has no explicit colors, the script falls back to rasterization via cairosvg, which must be installed separately.

What happens if extracted colors fail WCAG contrast checks?▼

The script automatically adjusts on-primary and on-tertiary colors by lightening or darkening them until they reach the 4.5:1 ratio, and reports every adjustment in the output so you can review the final palette.

What are the limitations of logo-based palette extraction?▼

Gradients are ignored and only solid colors are extracted, palettes with fewer than 3 colors are rejected, and raster logos cannot prove a font family. Images over 10MB are resized to 256x256, which may lose subtle color detail.