brand-extractor
Crawls target websites, captures high-fidelity viewport and full-page screenshots, extracts computed CSS tokens from the DOM, and synthesizes structured Brand DNA and a DESIGN.md specification adhering strictly to the Design Alpha spec. Use when analyzing an existing website's visual brand identity, extracting color palettes, typography, spacing, and shape tokens, or generating a DESIGN.md design system.
- Version
- 1.0.0
- License
- Apache-2.0
- Compatibility
- Requires python3 and google-chrome or chromium for automated browser crawl.
Pinned to revision 649ef66d30d5, so it is the text this page describes rather than whatever the author pushed since.
Files
- skills/brand-extractor/SKILL.md
- skills/brand-extractor/assets/brand_dna.template.json
- skills/brand-extractor/assets/design_md.template
- skills/brand-extractor/references/BRAND_DNA_SCHEMA.md
- skills/brand-extractor/references/DESIGN_MD_SPEC.md
- skills/brand-extractor/scripts/extract_brand_dna.py
- skills/brand-extractor/scripts/validate_design_md.py
Every link opens the file at its source, pinned to the revision this page describes.