Back to directory

design-dna

An agent skill that extracts a reference UI's visual identity, its design tokens, qualitative style and visual effects, into a structured Design DNA JSON, then generates matching UI from new content.

design-dna

design-dna is an agent skill for extracting, structuring and applying visual design identity as machine-readable Design DNA across three dimensions: measurable design tokens (color, typography, spacing, layout, shape, elevation, motion, components), qualitative style (mood, visual language, composition, imagery, interaction feel, brand voice), and visual effects beyond plain CSS, such as canvas, WebGL, 3D, particles, shaders and glassmorphism.

Its three-phase workflow structures the schema, analyzes screenshots, images or live URLs into a complete quantified JSON profile noting any conflicts across references, and generates matching UI, by default as self-contained HTML/CSS/JS, from that profile plus new content. The phases can be run alone or chained.

It installs into an agent such as Cursor or Claude Code with the skills CLI over npx, or from a local clone.

More in Agent skills

See all 581
  • Provenance gate

    github.com

    A deterministic authorization gateway that sits between an AI agent and its tools, tracing where each parameter of a side-effect call came from, and blocking the call or asking a human when the source does not check out.

  • A markdown framework of system rules that restates Isaac Asimov's Four Laws of Robotics as a set of prioritized loss calculations for large-language-model agents to follow, published as a discovery file for agents and crawlers to read.

  • Vitruvius

    github.com

    An engineering research agent that runs a discover, read, synthesize, verify and review loop over technical questions, reading sources directly rather than inferring from titles, and publishing its own scored verifier benchmark, weaknesses included.