agentsclimarketplace

Ss reference

Skill bitjaru/styleseed/engine/.claude/skills/ss-reference

Open-source design-method engine for Claude Code, Codex & Cursor. Gives coding agents fixed design judgment—not one fixed aesthetic—then selects or derives the right grammar from references, locks project decisions, and verifies UI, carousels, decks & docs. 20 skills · MIT.

Install
npx -y skills add bitjaru/styleseed --skill ss-reference

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

What its author says it does

Copied from the file, not written here

Compile screenshots, URLs, Figma exports, or an existing UI into a project-local StyleSeed output grammar with evidence, tokens, confidence, anti-patterns, and a validation screen. Use when the user supplies a design reference that StyleSeed does not already model.

SKILL.md

2.2 KB, as published. Nobody here has run it

Compile references into a design grammar

Do not merely imitate the supplied screen. Read PRODUCT-PRINCIPLES.md, RULESETS.md, ADAPTERS.md, and REFERENCE-COMPILER.md, then execute the compiler pipeline in full.

Workflow

  1. Ingest every supplied reference and assign evidence IDs (R1, R2, ...). If a URL can be rendered, capture it. If an image cannot be seen, stop claiming visual analysis for it.
  2. Separate references by surface adapter and job. Do not merge a marketing homepage with an app dashboard unless the user explicitly wants both languages connected.
  3. Observe and measure the twelve axes. Every rule cites evidence IDs and a confidence level.
  4. Resolve contradictions instead of averaging them. Explain any material choice briefly.
  5. Choose the nearest built-in fallback grammar and adapter, then compile the project artifacts required by REFERENCE-COMPILER.md under .styleseed/rulesets/<slug>/.
  6. Update STYLESEED.md to select reference:<slug> while preserving bounded brand choices.
  7. Validate transfer: apply the grammar to one representative screen not present in the source set, run /ss-score, then /ss-verify if renderable. Fix and repeat to the gate floor.
  8. Report what was learned, what remains low-confidence, where the artifacts live, and the validation result.

Rules

  • Visible evidence before adjectives. “Calm” is not a rule; the spacing, type, color, hierarchy, and motion decisions that create calm are rules.
  • Never copy protected assets, brand marks, or prose.
  • One reference produces a provisional grammar. Say so and keep confidence low where warranted.
  • The generated grammar is project-local. Do not edit RULESETS.md or publish it as built-in.
  • Core invariants and accessibility remain non-negotiable.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.