Extract design system
Skill kimtth/agent-skill-100-lines-or-less/skills/extract-design-system
🧿 Minimal but effective AI agent skill definitions in 100 lines or less.
npx -y skills add kimtth/agent-skill-100-lines-or-less --skill extract-design-systemAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Use when: extract tokens, components, and patterns from an existing codebase into a documented system.
SKILL.md
1.1 KB, as published. Nobody here has run it
Goal: recover the implicit design system already in the code.
Use for:
- inconsistent UI grown without a defined system
- documenting tokens and patterns for reuse
- preparing a refactor toward shared components
Workflow:
- Inventory colors, spacing, type, radius, and shadow values in use.
- Cluster near-duplicates into canonical tokens.
- Identify repeated component shapes (buttons, cards, inputs).
- Note variant axes: size, intent, and state.
- Document the tokens and components with usage rules.
- Flag outliers to reconcile and propose the migration order.
Capture:
- token tables with names and values
- component catalog with variants
- spacing and type scales
- inconsistencies and one-offs to resolve
Rules:
- derive tokens from real usage, not invention
- collapse accidental near-duplicates deliberately
- keep names semantic so intent survives refactors
- record outliers instead of silently normalizing them