agentleFS
divyanshu-iitiandivyanshu-iitian/agent-website-design-skills/web-design-system/SKILL.md

web-design-system

Skill2 starsChanged 4 months agoMITView on GitHub

Extract, create, or refine an implementation-ready design system for a website or web app. Use when an agent needs semantic tokens, component anatomy, variants, interaction states, responsive rules, accessibility defaults, or consistency improvements grounded in an existing frontend codebase.

The file

We split this skill into the rules it gives an agent

11 rules. About 0 are common, 11 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈11

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Extract: when the product is visually coherent but undocumented.

    line 12
  2. Distinctive:

    Reconcile: when multiple patterns conflict.

    line 13
  3. Distinctive:

    Create: when a new product has no established UI language.

    line 14
  4. Distinctive:

    Extend: when a feature needs states or components the system lacks.

    line 15
  5. Distinctive:

    Verify light/dark themes, core states, narrow/wide layouts, and at least one realistic content stress case.

    line 31
  6. Distinctive:

    Keep primitive escape hatches available, but make the correct path easier.

    line 36
  7. Distinctive:

    Do not force every region into a card.

    line 37
  8. Distinctive:

    Do not encode status through color alone.

    line 38
  9. Distinctive:

    Keep component APIs small.

    line 39
  10. Distinctive:

    Document decisions where future contributors would otherwise recreate the inconsistency.

    line 41
  11. Distinctive:

    Read references/token-checklist.md while defining or auditing tokens and component states.

    line 55

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Web Design System

Build the smallest system that makes the product more coherent. Favor semantic contracts that components can use over a large inventory of decorative values.

Choose the Mode

  • Extract when the product is visually coherent but undocumented.
  • Reconcile when multiple patterns conflict.
  • Create when a new product has no established UI language.
  • Extend when a feature needs states or components the system lacks.

Workflow

  1. Inspect the framework, CSS strategy, theme files, primitives, component library, icon set, and representative screens.
  2. Inventory repeated values and patterns. Separate intentional variation from accidental drift.
  3. Map raw values to semantic roles before changing code. Example: blue-600 -> action-primary, not "replace every blue."
  4. Define the minimum token layers:
    • foundations: color, type, spacing, radius, border, shadow, motion;
    • semantic tokens: background, surface, text, border, action, focus, and status;
    • component tokens only where a component genuinely needs them.
  5. Specify component anatomy, variants, sizes, and state behavior. Include content constraints, not only appearance.
  6. Define responsive behavior and density rules without inventing device-specific duplicates.
  7. Encode accessibility defaults: semantic elements, names, labels, focus-visible, keyboard behavior, contrast, errors, target size, and reduced motion.
  8. Implement inside the existing styling mechanism. Avoid parallel token systems.
  9. Migrate one representative component or screen and remove superseded values when safe.
  10. Verify light/dark themes, core states, narrow/wide layouts, and at least one realistic content stress case.

System Rules

  • Name tokens by purpose, not by current appearance.
  • Keep primitive escape hatches available, but make the correct path easier.
  • Do not force every region into a card.
  • Do not encode status through color alone.
  • Keep component APIs small; prefer composition over variant explosions.
  • Preserve established patterns unless they harm usability, accessibility, or maintainability.
  • Document decisions where future contributors would otherwise recreate the inconsistency.

Delivery Contract

Provide:

  1. Mode and audit - what exists, what conflicts, and what remains.
  2. Token map - existing value -> semantic role -> implementation location.
  3. Component contract - anatomy, variants, states, content limits, responsive behavior.
  4. Migration slice - at least one real component when code changes are requested.
  5. Verification evidence - themes, states, viewports, and exceptions tested.

Reference

Read references/token-checklist.md while defining or auditing tokens and component states.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.