agentleFS
gonimargonimar/claude-web-studio/skills/design-system/SKILL.md

design-system

Skill4 starsChanged 46 days agoMITView on GitHub

Defines the project design system — principles, --ds-* tokens (colour roles, spacing, type, radius, motion) for light/dark, component inventory with states and aria patterns, mapping onto the chosen UI kit, game HUD rules — into docs/specs/design-system.md and a tokens CSS draft. Run before UI implementation, or for 'design tokens', 'dark theme', 'component library'.

192 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use setup-engine, team-level and 8 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • CoralGameSkill

    setup-engine

    Configure the project's game engine and version. Pins the engine in CLAUDE.md, detects knowledge gaps, and populates engine reference docs via WebSearch when the version is beyond the LLM's training data.

    Also in 13 projects that use this

  • CoralGameSkill

    team-level

    Orchestrate level design team: level-designer + narrative-director + world-builder + art-director + systems-designer + qa-tester for complete area/level creation.

    Also in 12 projects that use this

  • lilangMaxSkill

    asset-spec

    Generate per-asset visual specifications and AI generation prompts from GDDs, level docs, or character profiles. Produces structured spec files and updates the master asset manifest. Run after art bible and GDD/level design are approved, before production begins.

    Also in 10 projects that use this

  • lilangMaxSkill

    create-control-manifest

    After architecture is complete, produces a flat actionable rules sheet for programmers — what you must do, what you must never do, per system and per layer. Extracted from all Accepted ADRs, technical preferences, and engine reference docs. More immediately actionable than ADRs (which explain why).

    Also in 10 projects that use this

  • +2 more from CoralGame
  • +4 more from lilangMax

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 175 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    When HEAD is a story branch, name it and ask one AskUserQuestion: switch to the default branch and commit there (Recommended — a …

    line 35

“Common” is measured: kept by at least 6 in 10 of the 175 edited versions of this file we could read. “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

Design System

Reply in the project conversation language (CLAUDE.md → Language); code, identifiers, paths and commit messages stay in English.

Template .claude/docs/templates/design-system.md. References: web-platform.md (WCAG, CSS Baseline), angular.md/vue.md (UI-kit themes). In the commands below, <hooks> is .claude/hooks/ in copy mode and ${CLAUDE_PLUGIN_ROOT}/hooks/ in plugin mode.

Phase 1: Base and principles

Base from technical-preferences.md or the argument; questions: tone (strict/playful), density, brand colours (if any), dark theme needed?, target devices. No product spec (docs/specs/product-spec.md missing) → not blocking: the questions above are asked all the same, the component needs Phase 3 would read from the spec are asked here too (the screens and controls the product will have), and the document says its inventory came from these answers, not from a spec — /product-spec is named as the follow-up that will confirm it.

Phase 2: Tokens

Draft colour roles with computed contrast (4.5:1 / 3:1), spacing/typography scales (fluid clamp()), radii/shadows/motion.

  • Dark theme wanted (Phase 1 answer): two colour sets, light and dark, each with its contrast computed; color-scheme: light dark and light-dark() per role in the draft.
  • No dark theme: one colour set, color-scheme: light, no light-dark() — the role names stay the same, so a dark set can be added later without renaming a token.
  • Mapping onto the base kit: --mat-* (Material — the theme itself is a mat.theme() call in the theme SCSS, as angular.md states; the --ds-* roles are mapped onto the --mat-* system tokens, never onto component internals) / --tui-* (Taiga) / @theme (Tailwind-based kits and custom). Show a tokens.css draft (@layer base { :root { --ds-… } }, with light-dark() only in the dark-theme case) and, for Material, the mat.theme() snippet.

Phase 3: Components and patterns

Inventory from the needs of the product spec/feature specs (or the Phase 1 answers when there is no spec); per component — states and aria pattern (WAI-ARIA APG); patterns for forms/tables/empty states/dialogs.

Phase 4: Write

Show the tokens table and the inventory in the chat, then "May I write docs/specs/design-system.md and [frontend_root]/src/styles/tokens.css?" — one AskUserQuestion: write (Recommended) · show the draft/diff first · not now — the CSS is written by css-engineer via Task after consent. After the "write" answer: touch .claude/.write-consent (rule 7 — the consent-guard hook checks the marker).

Phase 5: Commit (documents lane)

Right after the write, one commit gate (rule 7 (4), .claude/docs/git-workflow.md § Documents): docs: design system, staging exactly docs/specs/design-system.md. Record the gate before asking — <hooks>session-state.sh set Gate "/design-system Phase 5: commit?" — and clear it after the answer (<hooks>session-state.sh set Gate "—").

  • On the default branch when no story work is in progress: one AskUserQuestion — commit (Recommended) · leave uncommitted.
  • When HEAD is a story branch, name it and ask one AskUserQuestion: switch to the default branch and commit there (Recommended — a pipeline-wide document) · commit here (the document belongs to this story) · leave uncommitted.
  • [frontend_root]/src/styles/tokens.css (and a Material theme SCSS) is code, not a document: it never rides the docs: commit — name it and offer the chore lane (git-workflow.md § Chore / infra, branch chore/design-tokens) or the first UI story it belongs to.

Nothing is committed without the answer.

Verdict: COMPLETE. Next step — one AskUserQuestion: /ux-spec for the first flow (Recommended) · /feature-spec · revise the tokens.

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.