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
- Rojios/everything-claude-codetheir own version, first seen Nov 8, 2026
- caidanw/skillstheir own version, first seen Nov 8, 2026
- Adelie-Squad/solosquadtheir own version, first seen Nov 8, 2026
- darkweb19/skillstheir own version, first seen Nov 8, 2026
- dmoreq/agent-grimoiretheir own version, first seen Nov 8, 2026
- ahmadvahidi/skill-atlastheir own version, first seen Nov 8, 2026
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.
CoralGameSkillsetup-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
CoralGameSkillteam-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
lilangMaxSkillasset-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
lilangMaxSkillcreate-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
Other versions192 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 192
- nextlevelbuilder/ui-ux-pro-max-skill★ 147ksame name
- getsentry/sentry★ 46ksame name
- anthropics/knowledge-work-plugins★ 35ksame name
- Donchitos/Claude-Code-Game-Studios★ 27ksame name
- ethereum/ethereum-org-website★ 6ksame name
- langwatch/langwatch★ 5ksame name
- joye61/pic-smaller★ 2.9ksame name
- daveebbelaar/bama★ 1.7ksame name
- reatom/reatom★ 1.4ksame name
- microsoft/power-platform-skills★ 1.1ksame name
182 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository52 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- testing/CLAUDE.mdCLAUDE.md
- a11y-auditSkill
- adoptSkill
- api-contractSkill
- architecture-decisionSkill
- architecture-reviewSkill
- backlogSkill
- brainstormSkill
- changelogSkill
- code-reviewSkill
- collaboration-protocolSkill
- create-storiesSkill
- data-modelSkill
- dependency-auditSkill
- deploySkill
- dev-storySkill
- docsSkill
- feature-specSkill
- game-conceptSkill
- hardenSkill
- helpSkill
- hotfixSkill
- impactSkill
- incidentSkill
- initSkill
- migrateSkill
- pentestSkill
- perf-auditSkill
- product-specSkill
- qa-planSkill
- refactorSkill
- release-checklistSkill
- retrospectiveSkill
- security-auditSkill
- setup-stackSkill
- skill-improveSkill
- skill-testSkill
- sprint-planSkill
- sprint-statusSkill
- stack-updateSkill
- startSkill
- story-doneSkill
- team-featureSkill
- team-gameSkill
- team-releaseSkill
- team-securitySkill
- tech-debtSkill
- test-setupSkill
- threat-modelSkill
- updateSkill
- ux-specSkill
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
- Very specific: line 35
When HEAD is a story branch, name it and ask one AskUserQuestion: switch to the default branch and commit there (Recommended — a …
“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.
Files
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 darkandlight-dark()per role in the draft. - No dark theme: one colour set,
color-scheme: light, nolight-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 amat.theme()call in the theme SCSS, asangular.mdstates; the--ds-*roles are mapped onto the--mat-*system tokens, never onto component internals) /--tui-*(Taiga) /@theme(Tailwind-based kits andcustom). Show atokens.cssdraft (@layer base { :root { --ds-… } }, withlight-dark()only in the dark-theme case) and, for Material, themat.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 thedocs:commit — name it and offer the chore lane (git-workflow.md § Chore / infra, branchchore/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.
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
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.

