design-system
Skill1 starsChanged 7 months agoMITView on GitHub
Audit, document, or extend your design system. Use when checking for naming inconsistencies or hardcoded values across components, writing documentation for a component's variants, states, and accessibility notes, or designing a new pattern that fits the existing system. Trigger phrases: "design system audit", "document this component", "design system review", "naming conventions", "add to design system", "component documentation", "design tokens", "pattern library", "extend the design system", "system consistency"
193 other projects use a version of this.
Adopted by
Most recently taken up by
- ohvignas/lancetonsitetheir own version, first seen Nov 16, 2026
- lengrufeng2008/dsh-skill-librarytheir own version, first seen Nov 15, 2026
- dmoreq/precepttheir own version, first seen Nov 15, 2026
- carlos2219/web-kittheir own version, first seen Nov 15, 2026
- kobiniv888-ai/Claude-codetheir own version, first seen Nov 15, 2026
- chuanglibs/Claude-Code-Game-Studios-Codextheir own version, first seen Nov 15, 2026
Used with
Projects with it also use setup-engine, team-level and 10 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
lilangMaxSkillcreate-stories
Break a single epic into implementable story files. Reads the epic, its GDD, governing ADRs, and control manifest. Each story embeds its GDD requirement TR-ID, ADR guidance, acceptance criteria, story type, and test evidence path. Run after /create-epics for each epic.
Also in 11 projects that use this
lilangMaxSkillstory-done
End-of-story completion review. Reads the story file, verifies each acceptance criterion against the implementation, checks for GDD/ADR deviations, prompts code review, updates story status to Complete, and surfaces the next ready story from the sprint.
Also in 11 projects that use this
- +2 more from CoralGame
- +6 more from lilangMax
Other versions193 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 193
- nextlevelbuilder/ui-ux-pro-max-skill★ 150ksame name
- getsentry/sentry★ 46ksame name
- Donchitos/Claude-Code-Game-Studios★ 39ksame name
- anthropics/knowledge-work-plugins★ 36ksame 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★ 1.2ksame name
183 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 repository164 other files it gives its agents.
- instrument-data-to-allotropeSkill
- literature-reviewSkill
- nextflow-developmentSkill
- scientific-problem-selectionSkill
- scvi-toolsSkill
- single-cell-rna-qcSkill
- discover-brandSkill
- enforce-voiceSkill
- generate-guidelinesSkill
- csat-reportSkill
- customer-escalationSkill
- customer-researchSkill
- draft-responseSkill
- kb-articleSkill
- sentiment-analysisSkill
- ticket-triageSkill
- analyzeSkill
- build-dashboardSkill
- create-vizSkill
- data-context-extractorSkill
- data-modelingSkill
- data-pipelineSkill
- etl-designSkill
- explore-dataSkill
- sql-queriesSkill
- statistical-analysisSkill
- validate-dataSkill
- write-querySkill
- accessibility-reviewSkill
- component-librarySkill
- design-critiqueSkill
- design-handoffSkill
- frontend-designSkill
- research-synthesisSkill
- user-researchSkill
- ux-copySkill
- wireframingSkill
- Agent DevelopmentSkill
- CLAUDE.md ManagementSkill
- MCP Server BuilderSkill
- Plugin DevelopmentSkill
- Prompt EngineeringSkill
- Skill CreatorSkill
- curriculum-designSkill
- lesson-planningSkill
- quiz-generatorSkill
- study-guideSkill
- tutoringSkill
- api-designSkill
- architectureSkill
- ci-cd-pipelineSkill
- code-reviewSkill
- database-migrationSkill
- debugSkill
- dependency-auditSkill
- deploy-checklistSkill
- documentationSkill
- error-handlingSkill
- git-workflowSkill
- incident-responseSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
8 rules. 0 are common, 7 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 175 edited versions we read keep these.
7
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
- Distinctive: line 71
Use this template for each component:
- Distinctive: line 103
When adding a new component or pattern:
- Distinctive: line 116
Design all states: Before documenting, ensure these are designed:
- Distinctive: line 117
Default, Hover, Active, Focus, Disabled
- Distinctive: line 157
Response: Write the full component doc including purpose, anatomy (overlay, container, header, body, footer), variants (default, alert, …
- Very specific: line 165
Semantic naming over visual naming: Use color-text-primary not color-dark-gray.
- Distinctive: line 168
Version components: When making breaking changes, version the component API so consumers can migrate gradually.
- Distinctive: line 172
Accessibility is not optional: Every component needs keyboard behavior, screen reader support, and focus management documented.
“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 Management
Audit, document, and extend design systems. Ensure naming consistency, comprehensive component documentation, and patterns that scale.
Workflow
Step 1: Determine the Task
| Task Type | Approach |
| Audit | Review existing system for inconsistencies, gaps, and technical debt |
| Document | Write or improve documentation for existing components |
| Extend | Design a new component or pattern that fits the system |
| Refactor | Rename, restructure, or consolidate existing patterns |
Step 2: Audit the System (if auditing)
Check each layer:
Token Audit
### Token Consistency Check
#### Colors
- [ ] Named semantically (color-text-primary, not color-gray-900)
- [ ] No hardcoded hex values in components
- [ ] Dark mode / theme-aware tokens exist
- [ ] Consistent naming pattern (color-{usage}-{variant})
#### Typography
- [ ] Type scale follows a consistent ratio
- [ ] No orphan font sizes outside the scale
- [ ] Font weights are tokenized (not raw 400, 600)
- [ ] Line heights are paired with font sizes
#### Spacing
- [ ] Spacing scale is consistent (4px base, 8px increments, etc.)
- [ ] No arbitrary spacing values in components
- [ ] Spacing tokens used for margin and padding
#### Shadows, Radii, Borders
- [ ] Consistent elevation system (shadow-sm, shadow-md, shadow-lg)
- [ ] Border radius values are tokenized
- [ ] Border colors reference color tokensComponent Audit
### Component Consistency Check
| Component | Naming | Variants | States | A11y | Docs | Score |
|-----------|--------|----------|--------|------|------|-------|
| Button | OK | Full | Full | Yes | Yes | 5/5 |
| Input | OK | Partial | Missing error | No | Partial | 2/5 |
| Card | Inconsistent | None | None | No | No | 1/5 |Score components on: naming consistency, variant coverage, state coverage, accessibility attributes, and documentation quality.
Step 3: Document Components (if documenting)
Use this template for each component:
## [Component Name]
### Purpose
[One sentence: what this component is for and when to use it]
### When to Use
- [Use case 1]
- [Use case 2]
### When NOT to Use
- [Anti-pattern 1]: Use [Alternative] instead
- [Anti-pattern 2]: Use [Alternative] instead
### Anatomy, Variants, States, Props, Accessibility
Document each component's anatomy (parts and their roles), variants (visual options with purpose), states (default through loading with visual changes), props/API (type, default, description), and accessibility requirements (ARIA role, keyboard behavior, screen reader announcements, focus management).
### Usage Examples
[Code examples showing common usage patterns]
### Do's and Don'ts
| Do | Don't |
|----|-------|
| Use for primary page actions | Use more than one primary button per section |
| Include clear, action-oriented labels | Use vague labels like "Click here" |Step 4: Extend the System (if adding)
When adding a new component or pattern:
- Check for existing patterns. Does something similar already exist? Can an existing component be extended instead?
- Follow the naming convention. Match the existing system's naming patterns:
Existing: Button, ButtonGroup, IconButton New: LinkButton (follows pattern) Wrong: BtnLink (breaks pattern) - Use existing tokens. New components should reference existing tokens, not introduce new values.
- Design all states. Before documenting, ensure these are designed:
- Default, Hover, Active, Focus, Disabled
- Loading, Empty, Error (where applicable)
- Responsive variants (if layout changes at breakpoints)
- Define composition rules. How does this component work with others?
Step 5: Compile the Output
For audits:
## Design System Audit: [System Name]
Date: [Date]
### Summary
- **Components audited**: [N]
- **Issues found**: [N critical, N major, N minor]
- **Overall health**: [Good / Needs work / Significant gaps]
### Token Issues
[Findings]
### Component Issues
[Findings with priority]
### Recommendations
1. [Action item with priority]
2. [Action item with priority]
### Roadmap
[Suggested order of improvements]Examples
Example 1: System Audit
User: "Audit our design system for consistency issues." Response: Review tokens for naming patterns and orphan values. Check each component for state coverage and documentation. Identify hardcoded values that should be tokens. Report findings ranked by impact.
Example 2: Component Documentation
User: "Document our Modal component." Response: Write the full component doc including purpose, anatomy (overlay, container, header, body, footer), variants (default, alert, confirmation), states (opening, open, closing), props, accessibility (focus trap, Escape to close, aria-modal), and composition with other components.
Example 3: New Pattern
User: "We need an empty state pattern for our design system." Response: Review how other empty states in the product look (if any). Propose a pattern with: illustration slot, heading, body text, and CTA button. Define variants (first-time, no results, error). Document sizing, spacing using existing tokens, and when to use each variant.
Best Practices
- Semantic naming over visual naming. Use
color-text-primarynotcolor-dark-gray. Semantic names survive theme changes and rebrands. - Document the why, not just the what. "Use Primary for the single most important action on a screen" is more useful than "Primary: blue button."
- Include anti-patterns. Showing what not to do is as valuable as showing what to do. Developers reference these when making decisions.
- Version components. When making breaking changes, version the component API so consumers can migrate gradually.
- Audit regularly. Design systems drift as products evolve. Quarterly audits catch inconsistencies before they compound.
- Single source of truth. Tokens should be defined once and consumed everywhere. If a token changes, it should propagate automatically.
- Design for composition. Components should combine predictably. Test common compositions and document how components work together.
- Accessibility is not optional. Every component needs keyboard behavior, screen reader support, and focus management documented. This is a baseline, not an enhancement.
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.

