design-score
Skill8 starsChanged 7 months agoMITView on GitHub
Quick design score card covering 12 dimensions with the top 5 improvements, in under 2 minutes. Use when the user asks for a design score, to score their design, to rate their UI, or for a quick audit.
In this repository16 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- llms.txtllms.txt
- a11y-auditSkill
- color-auditSkill
- component-auditSkill
- design-auditSkill
- design-checklistSkill
- design-compareSkill
- design-tokensSkill
- flow-auditSkill
- layout-auditSkill
- refactor-planSkill
- style-directionSkill
- theme-builderSkill
- type-auditSkill
The file
Files
/design-score: Quick Design Score Card
Fast score across 12 dimensions. Takes under 2 minutes.
Flow
- Fast scan of project styling and component files
- Quick-score each dimension (heuristic-based, not deep audit)
- Calculate weighted overall score
- Identify top 5 highest-impact improvements
- Output concise score card
Output
Design Score: 7.2/10 - Good
Color System: 8/10 |########..|
Typography: 6/10 |######....|
Layout & Spacing: 7/10 |#######...|
Components: 7/10 |#######...|
Accessibility: 5/10 |#####.....|
Visual Hierarchy: 8/10 |########..|
Interaction: 6/10 |######....|
Responsiveness: 7/10 |#######...|
Visual Polish: 8/10 |########..|
Performance UX: 6/10 |######....|
IA & Flows: 7/10 |#######...|
Platform: 8/10 |########..|
Top 5 Improvements:
1. [critical] Add focus indicators for keyboard navigation
2. [important] Body text contrast is 3.2:1, needs 4.5:1
3. [important] Consolidate 47 unique colors to ~20
4. [suggestion] Add skeleton screens for data loading
5. [suggestion] Establish consistent spacing scale (currently 23 unique values)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.