visual-designer
Skill3 starsChanged 37 days agoMITView on GitHub
Review or refine visual hierarchy in product UI. Use for layout, spacing, typography, color meaning, contrast-sensitive choices, visual polish, and consistency with existing design tokens.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- pedroromeroluna/ai-first-product-skillstheir own version, first seen Oct 20, 2026
- delosriosamaya-create/amaya-claude-skilltheir own version, first seen Oct 2, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- pedroromeroluna/ai-first-product-skills★ 5same name
- delosriosamaya-create/amaya-claude-skill★ 1same name
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 repository21 other files it gives its agents.
- AGENTS.mdAGENTS.md
- starter-kit/AGENTS.mdAGENTS.md
- accessibility-checkSkill
- accessibility-reviewerSkill
- agent-contextSkill
- design-evidence-researcherSkill
- design-reviewerSkill
- design-system-architectSkill
- design-understandSkill
- information-architectSkill
- interaction-designerSkill
- knowledge-graph-architectSkill
- mobile-ux-expertSkill
- motion-designerSkill
- performance-reviewerSkill
- product-designerSkill
- prompt-architectSkill
- reference-driven-designSkill
- responsive-checkSkill
- ux-reviewerSkill
- visual-qaSkill
The file
We split this skill into the rules it gives an agent
9 rules. About 0 are common, 4 are distinctive, and 5 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 41
Check typography scale, spacing, density, and hierarchy.
- Distinctive: line 42
Check whether color, shape, material, depth, and status styling use semantic meaning.
- Distinctive: line 43
Keep expressive treatment subordinate to content and primary action.
- Distinctive: line 44
Ensure repeated items scan cleanly.
- Very specific: line 103
Use design-system-architect when token or reusable state naming is needed.
- Very specific: line 104
Use reference-driven-design when the visual direction lacks traceable references.
- Very specific: line 105
Use accessibility-reviewer for contrast, focus, and target checks.
- Very specific: line 106
Use mobile-ux-expert when visual density breaks on narrow screens.
- Very specific: line 107
Use design-reviewer for final signoff.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.
Files
Visual Designer Skill
Role
Review visual hierarchy, typography, spacing, color meaning, and product polish.
Mission
Make the interface feel modern, legible, and product-specific while preserving rule and pattern intent.
When To Use
- A screen is structurally correct but visually unclear or generic.
- Hierarchy, spacing, contrast, density, or status styling needs review.
- A product surface needs polish without redesigning the workflow.
- Semantic token use needs visual validation.
When Not To Use
- Product direction or IA is unresolved.
- The task asks for a new design system or component library.
- The issue is primarily accessibility, motion, or performance.
Inputs
- Current screen or implementation.
- Product goal and selected patterns.
- Evidence-backed reference brief when visual direction or polish is requested.
- Existing tokens, theme values, and component styles.
- Accessibility constraints and viewport requirements.
Process
- Identify the primary content and action.
- Identify the content layer, functional layer, focal emphasis, and quiet supporting surfaces.
- Check typography scale, spacing, density, and hierarchy.
- Check whether color, shape, material, depth, and status styling use semantic meaning.
- Keep expressive treatment subordinate to content and primary action.
- Ensure repeated items scan cleanly.
- Preserve platform, mobile, and accessibility constraints.
- Hand off reference, token, accessibility, or final review concerns.
Output Format
## Visual Review
- Primary visual issue:
- Product impact:
- Recommended change:
- Evidence or reference:
## Hierarchy
- Primary:
- Secondary:
- Supporting:
## Surface Roles
- Content layer:
- Functional layer:
- Focal emphasis:
- Quiet surfaces:
## Token And Pattern Links
- Rule:
- Pattern:
## Handoff
- Next skill:
- Reason:Quality Checklist
- Primary action and content are visually dominant.
- Typography fits the surface.
- Spacing supports scanning.
- Color communicates meaning, not decoration alone.
- Expressive materials preserve content priority and platform behavior.
- Visual polish does not change product logic.
- The recommendation uses existing rules and patterns.
Related Rules
RULE-00001/PRD-001Daily Actions FirstRULE-00003/IA-001One Stable Home SurfaceRULE-00008/VIS-001Semantic Tokens OnlyRULE-00009/A11Y-00144x44 Touch TargetsRULE-00014/VIS-002Keep Expression Subordinate To Content
Related Patterns
PAT-00001/PAT-001Daily Home SurfacePAT-00004/PAT-004Progressive DetailPAT-00006/PAT-006Object Status List
Handoff To Other Skills
- Use
design-system-architectwhen token or reusable state naming is needed. - Use
reference-driven-designwhen the visual direction lacks traceable references. - Use
accessibility-reviewerfor contrast, focus, and target checks. - Use
mobile-ux-expertwhen visual density breaks on narrow screens. - Use
design-reviewerfor final signoff.
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.

