style-direction
Skill8 starsChanged 7 months agoMITView on GitHub
Visual style direction recommendation with current style analysis plus the top 3 directions and implementation guidance. Use when the user asks for a style direction, a visual or design direction, or what style they should use.
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-scoreSkill
- design-tokensSkill
- flow-auditSkill
- layout-auditSkill
- refactor-planSkill
- theme-builderSkill
- type-auditSkill
The file
Files
/style-direction: Visual Style Recommendation
Get a visual style direction recommendation for your project.
Flow
- Analyze current visual style
- Identify product type and likely audience
- Compare against 10 viable style directions
- Recommend top 3 with rationale
- For each recommendation: characteristics, implementation checklist, risk factors, reference products
10 Style Directions
- Neo-Minimal - max whitespace, single accent, ultra-clean
- Soft Material - subtle shadows, rounded corners, layered
- Editorial - strong typography, generous whitespace, grid-based
- Glass/Depth - translucent layers, blur, depth cues
- Dark Luxury - dark surfaces, premium accents, bold
- Warm Organic - warm neutrals, rounded, hand-drawn
- Dense Functional - high density, compact, utility-focused
- Bold Expressive - strong colors, large type, animated
- Calm Tech - muted colors, gentle motion, mindful
- System Native - OS conventions, familiar, low-friction
Output
- Current style assessment
- Top 3 recommended directions with:
- Why it fits
- Key characteristics to implement
- Risk factors
- Durability estimate
- Reference products
- Implementation checklist
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.