design-toolkit
Skill1 starsChanged 8 months agoMITView on GitHub
Complete design toolkit - 7 specialized skills, 3 templates, and a workflow router for visual design, frontend design, theming, and design-system work.
In this repository5 other files it gives its agents.
- coordination-toolkitSkill
- developer-toolkitSkill
- document-toolkitSkill
- knowledge-toolkitSkill
- pm-toolkitSkill
The file
Files
Design Toolkit
This toolkit restores the workflow-level entry point that previously lived in claude-skills/design. Use it when the user needs design intent routing rather than jumping straight to one leaf skill.
Routing Guide
| User Intent | Primary Skills | Templates |
| Generative visuals, procedural art, animated assets | algorithmic-art, slack-gif-creator | design-brief |
| Posters, brand-aligned visuals, canvas compositions | canvas-design, brand-guidelines | design-brief, style-guide |
| UI systems, themed interfaces, React artifacts | frontend-design, web-artifacts-builder, theme-factory | design-brief, design-review-checklist |
| Design standards, consistency, review, accessibility | Use this router with style-guide and design-review-checklist | style-guide, design-review-checklist |
Quick Actions
- "Create generative art" -> algorithmic-art
- "Design a poster" -> canvas-design
- "Apply brand constraints" -> brand-guidelines
- "Build a themed UI" -> frontend-design + theme-factory
- "Create a React artifact" -> web-artifacts-builder
- "Review design quality" -> design-review-checklist
- "Define tokens and standards" -> style-guide
Templates
| Template | Use Case |
| design-brief | Scope a visual, UI, or motion design project |
| style-guide | Define tokens, typography, spacing, and component rules |
| design-review-checklist | Review hierarchy, consistency, accessibility, and performance |
Related Skills
- cli-demo-gif for terminal demos rendered as GIFs
- asciinema-recorder for terminal capture workflows
design/web-asset-generatorremains available as a submodule-backed asset utility
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.