design-system
Design System Skill v3.0
Manage DESIGN.md files that frontend agents read to generate consistent UI.
Actions
/design-system init
Create a new DESIGN.md from the template:
- Copy
docs/templates/DESIGN.md.templateto project root asDESIGN.md - Ask user for: project name, visual theme, primary color
- Fill in template variables
- Output:
DESIGN.mdready for customization
/design-system init
# Creates DESIGN.md with 9 sections from template
/design-system load
Load DESIGN.md into current context for frontend work:
- Read
DESIGN.mdfrom project root (or specified path) - Extract design tokens as structured data
- Inject into agent context as reference
- Used automatically by orchestrator Step 3 (PLAN) for frontend tasks
/design-system load
# Loads DESIGN.md tokens into context
/design-system validate
Check generated components against DESIGN.md:
- Read DESIGN.md
- Scan specified files for design token usage
- Report violations: hardcoded colors, wrong spacing, missing states
- Output: compliance report with fix suggestions
/design-system validate src/components/
# Checks all components against design system
Integration Points
| Skill/Agent | How It Uses DESIGN.md |
|---|---|
| Orchestrator Step 3 | If task is frontend and DESIGN.md exists, include as context |
| ralph-frontend | Loads DESIGN.md before generating any component |
| /create-task-batch | Phase 1 asks about design system for frontend tasks |
| /gates Stage 5 | BROWSER validation checks design compliance (future) |
Validation Checklist
The 9 required sections in every DESIGN.md:
- Visual Theme
- Color Palette (with CSS custom property tokens)
- Typography (with font stack and scale)
- Components (buttons, inputs, cards minimum)
- Layout (grid, spacing scale, breakpoints)
- Depth and Elevation
- Do's and Don'ts
- Responsive Behavior
- Agent Prompt Guide
Template
Source: docs/templates/DESIGN.md.template
Inspired by VoltAgent/awesome-design-md — 55+ real-world DESIGN.md files.
More from alfredolopez80/multi-agent-ralph-loop
stop-slop
A skill for removing AI-generated writing patterns ('slop') from prose. Eliminates telltale signs of AI writing like filler phrases, excessive hedging, overly formal language, and mechanical sentence structures. Use when: writing content that should sound human and natural, editing AI-generated drafts, cleaning up prose for publication, or any content that needs to sound authentic rather than AI-generated. Triggers: 'stop-slop', 'remove AI tells', 'clean up prose', 'make it sound human', 'edit AI writing'.
10gemini-cli
|
2minimax
Custom skill for minimax
1clarify
Intensive requirement clarification using structured AskUserQuestion workflow. Gathers MUST_HAVE (blocking) and NICE_TO_HAVE (optional) information before implementation. Use when: (1) starting new feature implementation, (2) requirements are ambiguous, (3) multiple approaches possible, (4) before writing any code. Triggers: /clarify, 'clarify requirements', 'ask questions', 'gather requirements'.
1security
Security audit with Codex + MiniMax second opinion. Integrates ralph-security agent (6 quality pillars, OWASP A01-A10). Uses LSP for code navigation during analysis. Use when: (1) /security is invoked, (2) task relates to security functionality.
1adr
Architecture Decision Records management. Actions: create (new ADR), list (show all), search (find by keyword). Use when: (1) making architecture decisions, (2) choosing between technologies, (3) documenting trade-offs. Triggers: /adr, 'architecture decision', 'decision record', 'document decision'.
1