home / skills / phrazzld / claude-config / design-catalog

design-catalog skill

/skills/design-catalog

This skill generates a catalog of 5-8 design proposals by coordinating Kimi and Claude to explore options before implementation.

npx playbooks add skill phrazzld/claude-config --skill design-catalog

Review the files below or copy the command above to add this skill to your agents.

Files (1)
SKILL.md
2.9 KB
---
name: design-catalog
description: |
  DESIGN-CATALOG
effort: high
---

---
description: Generate visual design proposal catalog with 5-8 options
argument-hint: "[route-or-url]"
---

# DESIGN-CATALOG

Generate a catalog of 5-8 design proposals before implementing anything.

## MANDATORY: Kimi Delegation

**All proposal generation MUST be delegated to Kimi K2.5 via MCP.**

Kimi excels at frontend/visual work. Claude orchestrates, Kimi implements:

```javascript
// Generate proposals in parallel (4.5x faster than sequential)
mcp__kimi__spawn_agents_parallel({
  agents: [
    { prompt: "Generate proposal 1: [DNA code]. Output: .design-catalog/proposals/01-[name]/", thinking: true },
    { prompt: "Generate proposal 2: [DNA code]. Output: .design-catalog/proposals/02-[name]/", thinking: true },
    // ... 5-8 total proposals
  ]
})
```

**Workflow:**
1. Research direction → Gemini (web grounding)
2. Generate proposals → Kimi (parallel agents)
3. Validate & review → Claude (quality gates, expert panel)

## Why Catalogs

Design is visual and iterative. Showing options before implementing:
- Prevents commitment to first idea
- Surfaces unexpected directions
- Lets user make informed choices

## Process

### 1. Load Design Skills

```
Skill("frontend-design")      # Philosophy
Skill("aesthetic-system")     # Strategic direction
Skill("ui-skills")            # Implementation constraints
```

### 2. Analyze Current State

If `$1` provided (route or URL):
- Screenshot the target via Chrome MCP
- Analyze existing design DNA (typography, colors, layout, motion)

If no argument:
- Ask what to design

### 3. Research via Gemini

```bash
gemini "Analyze this [product type] for distinctive design directions.
Research 2025 trends. Anti-convergence: avoid Inter, Space Grotesk,
purple gradients, Tailwind default blue-500."
```

### 4. Generate 5-8 Proposals

For EACH proposal:
1. Build working HTML/React preview
2. Validate against ui-skills constraints
3. Run `/rams` — Must score ≥70/100
4. Only passing proposals enter catalog

**DNA variety rule**: No two proposals share >2 axes.

### 5. Present Catalog

```bash
mkdir -p .design-catalog && cd .design-catalog
python -m http.server 8888 &
```

Open in browser, screenshot, present:

```
Design Catalog Ready

[N] proposals passed validation. Live: http://localhost:8888

1. [Name] - [soul] - DNA: [code] - RAMS: [score]/100
2. [Name] - [soul] - DNA: [code] - RAMS: [score]/100
...

Browse, compare, tell me which 2-3 resonate.
```

### 6. Iterate

User selects favorites → generate hybrids → re-validate.

## Anti-Convergence Checklist

Verify NO proposal uses:
- Inter, Roboto, Space Grotesk, Satoshi as primary fonts
- Purple gradients on white backgrounds
- Tailwind default blue-500 (#3B82F6)
- Centered max-w-4xl container everywhere
- No animations at all

## Output

Catalog ready for user selection. Next: User picks direction → `/design-theme`.

Overview

This skill generates a visual design proposal catalog of 5–8 distinct options before any implementation begins. It orchestrates research, parallel proposal generation, and validation so you can compare curated directions and pick favorites. All visual proposal generation is delegated to a specialist visual agent (Kimi K2.5) to maximize quality and speed.

How this skill works

If a route or URL is provided, the skill captures the current screen and extracts the design DNA (typography, color, layout, motion). It runs web research to define directional constraints, then spawns parallel visual agents to produce 5–8 working HTML/React previews. Each proposal is validated against UI constraints and a RAMS quality score; only proposals scoring ≥70/100 are included in the catalog.

When to use it

  • Before starting implementation on a new or redesigned interface to explore options.
  • When stakeholders want a side-by-side comparison of distinct visual directions.
  • To avoid locking into the first idea and surface unexpected creative paths.
  • When you need quick, vetted HTML/React previews for user testing or stakeholder review.
  • When you want an evidence-backed shortlist before committing design resources.

Best practices

  • Provide a target route or URL so the skill can ground proposals in the existing product.
  • Accept only proposals that pass automated quality checks (RAMS ≥70) to keep the catalog practical.
  • Enforce DNA variety: avoid proposals that share more than two design axes to maximize contrast.
  • Use the catalog as a conversation tool—pick 2–3 favorites, then request hybrids and iterations.
  • Apply the anti-convergence checklist to maintain originality and avoid common defaults.

Example use cases

  • Product team preparing a redesign wants five distinct visual directions to present to executives.
  • A startup wants quick, implementation-ready previews to test with early users before building.
  • Design lead needs to avoid team bias toward a single aesthetic and solicit broader feedback.
  • Agency wants to validate visual concepts against accessibility and implementation constraints.
  • Developer handoff: deliver vetted HTML/React previews that already satisfy UI rules.

FAQ

Do proposals include working code?

Yes. Each proposal is delivered as a working HTML/React preview validated against implementation constraints.

How many proposals will be produced?

The skill produces 5–8 proposals and includes only those that pass validation and quality scoring.