Turning Human Knowledge
into AI Skills
A practical guide for design architects
February 2026 · Prepared by Bob for Ako
Every team has unwritten expertise trapped in one person's head.
Heroes don't scale. AI can — if you structure the knowledge.
"The teams winning at AI aren't the ones with
the best models. They're the ones who've
packaged their knowledge best."
Modular instruction packages that teach Claude
how to handle specific tasks or domains.
Think of them as "onboarding docs for AI"
my-brand-skill/
├── SKILL.md # Core instructions (required)
├── REFERENCE.md # Supplemental info (optional)
├── resources/
│ ├── helper.py # Executable scripts
│ └── examples.json # Reference data
Minimum: one folder + one SKILL.md file
---
name: brand-guidelines
description: >
Apply company brand guidelines for marketing
copy, presentations, and customer-facing content.
dependencies:
- python3
---
# Brand Guidelines Skill
## Voice & Tone
- Professional but approachable
- Active voice preferred
## Color Usage
- Primary: #1A73E8 (trust blue)
- Error: #DE3E25 (destructive only)
- Never use raw hex — use semantic tokens
## ✅ Good
"We've updated your dashboard with new insights."
## ❌ Bad
"The UI has been refactored with enhanced data viz."
| Tier | What Claude Sees | When |
|---|---|---|
| Metadata | Name + description | Always — every conversation |
| Full Instructions | Entire SKILL.md body | Only when relevant |
| Resources | Scripts, data, refs | Only when executing |
10 skills loaded → only 1 fully expanded → token-efficient
Everyone is solving the same problem — different shapes, same DNA.
| Claude Skills | Custom GPTs | Cursor Rules | AGENTS.md (GitHub Copilot) |
Figma MCP | |
|---|---|---|---|---|---|
| Format | SKILL.md + folder | Web UI config | .mdc files | Plain markdown | Auto-generated |
| Activation | Auto by context | User selects | Glob / AI-decided | Always loaded | MCP protocol |
| Progressive | ✅ 3-tier | ❌ | ⚠️ Glob | ❌ | ✅ |
| Executable | ✅ Scripts | ❌ | ❌ | ❌ | ❌ |
| Composable | ✅ | ❌ | ✅ | ✅ | ✅ |
Composable = can mix & combine multiple skills/rules · AGENTS.md = GitHub Copilot's instruction file format
📄 Consistent document output? → Claude Skills (scripts for PDF, Excel)
💬 Customer-facing assistant? → Custom GPTs (easy sharing, web UI)
🖥️ Coding conventions? → Cursor Rules (auto-attach by file type)
🎨 Design system compliance? → Figma MCP + token docs
🏢 Team process capture? → AGENTS.md (simplest approach)
They're not mutually exclusive — combine as needed
AI has zero tacit knowledge. Everything must be explicit.
| Knowledge Type | Example | Encoding |
|---|---|---|
| Rules | "Error text = red-600" | Explicit constraints |
| Patterns | "Cards have 16px padding" | Templates + examples |
| Preferences | "Prefer shorter headlines" | Ranked examples ✅/❌ |
| Judgment | "Layout feels too dense" | Decision trees |
| Process | "PRs need design review" | Step-by-step workflows |
AI learns almost as much from what NOT to do.
## Common Mistakes (DO NOT)
- ❌ Using primitive color tokens directly (e.g., `red-6`)
- ❌ Hardcoding pixel values instead of spacing tokens
- ❌ Creating new variants when an existing one works
- ❌ Skipping loading/error states in components
The "new hire" test: If a smart new hire could follow
your instructions and produce 90%+ acceptable output,
your instructions are good enough for AI.
{
"red-6": {
"value": "#DE3E25",
"type": "color"
}
}
No idea that red-6 is a primitive,
not for direct use
{
"color-feedback-error": {
"value": "#DE3E25",
"description": "Error states:
alerts, destructive buttons",
"usage": ["Alert.error",
"Button.destructive"],
"pairedWith": [
"color-feedback-errorText"]
}
}
AI-readability starts at Layer 2 · Guardrails live at Layer 4
# Component: Button
## Variants
- `primary`: Main actions (1 per section)
- `secondary`: Supporting actions
- `destructive`: Delete, irreversible actions
## Token Usage
| Property | Token |
|------------- |-------------------------------|
| Background | `color-interactive-primary` |
| Text | `color-text-onColor` |
| Padding | `spacing-component-btn-pad` |
| Border radius| `radius-component-button` |
| Min height | `sizing-touch-target-min` |
## Rules
- NEVER use raw hex values
- ALWAYS pair with appropriate text color token
- Maximum 1 primary button per section
- Destructive buttons require confirmation
Connects your Figma designs directly to your IDE's AI agent
📦 Sends: Components, styles, variables, Code Connect
🎯 Enables: AI uses your components, not generic ones
⚡ Killer feature: Auto-generates design system rules from your codebase
1. Be explicit, not implicit
2. Structure beats prose (tables & lists > paragraphs)
3. Include examples — good AND bad
4. State what NOT to do
5. Use progressive disclosure
6. Test with edge cases
7. Version and iterate
"Make it look professional" means nothing.
"16px body, 48px headers, neutral-700" means everything.
5 extraction questions:
🚀 Trigger.dev — Cursor rules for task writing
Explicit SDK version + full examples → dramatically improved consistency
🎨 Figma MCP — Design system context for AI agents
AI reuses existing components instead of generating generic code
🏗️ Builder.io — Context-aware design-to-code
AI learns from your actual repo and uses your components
🤖 OpenClaw / AGENTS.md — Agent self-knowledge
Plain markdown in project root — simple but effective
🎯 Romina Kavcic — AI-readable design tokens
Added descriptions + usage arrays → Claude picked the right tokens automatically
description fieldsusage & pairedWith🔄 Phase 5: Test & Iterate — ongoing, review monthly
If you only do ONE thing, create this file:
# Design System Quick Reference for AI
## Tokens (Use These, Not Raw Values)
- Primary action: `color-interactive-primary` (#1A73E8)
- Error: `color-feedback-error` (#DE3E25)
- Body text: `color-text-primary` (#1F2937)
- Spacing: sm (8px) · md (16px) · lg (24px)
- Border radius: `radius-default` (8px)
## Component Rules
- Use `
90% of the value · 10% of the effort
Add description to your top 10 most-used tokens:
That's it. You've just made your design system AI-readable.
All approaches converge on four pillars:
🔗 Emerging standard: agentskills.io
1️⃣ Heroes don't scale — package the knowledge
2️⃣ Be explicit — AI has zero tacit understanding
3️⃣ Anti-patterns are as valuable as patterns
4️⃣ Semantic tokens with descriptions = AI-readable design
5️⃣ Figma MCP is the highest-leverage integration
6️⃣ Start with one file — iterate from there
📘 Anthropic: How to Create Skills for Claude
📗 Figma: Design Systems and AI — Why MCP Servers Are the Unlock
📙 Design Tokens That AI Can Actually Read — Romina Kavcic
📕 Trigger.dev: How to Write Great Cursor Rules
📓 Agent Skills Specification — Emerging cross-platform standard
Thank you! 🙏
Research & presentation by Bob · February 2026