For humans and AI

Skills to design beyond the surface.

Whether you're directing your AI or working alongside it, Layers walks you both through all seven layers of product design — so the decisions underneath the screen actually get made.

/plugin marketplace add jamiemill/layers-skills
/plugin install layers@layers-skills

Run inside Claude Code.

npx skills add jamiemill/layers-skills

Universal install via the skills package.

How it works ↓

The framework

Seven layers, three zones

Most product design decisions live at one of seven layers. Most AI design tools generate at the top. Layers gives you a way to navigate down, find which layer the real problem lives at, and run the skill that thinks with you there.

Surface Interaction structure & flow Conceptual model Product & service strategy User needs The domain Observed behaviour

Not sure where to start? Run /layers:orient — it audits all seven layers and tells you which one is your bottleneck.

In practice

What you'd actually say

These are the kinds of prompts the Layers skills are built to handle. Drop one into your AI tool — the skill takes it from there.

Start broad

When you don't yet know which layer the problem lives at.

I've been asked to redesign onboarding — use the Layers skills to help me think it through properly.
Help me figure out why my team can't agree on how to design this feature. Use Layers to surface what we're actually disagreeing about.
I'm stuck on this design and I don't know what's wrong. Use Layers to diagnose where the real problem is.
Audit my mockups with the Layers skills — what decisions am I assuming, and which ones haven't actually been made?

Or go straight to a layer

When you know which decisions you need to make.

I've got 12 user interviews. Run /layers:user-needs and turn them into prioritised job stories.
Help me model the objects, relationships, and vocabulary for this scheduling tool with /layers:conceptual-model.
Run /layers:interaction-flow for this checkout — surface the edge cases and empty states I'm missing.
My team can't agree on terminology across product, design, and engineering. Use /layers:domain to map the conflicts.

What you get back

Decisions, not screens.

Skills capture design decisions as markdown and mermaid — job stories, strategy trees, object maps, breadboards, decision inventories. Plain text, readable by humans, by AI, and by every other tool you use.

Need decisions to live in Linear, Notion, Figma, or GitHub instead? Connect an MCP and the skill writes there directly.

Example artifact Output from /layers:product-strategy

Strategy tree

graph TD
    O["Outcome: increase weekly active use"]
    O --> Op1["Opp: users abandon onboarding"]
    O --> Op2["Opp: first task takes too long"]
    Op1 --> B1["Bet: show value before signup"]
    Op2 --> B2["Bet: pre-filled defaults"]

Prioritised bet: show value before signup.

Risk: cold visitors may not engage enough to surface real value.
Validation: cohort A/B on signup conversion + qualitative session review.
Linked needs: #user-needs/onboarding-momentum

## Strategy tree

```mermaid
graph TD
    O["Outcome: increase weekly active use"]
    O --> Op1["Opp: users abandon onboarding"]
    O --> Op2["Opp: first task takes too long"]
    Op1 --> B1["Bet: show value before signup"]
    Op2 --> B2["Bet: pre-filled defaults"]
```

**Prioritised bet:** show value before signup.

- *Risk:* cold visitors may not engage enough to surface real value.
- *Validation:* cohort A/B on signup conversion + qualitative session review.
- *Linked needs:* `#user-needs/onboarding-momentum`

The skills

Pick a layer, run a skill

Each skill guides your AI tool through one layer of design — methods, quality bars, common failure modes. Tool-agnostic; install once, run anywhere.

Start here /layers:orient

Orient

Diagnostic audit across all seven layers — find the bottleneck and where to focus.

Meta /layers:intro

Intro

Framework orientation — auto-loaded as context by every other skill.

All skills come from the Layers plugin. Install · GitHub

About

The Layers framework, made available to AI.

Layers is a model of product design as seven layers across three zones. The framework is by Jamie Mill; the skills make it executable inside the AI tools you already use.

More about the framework →