The skills
Pick a layer, run a skill.
Nine AI skills — one for each of the seven layers of product design, plus a diagnostic and a framework primer. Tool-agnostic; install once, run in your AI tool of choice.
- Layer 1
/layers-observed-behaviourObserved behaviour
Plan and synthesise user research at the observed-behaviour layer — produces job stories with confidence ratings.
- Layer 2
/layers-domainThe domain
Map domain concepts, terminology conflicts, and bounded contexts — produces a noun harvest for the conceptual model.
- Layer 3
/layers-user-needsUser needs
Elicit and prioritise user needs as job stories — produces opportunities ready for product strategy.
- Layer 4
/layers-product-strategyProduct & service strategy
Connect user opportunities to business outcomes and solution bets — produces a strategy tree and prioritised experiments.
- Layer 5
/layers-conceptual-modelConceptual model
Define the product’s objects, relationships, states, and vocabulary independently of any interface — the most load-bearing layer.
- Layer 6
/layers-interaction-flowInteraction structure & flow
Map interaction structure and flow — produces breadboard notation with edge cases, failure paths, and open decisions.
- Layer 7
/layers-surfaceSurface
Audit the surface against lower-layer decisions — produces a decision inventory across vocabulary, hierarchy, feedback, and accessibility.
Install
Install the skills
One command installs all nine skills. They become available in whichever AI tool you use.
Install in Claude Code, Cursor, Codex & more
npx skills add jamiemill/layers-skills
Install once with the skills package, then run any /layers-* skill
in your AI tool.