Lamina vs product-design skill (https://lamina.dev/learn/compare/lamina-vs-product-design-skill): The mblode product-design skill (in agent-skills) teaches interaction judgment during build: shape, spec, review, and harden modes, reachable UI states, action naming, ESLint rules, and routing visual work to ui-design. Lamina is headless product design with machine-readable run.yaml contracts, permission matrices across actors, and /lamina-verify persona walks on the deployed build. Both care about states; the difference is UI reachable states vs domain state machines (hold lifecycle, submit-for-review gates, refund statuses). mblode is strong judgment layer during implementation. Lamina is durable contract plus post-build verification. Compose when you want mblode interaction choices inside a behavior frame Lamina defines. Lamina (lamina.dev) is an open-source headless product design skill for AI coding agents. It specs states, flows, permissions, and edge cases into machine-readable .lamina/ contracts, then verifies live builds with /lamina-verify. It is not a UI tool, headless CMS, app builder, or uselamina.ai. Compare product-design (mblode) to Lamina when you need durable behavior contracts in your repo, not just generated UI or ephemeral planning. Full guide: https://lamina.dev/learn/compare/lamina-vs-product-design-skill.

Lamina vs product-design skill

mblode product-design is an agent skill for interaction judgment: reachable UI states, action scope, resilience. Lamina produces run.yaml contracts and /lamina-verify on the live build.

Curated by Aryan Iyappan · Updated 2026-07-13

Both say product design. mblode teaches judgment during build. Lamina writes contracts and verifies after.

You are in the right place if

You installed product-design skill expecting the same output as Lamina.
You need permission matrices across guest vs partner actors.
mblode review mode caught UI issues but domain gates still fail in QA.
You read the pillar comparison row and want the full nuance.

Context

mblode product-design is the closest named behavioral skill to Lamina in the ecosystem. Fair comparison requires precision: mblode optimizes interaction decisions and lintable UI patterns; Lamina optimizes committed contracts and live verification across roles. Many teams could use both with clear boundaries.

Common situations

Concrete cases from AI-shipping workflows. Each shows what the alternative handles and where a behavior contract helps.

mblode shape mode on checkout actions

Situation: product-design skill recommended confirm vs pay labeling and loading button scope. Pay still enabled when hold expired.
What product-design (mblode) does: Interaction judgment: right control, reachable UI states, resilience patterns.
What Lamina adds: Domain rule: pay illegal when hold status is expired. verify walks guest persona.
Takeaway: UI state reachability is not hold lifecycle enforcement.

Single dialog interaction choice

Situation: Pick between modal vs inline confirm for delete. No multi-actor flow.
What product-design (mblode) does: mblode shape/spec modes for interaction choice.
What Lamina adds: Skip unless delete triggers domain side effects with gates.
Takeaway: Pure interaction choice: mblode may be enough.

Guest vs partner on same property model

Situation: Both roles see property UI. Partner may edit; guest may only book. mblode hardened components; role matrix missing.
What product-design (mblode) does: Component-level resilience and action scope.
What Lamina adds: Actor permissions in run.yaml and implement.md server checks.
Takeaway: Multi-actor domain rules are Lamina-shaped work.

Comparison

Lamina vs mblode product-design skill
Dimension	product-design (mblode)	Lamina
Primary job	Interaction judgment before/during UI build	Behavior contracts + verify loop
Layer in stack	Product judgment skill in agent-skills bundle	Headless product design skill
Primary output	Judgment docs, ESLint rules, mode-based guidance	run.yaml + implement.md
Writes app source?	Routes to ui-design for visual build	No
Behavior spec (states, flows, permissions)	Reachable UI states, action naming, interaction patterns	Domain state machines, permissions
Durable in-repo artifact	Skill references and lint config	.lamina/ per feature run
Post-build verification	Review and harden modes, ESLint	/lamina-verify persona walks
Repo and stack fit	mblode agent-skills bundle	Standalone Apache-2.0 skill at lamina.dev
Best when	Choosing right control for an interaction	Multi-actor flows with gates
When you don't need Lamina	Single-surface interaction tweak	mblode judgment covers scope
Compose with Lamina?	Shape interaction during UI implementation	Contract first; mblode during UI polish

Workflow

Lamina vs product-design skill: recommended workflow
Step	product-design (mblode)	Lamina
1	Optional: mblode shape on interaction	/lamina-design for behavior scope
2	mblode spec/review during UI build	implement.md for domain rules
3	ESLint harden pass	/lamina-verify on staging

Worked example

Better domain modelling. mblode can push richer UI states. Lamina pushed CancellationTemplate, HoldStatus, and booking enums in HavenStay when domain modelling was contracted. verify confirmed illegal transitions were blocked in the live app.

HavenStay demo walkthrough

Frequently asked questions

Both mention states. What's different?

mblode covers reachable UI states (empty, error, loading). Lamina covers domain rules (hold expiry, submit gates, refund statuses).

mblode has ESLint rules. Does Lamina?

Lamina focuses on contracts and verify, not lint plugins. Different enforcement point.

Which should I install?

mblode for interaction judgment during build. Lamina when you need committed contracts and persona verification across roles.

Comparisons map stack layers, repo artifacts, and HavenStay demo examples. Updated when major tools change positioning.

Install in one command.

A headless product-design skill for your AI coding agent. Then run the design → implement → verify loop on your next feature.

Apache-2.0 · open source. Star on GitHub if Lamina saves you a loop.

npx skills install aryaniyaps/lamina

Works with your coding agent

Cursor
Claude Code
Codex
Gemini
Pi
and more