mblode product-design is an agent skill for interaction judgment: reachable UI states, action scope, resilience. Lamina publishes validated GraphVersions and runs /lamina-verify on the live build.
Curated by Aryan Iyappan · Updated 2026-07-27
Both say product design. mblode teaches judgment during build. Lamina writes contracts and verifies after.
You are in the right place if
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.
Concrete cases from AI-shipping workflows. Each shows what the alternative handles and where validated graph knowledge and verification evidence help.
| Dimension | product-design (mblode) | Lamina |
|---|---|---|
| Primary job | Interaction judgment before/during UI build | validated graph knowledge + verify loop |
| Layer in stack | Product judgment skill in agent-skills bundle | Transactional product graph + agent workflow |
| Primary output | Judgment docs, ESLint rules, mode-based guidance | Validated GraphVersion plus query projections |
| 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 | Validated GraphVersion plus query projections |
| Post-build verification | Review and harden modes, ESLint | Independent Persona Missions with runtime evidence |
| Repo and stack fit | mblode agent-skills bundle | CLI plus portable skills in any repo and stack |
| 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 |
| Step | product-design (mblode) | Lamina |
|---|---|---|
| 1 | Optional: mblode shape on interaction | /lamina-design for behavior scope |
| 2 | mblode spec/review during UI build | GraphVersion projection for domain rules |
| 3 | ESLint harden pass | /lamina-verify on staging |
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.
mblode covers reachable UI states (empty, error, loading). Lamina covers domain rules (hold expiry, submit gates, refund statuses).
Lamina focuses on contracts and verify, not lint plugins. Different enforcement point.
mblode for interaction judgment during build. Lamina when you need committed contracts and Persona Missions with runtime evidence across roles.
Comparisons map stack layers, durable outputs, and provenance-marked legacy examples. Updated when major tools change positioning.
Install Lamina with your agent.
Copy the repository-matched prompt. Your agent installs the standalone CLI, adds every Lamina skill for your active agent, configures supported passive rules, checks the setup, and tells you when to start a fresh session with /lamina-init.
Skills work across coding agents. Passive setup currently supports Codex, Claude Code, and Cursor.
Cursor
Claude Code
Codex
Gemini
PiRun these in your project, then start a fresh agent session. On Windows, use the PowerShell installer in the copied agent prompt.
curl -fsSL https://github.com/aryaniyaps/lamina/releases/latest/download/install.sh | shnpx skills add aryaniyaps/lamina --skill '*' -a <active-agent> -ylamina setup --agent <codex|claude-code|cursor>lamina doctor --json