agentsclimarketplace

Lamina user modeling

Skill aryaniyaps/lamina/skills/lamina-user-modeling

Headless Product Design skill for AI coding agents | Design how it works, verify what you ship.

Install
npx -y skills add aryaniyaps/lamina --skill lamina-user-modeling

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

What its author says it does

Copied from the file, not written here

Create evidence-grounded product actors and provisional personas, distinguish roles from preferences, and conduct bounded persona perspective reviews without treating simulations as user research.

SKILL.md

1.2 KB, as published. Nobody here has run it

User modeling

Write .lamina/personas.json with Contract v2. Each persona contains role, goals, constraints, evidence references, confidence, and whether it is primary.

Use research, explicit user input, analytics, support evidence, or brownfield behavior as evidence. Keep inferred personas low or medium confidence. Do not invent demographics or preferences that do not change product behavior.

Actors in run.json define authority, ownership, and operations. Personas add perspective and constraints; they do not replace the authorization model. When the mapping is known, record typed actor_refs on the persona so isolated reviews can receive only the relevant graph slice.

For perspective review, select at most three personas with materially different goals, authority, vulnerability, or context. Require graph citations and classify findings. Preserve simulated preference as persona_hypothesis; promote only structural, safety, contradiction, or evidence-backed findings.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.