Lamina usability evaluation
Headless Product Design skill for AI coding agents | Design how it works, verify what you ship.
npx -y skills add aryaniyaps/lamina --skill lamina-usability-evaluationAssembled 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
Actor evaluation — verify-phase simulated user walks on live product. Replaces recruit-N usability labs.
SKILL.md
1.2 KB, as published. Nobody here has run it
Actor Evaluation (agent-native)
Usability = simulated actors completing workflows on the built product during /lamina-verify.
Method
- Load personas +
run.jsonworkflows - Spawn parallel actor-walk subagents (persona-panel)
- Each attempts happy path + edge probes
- Record blockers: cannot find affordance, wrong feedback, dead end
- Merge into
findings[]with severity
Requires status: ready_to_build or post-build deployment — not wireframe review.
Anti-patterns
- Lab recruitment — N users in a room
- Pre-build usability — judging flows without runnable product
- Heuristic-only — checklist without actor attempts