aryaniyaps/lamina-evaluation
Judge product usability and evidence quality. Use when running Persona-based walkthroughs on a built product, planning an expert heuristic review, defining evidence-backed success metrics, or checking quantitative claims without inventing measurements. Use lamina-research to plan or synthesize evidence collection and lamina-ux to design interaction behavior.
npx skills add https://github.com/aryaniyaps/lamina --skill lamina-evaluation
method materially changes the answer; do not preload the directory.
Using lamina-evaluation: <topic path(s)> so theselected evaluation lens is auditable.
| Evaluation signal | Read | Adds |
|---|---|---|
| Need actors to attempt workflows and edge probes on a built product | Actor Evaluation | Persona-based walkthrough method and reproducible blockers |
| Need specialists to inspect a contract or live product through explicit lenses | Expert Lens Review | parallel lens coverage tied to evidence and contract refs |
| Need success metrics, analytics interpretation, or experiment claims | Metrics Discipline | measurement boundaries and anti-fabrication rules |
Use the smallest sufficient reference set. Actor evaluation requires a runnable
product; use expert review before build or when a lens-specific inspection is
requested. Pair either with metrics discipline only when real measurements or a
measurement plan are in scope.
Take aryaniyaps/lamina-evaluation from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.