Lamina research scoping
Headless Product Design skill for AI coding agents | Design how it works, verify what you ship.
npx -y skills add aryaniyaps/lamina --skill lamina-research-scopingAssembled 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
Evidence scoping — what grounding is needed (repo, walkthrough, user input) vs assumption. Not human study scope.
SKILL.md
1.0 KB, as published. Nobody here has run it
Evidence Scoping (agent-native)
Before design or verify, list what evidence exists and what must be captured.
| Evidence | Source |
|---|---|
| Domain rules | User input, business-context.md |
| Existing UI | Repo surfaces[].source, walkthrough pack |
| Actor behavior | Verify actor walks on live product |
| Metrics | User-provided only — never invented |
Label each design claim: verified, assumption, or to-verify.
Anti-patterns
- Exhaustive research scope — delaying contract without blocking gaps
- Invented analytics — fake A/B or usage data