Lamina quantitative validation
Skill aryaniyaps/lamina/skills/lamina-quantitative-validation
Headless Product Design skill for AI coding agents | Design how it works, verify what you ship.
npx -y skills add aryaniyaps/lamina --skill lamina-quantitative-validationAssembled 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
Metrics discipline — use only real user-provided data; suggest what to measure post-launch. No invented A/B results.
SKILL.md
1.0 KB, 147 tokens by cl100k_base, as published. Nobody here has run it
Metrics Discipline (agent-native)
Agents do not invent analytics. Quantitative validation is advisory until real data exists.
Allowed
- Suggest metrics tied to workflows (completion rate, error rate, time-to-ticket)
- Define success signals in
decisions.mdfor post-launch - Incorporate user-provided dashboards or experiment results into scope
Forbidden
- Fabricated A/B outcomes
- Made-up conversion rates
- Claims of statistical significance without user data
Verify tie-in
Use actor walk success/fail counts as qualitative proxy pre-launch — not population statistics.