Lamina onboarding
Headless Product Design skill for AI coding agents | Design how it works, verify what you ship.
npx -y skills add aryaniyaps/lamina --skill lamina-onboardingAssembled 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
First-run and learnability — primary path without training, progressive power features. Use when new actors can't complete first workflow in verify.
SKILL.md
2.0 KB, as published. Nobody here has run it
Onboarding (agent-native)
Onboarding = primary actor completes first valuable workflow without documentation — verified by actor walk, not tutorial copy alone.
Contract encoding
- First-run workflow flagged in
workflows[](e.g.onboarding: true) empty_states+surfaces[]for first dashboard visit- Power features in
secondary_actions/ progressive disclosure notes - Optional
scenarios[]for skipped onboarding — actor still reaches goal
Frameworks
- Working set: optimize discoverability for daily operations after day one.
- Command modalities: pedagogic (visible labels) → immediate (shortcuts) — spec accelerators in
implement.md, not required for pass. - Idioms over metaphors: consistent patterns across screens — reference in
decisions.md.
Design checklists
- First productive action obvious on empty state (
empty-states). - No mandatory feature tour blocking primary workflow.
- Help/docs are fallback — interface teaches via signifiers.
- Novice path ⊆ expert path (experts aren't forced through wizards).
- Onboarding workflow has full scenario coverage.
Verify checks
- Fresh-actor subagent (low
technical_literacypersona if defined) completes first workflow. - No dead ends before first value delivered.
Anti-patterns
- Multi-step modal tour before any action.
- Expert-only shortcuts with no discovery path.
- Metaphor-bound IA that breaks at scale.