Lamina discoverability

Skill aryaniyaps/lamina/skills/lamina-discoverability

Headless Product Design skill for AI coding agents | Design how it works, verify what you ship.

Install

npx -y skills add aryaniyaps/lamina --skill lamina-discoverability

Assembled 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

Signifiers and affordances in screen contracts — actors must see what they can do. Use when actor walks report execution/evaluation gulfs.

SKILL.md

2.1 KB, as published. Nobody here has run it

Discoverability (agent-native)

Specify what actors can perceive and do on each screen — signifiers, primary actions, disabled reasons — so verify catches gulfs of execution and evaluation.

Contract encoding

Per surfaces[]:

primary_actions[] — visible, labeled
secondary_actions[] — deferred or progressive disclosure
disabled_when — guards linking to scenarios
feedback — what actor sees after each action (ties to feedback-and-status)

Diagnostic (verify)

Gulf	Symptom in actor walk	Fix in contract
Execution	Can't find how to act	Add signifier / promote primary action
Evaluation	Can't tell if action worked	Add feedback scenario + screen state

Design checklists

Primary workflow actions visible without hunt.
Constraints prevent wrong actions; don't rely on warnings alone.
Mapping: control position relates to effect when spatial layout matters.
Consistent labels for same operation across screens.
Actor self-blame in simulation → design failure finding.

Verify checks

Primary actor completes workflow without instructions document.
Walkthrough: mystery meat / hidden gestures flagged.

Anti-patterns

Invisible affordances (gestures with no signifier).
Hidden modes changing control meaning.
Identical unlabeled controls.
Assuming actors learn internal jargon.