Lamina edge cases
Derive distinct product-risk scenarios from operations, dependencies, authority, lifecycles, concurrency, destructive actions, and recovery without generating exhaustive or duplicate edge-case lists.From its SKILL.md
npx -y skills add aryaniyaps/lamina --skill lamina-edge-casesAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- runs commandsInstructs the agent to run 1 command, including `graph-tool.mjs derive`.
SKILL.md
1.1 KB, 175 tokens by cl100k_base, as published. Nobody here has run it
Distinct product risks
Use scenarios[] for observable behavior that differs from the primary path. One scenario represents one distinct risk; reuse its risk_key rather than multiplying equivalent cases across actors and surfaces.
Prioritize:
- Declared operation failures.
- Unmet dependencies.
- Forbidden authority or ownership.
- Invalid and stale transitions.
- Concurrent consequential mutations.
- Destructive confirmation and recovery.
- External failure that changes product behavior.
Every scenario declares given[], when.operation_ref, then[], covers[], metadata, and a unique risk_key. Acceptance must be externally observable. “Handle gracefully” is not acceptance.
Run graph-tool.mjs derive for mechanical suggestions, then add only missing distinct risks. Persona preferences do not become scenarios unless they reveal a structural, safety, or evidence-backed failure.