Lamina task analysis
Operations actors perform — map tasks to workflows and navigation. Use when workflows[] or IA don't match actor goals.From its SKILL.md
npx -y skills add aryaniyaps/lamina --skill lamina-task-analysisAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
SKILL.md
2.0 KB, 344 tokens by cl100k_base, as published. Nobody here has run it
Task Analysis (agent-native)
Decompose actor goals into operations — verbs on domain entities — that become workflows[] steps and navigation structure.
Procedure
- From primary actor goals (
personas.json), list operations: "download ticket", "assign venue". - Group operations into workflows by outcome, not by backend module.
- Rank deal-breaker operations — if blocked, actor abandons product.
- Map working-set (daily) operations to shortest nav path in screen specs.
- Rare operations → progressive disclosure (
platform-posture).
Contract encoding
workflows[].steps= ordered operations; userequires+dependencies[]for prerequisitestask-analysisprose optional inreport.mdfor complex domains- Navigation labels = operation vocabulary, not org chart
Design checklists
- Nav structured by tasks, not implementation modules.
- Index/wayfinding separated from work area on sovereign apps.
- Key paths ≤ few steps for working-set tasks.
- Edge tasks reachable but not prominent.
- Each operation links to permission in
actors.
Verify checks
- Actor walk: deal-breaker operations completable on live product.
- Measure steps vs contract workflow length.
Anti-patterns
- Org-chart or file-system navigation.
- Deep hierarchy for daily tasks.
- Operations in contract that no actor has permission to perform.