菜单
Lamina Problem Router — product design at the intersection of UX, product rules, and systems thinking.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use only when explicitly invoked as lamina-design. Turn an incomplete product idea or brownfield change into a minimum sufficient product behavior graph: actors, entities, operations, workflows, rules, dependencies, decisions, persona perspectives, and distinct risks; then generate an implementation-ready contract.
Use only when explicitly invoked as lamina-init. Turn an incomplete product idea into usable business context and evidence-grounded personas, asking only high-leverage questions and labeling provisional assumptions for later product-graph design.
Product design workflows — domain contracts, implement brief, verify loop. Load via Read or Skill tool when /lamina-* workflows need it.
Use only when explicitly invoked as lamina. Route product design for developers building with AI — design, verify, or direct capability answers.
Use only when explicitly invoked as lamina-verify. Verify a live or brownfield product against its product graph: critical promises, reachable workflows, authority, invariants, state integrity, recovery, accessibility, and contract drift; emit evidence-backed fixes before merge.
Business context UX guidance. Use when bootstrapping Lamina for a project; answering business questions UX work needs; updating context after a pivot or scope change.
| name | lamina-core |
| description | Lamina Problem Router — product design at the intersection of UX, product rules, and systems thinking. |
Load one capability skill per problem.
| Command | Use when |
|---|---|
/lamina | Auto-route or single-topic answer |
/lamina-init | Bootstrap domain charter |
/lamina-design | Design how the product works → ready_to_build |
/lamina-verify | Post-build or brownfield verification |
Guardrail: .lamina/ writes only; never app source. See guardrails.md.
| Problem signal | Skill |
|---|---|
| Entities, relationships, purpose | system-structure |
| Feedback, delays, oscillation | feedback-loops |
| Fixes keep failing, structural traps | system-traps |
| Where to intervene (rules vs UI) | leverage-points |
| Impossible states, business rules | invariants |
| Feature reachability, unmet prerequisites, degraded modes | dependencies — first-class |
| Domain boundaries, hide complexity | modularity-boundaries |
| What users see when (stale data) | consistency-guarantees |
| Double-submit, concurrent edits | idempotency-concurrency |
| Name trade-offs before mechanisms | tradeoffs |
| Multi-actor views stay consistent | multi-view-integrity |
| Evolving rules safely | evolutionary-rules |
| Notifications, downstream updates | side-effects |
| Dates, deadlines, expiry, recurrence, timezones | time-semantics |
| Problem signal | Skill |
|---|---|
| Bootstrap context | business-context |
| Inclusive design | accessibility |
| Copy, labels, errors | content-design |
| Prioritize, resolve conflicts | decision-making |
| Affordances, signifiers | discoverability |
| Domain-empty screens | empty-states |
| Violation recovery UX | error-handling |
| Permission/conflict scenarios | edge-cases |
| Unreachable or silently broken prerequisites | dependencies |
| Async feedback, status | feedback-and-status |
| User journeys over state | flow-design |
| Forms under rules | forms |
| Local date/time input | time-semantics |
| Entity organization | information-architecture |
| Wayfinding | navigation |
| First-run paths | onboarding |
| UI reflects domain truth | product-behavior |
| Operations actors perform | task-analysis |
| Actors, roles, permissions | user-modeling |
Human labs, interviews, and workshop ceremony are reframed as contract + live-product simulation.
| Problem signal | Skill |
|---|---|
| Design→build→verify loop | design-process |
| Scope the design target | problem-framing |
| Map ask → workflows | feature-discovery |
| What evidence vs assumption | research-scoping |
| Plan verify actor walks | research-planning |
| Merge walk results | research-synthesis |
| Report verify findings | research-communication |
| Actor-walk scripts | interview-design |
| Walkthrough evidence | interview-documentation |
| Repo + live UI grounding | field-research |
| Simulated usability (verify) | usability-evaluation |
| Real metrics only | quantitative-validation |
| Conflicting actor goals | stakeholder-alignment |
| User-cited references | competitive-analysis |
| Workflow priority | feature-prioritization |
| Group permissions / shared state | persuasion-and-groups |
| Parallel expert lenses | heuristic-review |
| Complexity budget / disclosure | platform-posture, progressive-disclosure |
| Payment / sensitive action honesty | trust |
| Testable acceptance criteria | requirements-definition |
