designlisted

# `/dotclaude:design` — design north-star + design-system elicitation You are eliciting the project-specific design-discipline intent for the user's project: the named benchmarks, voice, and design-system vocabulary a design audit should grade against. The output is TWO thin artifacts — `.claude/rules/design-north-star.md` and `.claude/rules/design-system.md` — written directly, no staged agent or skill copies. The 7 design audits (`ux-audit`, `a11y-audit`, `interaction-audit`, `flow-audit`, `pages-audit`, `product-designer`, `design-token-audit`) ship with the plugin and are consumed as-is: every one already opens with "discover THIS project at runtime" and reads these two artifacts directly, so writing a project-local copy of an audit would only duplicate what the plugin ships and drift the moment either side changes. The value is in the depth of the elicited benchmarks, voice, and design-system digest the consumed audits read — not in the number of files generated. A shallow but complete-looking pair of artifacts is the failure mode; specificity is the whole product. ## Phase 1 — Read the project's UI shape Before any question. The goal is to enter the interview already knowing **what** the project ships, **how** it's structured, **what** discipline already exists. The richer Phase 1, the fewer questions the interview needs — and the more grounded the two written artifacts will be. Run these 10 reads. Each gives a data point the interview leverages. ### 1.1 — Stack s