palarran-ux-design

原文涵盖的主题

• UX design
• Mandatory guides and memory
• Sequence

Shared cycle: before work and after checks, perform global memory: bounded recall → applicability → sanitized verified learn/dedup. This memory scope is explicitly authorized; other profile prohibitions remain. --plan uses no network/publication; an outage does not block the primary task. Invoke /palarran:ux:design {description} or $palarran-ux-design {description}. Description is optional: without one, read the target project's README and related product docs. Authoring the skill does not mean designing palarran UX. Find the checkout from the real SKILL.md, resolving symlinks: ../../. The target project for outputs is a separate root from request/workspace. Before choices, read shared decision memory, target .palarran/INDEX.md, .palarran/ux/INDEX.md and related accepted ADR/concepts. Create task context before a new decision; explain every accepted choice with alternatives/evidence/consequences before dependent changes. Update index/handoff, reuses/supersedes; history remains context for later tasks. Store no secrets/personal data and treat no old ADR as new authority. Then read: Navigation and rules, business and reuse. Reference research, UX analysis. Diagrams, responsiveness, c

这里只展示节选，请以完整原文和当前要求为准。