What problem does it solve? Teams struggle to identify genuine UI inconsistencies without false positives, and design feedback often lacks the evidence needed for another engineer or agent to act on it. This Skill audits a product surface against its governing design system, proves each finding with contract, runtime, and correction evidence, and produces self-contained implementation plans. ## Core Features & Use Cases - Evidence-based UI audit: Traces rendered paths through components, tokens, and variants, then keeps only findings backed by a binding design contract, a proven runtime relationship, and a deterministic correction. - Read-only safety: Never modifies product source, installs dependencies, or commits changes; all output is written under design-plans/. - Self-contained implementation plans: Generates one plan per selected change using a structured template covering evidence chain, reuse of existing tokens and components, validation steps, and stop conditions. - Use Case: Ask it to review your app's settings page for design-system drift; it reports up to three verified findings with confidence levels, then writes a handoff plan another agent can execute without any prior context. ## Quick Start Use the improve-ui skill to audit the primary product surface, identify supported UI problems, and recommend what to improve first without modifying anything.
