shadcn-usage — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited shadcn-usage (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Use this skill for dashboard UI and design-system work.
Read DESIGN.md before changing interface behavior, visual hierarchy, product language, or layout. Keep UI decisions aligned with the existing shadcn/Tailwind style instead of inventing a parallel component system.
The dashboard should feel like a professional market-monitoring console:
Use existing shadcn primitives and local UI components before adding new abstractions. Keep Client Components focused on interaction and rendering; keep provider and credential logic on the server.
Do not reintroduce removed portfolio UI unless the specification changes.
Use user-facing language that is professional and product-like. Avoid comments or UI copy that sound like an agent speaking privately to the developer.
Generated analysis must remain informational. Use labels such as "AI brief", "notable movement", "source", "last updated", and "demo quota" honestly.
For any new UI surface, define:
Use Playwright coverage for meaningful viewport or interaction changes.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.