The Agent Skills Directory

[SAFE]: The skill contains legitimate UI/UX guidelines and documentation. The provided code snippets for CSS transitions, Tailwind classes, and Framer Motion components follow industry best practices for design engineering.
[DYNAMIC_EXECUTION]: The skill includes a technique for suppressing transitions during theme switches by dynamically injecting a stylesheet. This is a common performance optimization for web applications and uses hardcoded CSS strings, posing no security risk.
Evidence: The DisableThemeTransitions component in animations.md uses document.createElement('style') to inject transition-reset rules.
[INDIRECT_PROMPT_INJECTION]: As the skill is designed to analyze user-provided source code to suggest UI improvements, it naturally possesses an ingestion surface for data. However, given its specific focus on stylistic review and lack of dangerous autonomous capabilities, this surface is considered a standard part of its functional design.
Ingestion points: The skill instructs the agent to review the project's component library, tokens, and density as mentioned in SKILL.md.
Boundary markers: Absent; the skill does not define specific delimiters to wrap or isolate the code content being analyzed.
Capability inventory: The skill includes recipes for dynamic style injection (animations.md) and instructs the agent to analyze the project's dependency tree (SKILL.md).
Sanitization: Absent; no explicit sanitization or validation of the analyzed source code is specified.

better-ui