The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and modify user-supplied UI code and design descriptions, creating a potential surface for indirect prompt injection if the processed data contains malicious instructions.
Ingestion points: The skill ingests user-provided code snippets and UI descriptions via triggers like 'fix the design', 'Tailwind styling', and 'visual hierarchy'.
Boundary markers: No specific boundary markers or instructions to isolate the agent from embedded commands in the user-provided content are defined.
Capability inventory: The skill is capable of generating and refactoring frontend code (HTML, CSS, Tailwind).
Sanitization: No explicit sanitization or filtering logic is present to validate the input data before processing.
[EXTERNAL_DOWNLOADS]: The skill includes external references to educational materials and documentation.
Evidence: Several links to books on Amazon and the official Refactoring UI website are provided in the 'Further Reading' section of SKILL.md.
Context: The Amazon links include affiliate marketing tags (tag=wondelai00-20) associated with the author. Amazon is a well-known service, and these references are consistent with the skill's educational purpose.

refactoring-ui