The Agent Skills Directory

[SAFE]: The skill provides purely instructional content focused on UI/UX principles such as typography, color intensification, and spatial drama. It does not include any executable code or system-level commands.
[INDIRECT_PROMPT_INJECTION]: The skill ingests design context from the codebase or user input to perform its analysis. While it lacks explicit sanitization for this input, the risk is negligible as it only generates design suggestions and does not possess capabilities (such as network access or file writes) that could be exploited by malicious data in the context. The inclusion of an 'AI Slop Trap' check acts as a logical guardrail for output quality.
[METADATA_POISONING]: The metadata fields are descriptive and consistent with the skill's stated purpose, with no attempts to mislead the agent or the platform environment.

bolder