The Agent Skills Directory

[PROMPT_INJECTION]: The skill uses strong directives (e.g., "strictly BANNED", "CRITICAL") to establish a specific design persona and enforce aesthetic constraints. These are standard instructional guardrails for persona consistency and do not attempt to bypass safety filters, disregard system instructions, or extract system prompts.
[COMMAND_EXECUTION]: The instructions include a mandatory dependency verification step where the agent is told to check package.json and suggest npm install commands if required libraries are missing. This is a standard and safe developer workflow recommendation.
[EXTERNAL_DOWNLOADS]: The skill references legitimate, well-known industry libraries and services such as Framer Motion, GSAP, Three.js, and standard font providers. It also uses a trusted placeholder service (picsum.photos) for images, which is standard practice in web prototyping.
[DATA_EXFILTRATION]: No patterns related to sensitive file access, credential harvesting, or unauthorized network operations were detected. The skill operates entirely within the context of frontend code generation and design logic.

design-taste-frontend