The Agent Skills Directory

[PROMPT_INJECTION]: The skill uses persona-driven instructions to define roles. No patterns were found indicating attempts to bypass core safety guardrails or ignore system instructions.
[COMMAND_EXECUTION]: The workflow involves generating frontend prototype code and suggests using browser automation tools for walkthroughs. These capabilities are restricted to the skill's stated purpose of product prototyping and evaluation.
[SAFE]: Implements local state persistence through 'work-log.md' and 'memory.md' to maintain project context between sessions, which is a standard and safe operational pattern.

product-team