The Agent Skills Directory

[SAFE]: The skill is entirely instructional and operates by generating text prompts for the user to copy and paste into external tools. It does not perform any file writes, network requests, or command executions.
[DATA_EXPOSURE]: The skill accesses local project files such as brand-kit.md and about-me.md to gather brand context. These are non-sensitive application-level files and no data is exfiltrated.
[PROMPT_INJECTION]: The use of 'CRITICAL' in the markdown text is used for workflow prioritization (auto-starting the task) rather than attempting to bypass safety filters or override the agent's underlying system instructions.

youtube-thumbnail