The Agent Skills Directory

[SAFE]: The skill performs benign motivational tasks and maintains its state locally within the markdown file. No sensitive files are accessed, and no external network operations are performed.
[INDIRECT_PROMPT_INJECTION]: The skill has a minimal attack surface as it reads and writes to its own SKILL.md file to track used quotes. The risk is considered negligible because the agent generates the content written to the file and uses explicit sentinel markers () to delimit the data block.
[DYNAMIC_EXECUTION]: The instructions require the agent to read from and write to the local file to maintain a list of previously used quotes. This file manipulation is restricted to specific blocks and is a functional requirement for the skill's state-management, not a vector for code execution.

motivate