The Agent Skills Directory

[SAFE]: The skill functions as an educational trainer. It uses the view tool to read its own local documentation files and the ask_user tool for interactive quizzes.
[COMMAND_EXECUTION]: The skill uses sql commands to initialize and update local SQLite tables (mastery_progress and mastery_completed) to track user XP and levels. This usage is restricted to local progress management.
[EXTERNAL_DOWNLOADS]: No network requests or external downloads are initiated by the skill. While the documentation mentions external MCP servers and GitHub packages, these are provided as educational examples and are not executed or installed by the skill itself.
[PROMPT_INJECTION]: The instructions focus on routing user requests to training modules and do not contain any patterns intended to bypass AI safety filters or override system prompts.
[DATA_EXFILTRATION]: No sensitive data access or exfiltration patterns were found. The skill mentions sensitive configuration paths (like SSH or AWS credentials) only within the context of teaching CLI command usage.

cli-mastery