The Agent Skills Directory

[NO_CODE] (SAFE): The skill consists entirely of Markdown files providing structural guidelines and templates for documentation. No executable code (.py, .js, .sh) is included or invoked by the skill itself.
[DATA_EXPOSURE] (SAFE): Example code blocks use safe placeholders like 'your-api-key-here' and provide warnings to the user to keep keys secret, following security best practices for documentation.
[EXTERNAL_DOWNLOADS] (SAFE): References to external links (e.g., nodejs.org) and package installations (e.g., npm install) are provided as examples for the end-user to follow in their own environment, not as actions for the agent to perform.
[PROMPT_INJECTION] (SAFE): No patterns of instruction override, role-play jailbreaks, or system prompt extraction were found in the skill metadata or body.

tutorial-docs