The Agent Skills Directory

[SAFE] (SAFE): The skill is primarily a static knowledge base consisting of markdown reference files. All code snippets provided in the documentation are for illustrative purposes and use placeholders for sensitive information like API keys.
[COMMAND_EXECUTION] (SAFE): The scripts/search-docs.py utility is a safe, read-only script designed to search the local documentation files. It uses standard Python libraries (argparse, pathlib) and does not use dangerous functions such as eval() or exec(), nor does it execute arbitrary system commands.
[EXTERNAL_DOWNLOADS] (SAFE): Documentation references official Anthropic SDKs and installation commands (e.g., pip install anthropic). These are for developer guidance and are not executed by the skill automatically.
[DATA_EXPOSURE] (SAFE): The skill does not access sensitive system files or environment variables. Credentials mentioned in guides are documented best practices (e.g., using environment variables) rather than hardcoded secrets.

anthropic-expert