The Agent Skills Directory

[SAFE]: The skill's primary function is to serve as an educational and integration resource for the Anthropic Claude API. It promotes secure coding practices through explicit 'Critical Rules' and production checklists.
[COMMAND_EXECUTION]: Includes a helper script (scripts/check-versions.sh) that executes standard npm commands to check for package updates. This is a common utility for maintaining developer dependencies.
[REMOTE_CODE_EXECUTION]: A developer template (templates/tool-use-advanced.ts) contains an example of a mathematical tool that uses the eval() function. This finding is classified as safe because the code is marked with a prominent security warning advising developers to use safe alternatives in production.

claude-api