The Agent Skills Directory

[SAFE] (SAFE): No security issues detected. The skill is purely instructional, providing configuration examples for the Anthropic API's 'thinking' feature.
[EXTERNAL_DOWNLOADS] (SAFE): The code snippets reference official, trusted packages (anthropic for Python and @anthropic-ai/sdk for Node.js).
[COMMAND_EXECUTION] (SAFE): While the skill's metadata lists 'Bash' as an allowed tool, the skill content itself does not contain or execute any malicious shell commands. It merely defines the capabilities the agent is permitted to use.

extended-thinking