The Agent Skills Directory

[SAFE]: The skill consists solely of Markdown documentation and instructions. It defines a decision matrix for task delegation and structured output contracts for subagents like cavecrew-investigator and cavecrew-builder.- [SAFE]: No executable scripts, binary files, or remote dependencies are included or referenced. The skill does not perform any network requests or file system operations directly.- [SAFE]: The instructions include safety-conscious guidelines, such as subagents reverting to plain English for security warnings and confirmation prompts.

cavecrew