The Agent Skills Directory

[SAFE]: The skill performs legitimate file operations within the project scope, specifically reading and writing task data to .claude/data/tasks/records.yaml and creating files in the docs/tasks/ directory. No access to sensitive system paths or credentials was detected.\n- [SAFE]: No network communication or external downloads are initiated by this skill. All task management logic and data persistence occur within the local environment.\n- [SAFE]: The instructions and reference materials are transparent and do not utilize obfuscation, remote code execution, or prompt injection techniques to bypass agent safety guidelines.

secondbrain-task