The Agent Skills Directory

[SAFE]: No security issues were detected. The skill includes a SessionStart hook that executes a local shell command (yq) to read task scaling thresholds from a configuration file (.claude/config.yaml). This operation is static, uses a hardcoded file path, and is used solely for initializing the skill's state with user-defined parameters.
[SAFE]: The skill's primary function is to provide classification logic for an agent to evaluate task complexity. This logic is handled internally by the agent's reasoning processes and does not involve risky data processing or network communication.

task-scaler