The Agent Skills Directory

[SAFE]: The skill methodology is based on measurement and baseline capture, ensuring that optimizations are justified and do not introduce arbitrary code or dependencies.
[SAFE]: It promotes security best practices by instructing the agent to define clear data boundaries and avoid caching secrets or sensitive user-specific information.
[SAFE]: The workflow incorporates mandatory user approval for subagent spawning and scope expansion, maintaining strict control over the agent's autonomy and resource consumption.

performance-optimization