Use when performing adversarial analysis of LLM interactions, designing attack taxonomies, understanding red team methodologies, or implementing quality-diversity approaches to vulnerability discovery. Provides the 10x10 risk category and attack style taxonomy.
This skill should be used when designing context management, implementing tiered fidelity, reducing token waste, applying Four Laws patterns, creating "NOT PASSED" sections, optimizing agent context, or debugging context-related issues. Provides SOTA patterns for context-efficient multi-agent systems achieving 60-80% token reduction.
This skill should be used when designing agent orchestration, implementing firewall architecture, creating phase-based workflows, adding severity batching, structuring agent hierarchies, or implementing SOTA multi-agent coordination patterns. Provides production-ready patterns for scalable agent systems.
This skill should be used when designing agent coordination, implementing context handoffs, reducing context overhead, creating multi-agent workflows, optimizing agent communication, implementing progressive disclosure, selecting architectural patterns (hierarchical vs swarm), or debugging agent context issues. Provides SOTA patterns for multi-agent systems achieving 78%+ context reduction while maintaining analysis quality.