Declare what the system should be before writing code. Use when building new features, redesigning feature areas, or making significant changes that need a declaration of intent. Guides the declaration chain from findings through plans.
Wear the QA hat — think about quality the way a 15-year senior QA thinks. Use when building features, reviewing work, validating output, or when anything feels "done" but hasn't been proven to work. Prevents the gap between "it runs" and "it works."
Evidence-first research with mandatory citations and source evaluation. Use when gathering information for decisions, comparing approaches, investigating unknowns, or any task requiring verified evidence from multiple sources. Invoke at the START of research, not when writing up results.
Check and invoke available skills before starting work. Invoke at the start of any task to ensure relevant skills are loaded.
Effective Mermaid diagrams. Use when creating markdown documents with human audiences.
Guides effective documentation creation. Activates relevant guidance for north-star, gestalt, reference, research, design, plan, flow, findings, concepts, or process documents. Prevents cascading harm from wrong information.
Audit, sanitize, and package ~/.claude/ configuration into a distributable repository with versioned releases. Use when updating the public agentic-config repo, syncing local changes, creating releases, or auditing for PII. Handles cross-platform install scripts and semantic versioning.
Adversarial security testing — think and attack like a criminal to expose vulnerabilities before real criminals do. Use when testing code, live services, or infrastructure for security weaknesses. Spawns parallel attack subagents targeting different surfaces.