AI Config

Clarify goals, scope, and requirements to produce an agreed direction. Use when idea is vague, multiple interpretations exist, scope is undefined, or stakeholders need alignment before technical work begins

Restructure code without changing behavior, backed by tests or characterization checks. Use when code needs better clarity, less duplication, or safer future changes without altering outputs

Evaluate technical options with evidence and choose an approach. Use when requirements are fuzzy, multiple technical approaches exist, or change affects architecture, API, data, or security

Break a chosen approach into a detailed implementation blueprint with bite-sized tasks, exact paths, and verification steps. Use when approach is chosen and you need a plan before coding

Execute an approved implementation blueprint step by step with verification and checkpoints. Use when a blueprint exists and you are about to start implementation

Create reusable skills that teach AI agents techniques, patterns, or reference material. Use when a proven approach should be captured for reuse across projects

Design specialized subagents with focused prompts, scoped tools, and clear triggers. Use when a recurring task, domain-specific work, or pipeline step needs its own agent