What problem does it solve? Designing well-structured AI agents is hard: agents often end up over-specified with mechanical procedures, lack clear identity, or have no coherent memory architecture. This Skill guides users through a conversational discovery process to create outcome-driven agents with clear personas, focused capabilities, and optional persistent memory. ## Core Features & Use Cases - Agent Building: Six-phase conversational discovery process that produces stateless, memory, or autonomous agents with persona, capabilities, and sanctum templates. - Quality Analysis: Analyzes existing agents for over-specification, persona-capability misalignment, and structural issues, generating an interactive HTML report with grades, opportunities, and fix prompts. - Guided Editing: Surgical edit workflow that preserves agent identity while modifying capabilities, persona, memory structure, or PULSE autonomous behavior. - Use Case: A user says "create an agent that reviews my code like a senior engineer" and the builder walks them through discovery, determines it needs memory, and outputs a complete agent skill with bootloader SKILL.md, sanctum templates, and an init script. ## Quick Start Ask the agent builder to create a new agent by describing who the agent is and what outcome it should achieve, or provide a path to an existing agent and request analyze, edit, or rebuild.
