What problem does it solve? Designing well-structured AI agent skills 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 conversational discovery to build outcome-driven agents with clear personas, focused capabilities, and optional persistent memory. ## Core Features & Use Cases - Agent Building: Six-phase conversational process covering intent discovery, capability strategy, requirements gathering, drafting, building, and summary, producing stateless, memory, or autonomous agent types. - Quality Analysis: Analyzes existing agents for over-specification, persona-capability misalignment, and structural issues, generating an interactive HTML report with grades, opportunity themes, and fix prompts. - Guided Editing: Targeted edit workflow that assesses cascade impact across SKILL.md, sanctum templates, and capability files while preserving agent identity. - Use Case: Ask the builder to create a personal coding coach agent; it determines the agent needs memory, generates a bootloader SKILL.md plus sanctum templates (PERSONA, CREED, BOND, MEMORY, CAPABILITIES), an init script, and a First Breath onboarding conversation. ## Quick Start Ask the agent builder to create a new agent by describing who the agent is and what it should accomplish, for example: build an agent that acts as a creative writing coach with persistent memory.
