What problem does it solve? Designing a well-structured AI agent skill requires balancing persona design, capability prompts, memory architecture, and quality standards, which is difficult to do consistently by hand. This Skill guides the creation, editing, and quality analysis of agent skills so they meet a defined prompt-quality canon. ## Core Features & Use Cases - Conversational Agent Building: Discovers the agent's persona, mission, and capabilities through dialogue, then emits a complete skill directory with SKILL.md, templates, and scripts. - Three Agent Archetypes: Produces stateless, memory (persistent sanctum), or autonomous (PULSE-scheduled) agents based on natural discovery questions rather than upfront architecture choices. - Edit and Analyze Intents: Performs targeted edits that preserve an existing agent's design, or runs quality lenses over an agent to produce an actionable report. - Use Case: Ask to create a personal writing coach agent; the builder discovers it needs memory, emits a bootloader SKILL.md plus sanctum templates (PERSONA, CREED, BOND, MEMORY, CAPABILITIES), and scaffolds wake and init scripts. ## Quick Start Ask the agent builder to create a new agent by describing who it should be and what outcome it should deliver.
