What problem does it solve? Defining a reusable custom agent requires translating an ad-hoc conversation style into a structured .agent.md file with the right persona, tool restrictions, and scope. This Skill guides that process so the resulting agent is well-defined and reusable. ## Core Features & Use Cases - Conversation-Based Extraction: Reviews the current conversation to generalize a specialized role, tool preferences, and domain scope into an agent definition. - Guided Clarification: Asks targeted questions about the agent's job, when it should be chosen over the default agent, and which tools it should use or avoid. - Iterative Refinement: Drafts the .agent.md file, identifies ambiguous sections, and refines them with the user before finalizing. - Use Case: After spending a session constraining an assistant to only review Python security issues, use this Skill to capture that behavior as a reusable security-reviewer agent. ## Quick Start Ask the assistant to create a custom agent based on how you have been working in this conversation, then answer its clarifying questions to finalize the .agent.md file.