What problem does it solve? When you repeatedly steer an AI assistant toward the same specialized behavior—restricting tools, adopting a persona, or focusing on specific file types—this Skill captures that pattern as a reusable custom agent file instead of re-explaining it every session. ## Core Features & Use Cases - Conversation-Based Extraction: Reviews the current conversation to generalize specialized roles, 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 parts, and iterates with you until finalized, then suggests example prompts and related customizations. - Use Case: After spending a session making the AI act as a strict security reviewer that only reads code and never edits files, use this Skill to save that behavior as a reusable security-reviewer agent. ## Quick Start Ask the assistant to create a custom agent from how you have been working in this conversation, describing the job it should do and the tools it should use.
