What problem does it solve? Reporting bugs is tedious: users must translate their experience into structured, well-scoped GitHub issues that developers can act on. This Skill runs an interactive QA session where the user describes problems conversationally, and the agent clarifies, explores the codebase for domain context, and files durable GitHub issues automatically. ## Core Features & Use Cases - Conversational bug intake: Users describe problems in their own words with at most 2-3 short clarifying questions about expected behavior, reproduction steps, and consistency. - Background codebase exploration: An Explore subagent learns the project's domain language and intended behavior so issues read naturally without citing files or line numbers. - Smart issue scoping: Decides whether a report is a single issue or should be broken into multiple thin, parallelizable issues with honest blocking relationships, filed in dependency order via gh issue create. - Use Case: During a QA pass on a web app, a user says "the form validation is wrong and the redirect after submit is broken." The agent splits this into two independently fixable GitHub issues with reproduction steps and shares the URLs. ## Quick Start Start a QA session and describe the bug you encountered so the agent can file a GitHub issue for it.