What problem does it solve? Answering questions about a large codebase requires reading many files and tracing connections across components, which is slow and error-prone when done manually. This Skill orchestrates parallel research agents to investigate a codebase question and produces a structured, evidence-backed research document. ## Core Features & Use Cases - Parallel sub-agent research: Spawns 2-4 concurrent Explore and general-purpose agents to search files, trace code paths, and analyze architecture, each returning file:line references. - Scope clarification: Asks targeted questions about depth, focus, and output format before researching ambiguous queries. - Structured research documents: Generates a Markdown research artifact with YAML frontmatter, code references, architecture insights, and historical context stored under context/changes/<change-id>/research.md. - Use Case: Ask "how does authentication work in this repo" and receive a comprehensive document with component breakdowns, code references, GitHub permalinks, and open questions. ## Quick Start Invoke the 10x-research skill and ask a research question such as how the payment processing flow works across the codebase.
