What problem does it solve? Teams often jump into implementation before fully understanding a problem, leading to rework and misaligned requirements. This Skill provides a dedicated explore mode where the AI acts as a thinking partner—investigating the codebase, comparing options, and clarifying requirements—without writing any implementation code. ## Core Features & Use Cases - Open-ended exploration: Asks clarifying questions, challenges assumptions, and surfaces risks using ASCII diagrams to visualize architecture, state machines, and tradeoffs. - Codebase grounding: Reads files and maps existing architecture to ground discussions in the actual code rather than theory. - OpenSpec integration: Checks active changes via the openspec CLI, scaffolds new changes with openspec new change, and captures decisions into proposals, designs, specs, and tasks artifacts. - Use Case: Before adding real-time collaboration to your app, enter explore mode to map the collaboration spectrum (presence, cursors, CRDTs), investigate your current sync architecture, and capture the chosen approach as an OpenSpec change proposal. ## Quick Start Ask the AI to enter explore mode and think through whether SQLite or Postgres fits your CLI tool before creating a change proposal.
