What problem does it solve? When starting a new feature or change, developers often jump into implementation before fully understanding the problem space, existing architecture, or tradeoffs. This Skill provides a dedicated explore mode where the AI acts as a thinking partner—investigating the codebase, visualizing options with ASCII diagrams, and clarifying requirements—without writing any implementation code. ## Core Features & Use Cases - Codebase-grounded exploration: Reads files, maps existing architecture, finds integration points, and surfaces hidden complexity relevant to the discussion. - Visual thinking: Uses ASCII diagrams, comparison tables, and state machines to clarify problems, options, and tradeoffs. - OpenSpec integration: Checks active changes via openspec list --json, reads existing proposals/designs/specs, and offers to capture decisions into the right artifacts (proposal.md, design.md, tasks.md, specs). - Use Case: Before adding real-time collaboration to an app, enter explore mode to map the collaboration spectrum (presence, cursors, CRDTs), compare implementation complexity, and crystallize the approach into a change proposal. ## Quick Start Ask the AI to enter explore mode to think through your idea or investigate a problem in the codebase before creating an OpenSpec change proposal.
