What problem does it solve? When facing a vague idea, a messy problem, or an unclear requirement, jumping straight into implementation often leads to rework. This Skill provides a structured thinking partner that helps you explore the problem space, investigate the actual codebase, compare options, and surface risks before committing to a plan. ## Core Features & Use Cases - Exploration stance, not a script: Acts as a curious thinking partner that asks emergent questions, opens multiple threads, and follows the conversation wherever it goes, without forcing a fixed workflow. - Codebase-grounded investigation: Reads project context files (DESCRIPTION.md, ARCHITECTURE.md, ROADMAP.md, RESEARCH.md) and searches the actual code to ground discussions in reality rather than theory. - Visual thinking: Uses ASCII diagrams, comparison tables, state machines, and architecture sketches to clarify complex ideas. - Persistent research capture: Optionally saves exploration summaries and session notes to a RESEARCH.md file so context survives across sessions and feeds into later planning. - Use Case: You are considering adding real-time collaboration to your app. Enter explore mode, discuss the spectrum from presence indicators to CRDTs, visualize tradeoffs, and capture the decision before running a planning command. ## Quick Start Ask the AI to enter explore mode with a topic, for example: run /aif-explore with the topic "should we use Postgres or SQLite for this CLI tool" to think through the decision together.
