Separate and clarify one or more fragmented, implicit, or hard-to-word thoughts, expose only supported relationships, then respond or pass the result forward. Use only when the user invokes distill or asks for clarification before answering; never activate it silently.
Stress-test a proposal, assumption, decision, design, or plan through a relentless multi-turn grill that follows its decision tree one question and recommendation at a time. Use only when the user invokes grill or asks for a demanding challenge; never begin silently.
Explain the Think It Through deck, clarify any card or deck concept, or recommend normal conversation, one card, or a combo for the user's current situation or free-form goal. Use only when the user invokes help or explicitly asks how to use or continue with Think It Through. Never play a recommended card or suggest…
Explain a concept, feature, ticket, or implementation in plain language to build the user's mental model — grounded in verified code and sources, with a concrete running example, current-vs-target framing, and an explicit invitation to correct assumptions. Use whenever the user wants to UNDERSTAND how something in a…
Distill fragments into structured thought files — classify into existing files or synthesize new ones. Scans fragment pool for related insights, proposes actions, and executes. Accepts optional topic hint.
Adjust thinking-tree recording preferences via natural language. Updates /.thinking-tree/.preferences.md which guides how the clarifier captures and routes insights.
Clean the thinking-tree fragment pool — filter by preferences, deduplicate, and remove outdated entries. Uses AskUserQuestion for option-based interaction so user can review without typing.