A low-frequency strategy coach that helps decide what matters most now, what to pause, and what evidence should guide the next decision. It is intended for prioritisation and direction-setting rather than detailed coding or teaching.
A Chinese-language personal coaching guide for learning programming, AI agents, writing, languages, exams, research, or career skills through real projects and tasks. It tracks progress and teaches one useful action at a time.
Scaffold a new knowledge engine workspace OR link to an existing shared knowledge base. Use when starting a new knowledge base or connecting a project to an existing one.
Sharpen a vague idea, a literature gap, or a stalled project into a GOOD research question — consequential, specific, falsifiable, feasible — BEFORE committing to a technical route. Produces a structured Question Card, then optionally hands off to /kw-explore to form the technical route. Triggers: "is this a good…
Single entry for the knowledge engine. Detects state and offers choices — fetch papers by id/DOI/title, absorb all new papers (L1→L2), run L3 synthesis. Use when the user says "process the knowledge base", "/kw", "fetch this paper", or drops new papers.
Turn any complex topic into a 24-hour active-learning sprint with 80/20 concept mapping, prerequisite compression, active recall, hands-on exercises, teach-back prompts, and a final artifact.
Active recall layer. After giving a substantive answer, ask one compact multiple-choice question (4-5 options) mined from that answer, then grade it and explain. Use whenever the user asks to be quizzed or tested or wants to retain material — quiz me, test me, pop quiz, test my knowledge, check my understanding, drill…