study-assistant-skills

Study tutor (main orchestrator) for any exam — 考研, 期末考试, certifications. Use whenever the user wants to systematically learn or prepare for an exam from study material. Chinese triggers: uploading a textbook/课件/讲义 with "开始学习" "带我系统过一遍" "复习第X章" "帮我复习"; "继续学习" "上次学到哪了"; "做成思维导图"; uploading/mentioning past exam papers (真题/历年试卷) to analyze or imitate question style; "出题考我" "练练手" "来套模拟卷" "复盘错题本"; submitting answers (incl. handwritten photos) for grading; "费曼检验" "检验我的掌握程度". Orchestrates: study archive → mind map (study-mindmap) → one-knowledge-point lecture generation and audited chapter-level lecture HTML (study-teach) → global question bank and quizzes (study-quiz) → Feynman checks (study-feynman); images via study-img. Do NOT use for: writing papers/literature reviews, extracting PDF tables or converting formats outside study, Word formatting, translation, exam-news lookup (国家线), thesis figures, or merely describing an image.

Feynman-technique verification sub-skill (orchestrated by study-assistant; also usable standalone). Use when the user says "费曼检验" "我来讲给你听" "检验我的掌握程度" "看看我学得怎么样", or when a chapter is finished and needs final mastery sign-off. The learner explains a point in their own words; Codex plays a sharp beginner, probes gaps, scores mastery 1-5, and writes mastery reports.

Image-reading sub-skill (orchestrated by study-assistant; also usable standalone). Use for ANY study material that must be visually inspected: scanned textbook pages, courseware figures/charts/diagrams, photographed exam papers, photos of handwritten answers or notes, and png/jpg/jpeg/gif/webp/bmp files. Supports OCR, teaching-grade figure descriptions, and verbatim handwritten-answer transcription.

Mind-map sub-skill (orchestrated by study-assistant; also usable standalone). Use whenever a chapter knowledge-point mind map needs to be generated or refreshed — the user says "思维导图" "知识图谱" "脑图", or any knowledge point's mastery/status changed. Renders knowledge.json into a zero-dependency offline-capable interactive HTML with collapse/expand, drag/zoom, search, and mastery coloring.

Quiz & assessment sub-skill (orchestrated by study-assistant; also usable standalone). Use when the learner uploads past papers/questions ("真题", 历年试卷, 样题), wants AI to search for school-style questions, asks to be tested ("出题" "考我" "测验" "模拟题" "来套模拟卷"), submits answers for grading, or asks to review mistakes. Maintains one course-level global question bank, prioritizes uploaded questions over web-sourced material, generates MathJax-capable interactive HTML quizzes, grades answers, updates mastery, and maintains the mistake book.

Lecture & explanation sub-skill (orchestrated by study-assistant; also usable standalone). Use when the learner wants a chapter/section/knowledge point taught ("开始讲解" "讲一下第三章" "生成讲义" "继续下一个知识点"), asks a follow-up question about studied content, or says they didn't understand. Generates exactly one high-quality knowledge-point lecture at a time as structured JSON plus HTML/Markdown, then merges all completed points into one audited chapter-level main HTML. Must preserve source formulas, figures/tables, and worked examples when they help understanding.