2362094903-ops

study-assistant

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) → section lecture notes & Q&A (study-teach) → quizzes & exam-style analysis (study-quiz) → Feynman checks (study-feynman); images via study-img (native vision first, else user-configured API). Do NOT use for: writing papers/literature reviews, extracting PDF tables or converting formats, Word formatting, translation, exam-news lookup (国家线), thesis figures, or merely describing an image.

study-feynman

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 sign-off. The user explains a knowledge point in their own words; Claude plays a sharp beginner who probes for holes, scores mastery 1–5, and produces a chapter mastery report.

study-img

Image-reading sub-skill (orchestrated by study-assistant; also usable standalone). Use for ANY material that must be "seen" during study: scanned textbook pages, textbook figures/charts/diagrams, photographed exam papers, photos of handwritten answers or notes, and any png/jpg/jpeg/gif/webp/bmp file. Strategy: if the current model has native vision, just look (Read tool); otherwise call the vision-model API the user configured (OpenAI-compatible or Anthropic format), guiding configuration on first use.

Web & Frontend Listed

study-quiz

Quiz & assessment sub-skill (orchestrated by study-assistant; also usable standalone). Three mandatory scenarios: (1) the user uploads past exam papers ("真题", 历年试卷, 样题) — analyze the question style into exam-style.md; (2) the user has no papers but wants school-style questions — search the web for that school's papers/sample exams (user-provided papers always take precedence); (3) the user asks to be tested — "出题" "考我" "测验" "模拟题" "来套模拟卷" "复盘错题" — generate an interactive HTML quiz (single/multiple-choice, true-false, free-response; per-question instant answer & explanation), grade submitted answers, maintain the mistake book, update mastery.

study-teach

Lecture & explanation sub-skill (orchestrated by study-assistant; also usable standalone). Use when the learner wants a chapter/section taught ("开始讲解" "讲一下第三章" "生成讲义" "继续下一节"), asks a follow-up question about studied content, or says they didn't understand ("给我讲讲X" "没听懂，重讲一遍"). Default mode generates complete section-by-section lecture notes — Obsidian Markdown and/or interactive HTML with rendered math, one worked example per knowledge point; conversation is reserved for targeted Q&A and re-teaching.

study-mindmap

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 (regenerate to refresh colors). Renders knowledge.json into a zero-dependency, offline-capable interactive HTML: collapse/expand, drag & zoom, search, mastery color coding.