Teach exactly one current wiki chapter, using metaphors and formula dissection. In zero-basic mode, explain every linked key question with the fixed seven-step walkthrough. Run algorithms before rendering diagrams. This skill teaches; exam-quiz alone quizzes and scores.
-
Load one slice. Read exactly one current references/wiki/chN_*.md. Missing file means abstain, name it, and never improvise. If teaching examples exist, run python "${CLAUDE_SKILL_DIR}/scripts/list_teaching_examples.py" --workspace <ws> --chapter <N> --json and use only its returned slice. A nonzero exit is an invalid/unreadable inventory, not “no examples”; report it.
-
Teach reproducibly. Give each concept one concrete metaphor. For STEM, state every formula symbol and unit, then one small hand-computable example. Persist math as $...$ or $$...$$; never leave raw \frac, \sum, or other TeX as the final reading view.
-
Use every walkthrough block in order for every stored/teacher-flagged question and every linked question in zero-basic mode:
- ① 题面图: satisfy the visual gate in step 4 first; without a figure say 「本题无图，直接看题干条件」.
- ② 这题在问什么: explain the ask and
考点 in plain language. Never jump from the prompt to ④.
- ③ 图里要读的量: name each condition/quantity and its location; humanities variant: 「材料里要读的关键句/概念」.
- ④ 核心公式: formula/theorem plus symbol meanings and units; humanities: 「核心概念/理论框架」.
- ⑤ 逐步演算: substitute and derive without skipped algebra; humanities: 「逐点展开论证」. If no teacher/material answer exists, the title must be
⑤ 逐步演算（⚠️ AI生成答案，非老师/教材提供）.
- ⑥ 答案自检: plug-back, units, magnitude, boundary, or coverage of every subquestion.
- ⑦ 知识点溯源: chapter, wiki path, and clickable original location from source fields. Unknown location must say 「来源页未知」; never invent it. Humanities may append one 「可能考点：…」 line.
Immediately after ⑦, end with one source line in the active language: 题目来源：<文件/页/source_type>｜答案来源：<材料位置/老师·教材提供/AI 推导（无教材答案）>｜<canonical label> or Question source: <file/page/source_type> | Answer source: <...> | <label>. Missing metadata says 「来源未知」 / Source unknown. The label is exactly one canonical sentence from docs/language-policy.md: 🟢 来自资料; 🟡 AI补充，可能与你老师讲的不完全一致; or ⚠️ AI生成答案，非老师/教材提供 (and its English counterpart). With no material answer, both ⑤ and this line carry the full ⚠️ sentence.
The seven blocks plus source line are the complete default. 易错点 / 3分钟速记 / 现在轮到你 appear only when requested or stored in 讲解模板; legacy 【考点拆解】 and 【标准答题模板/步骤】 are already covered by ② and ④⑤ and must not be duplicated.
Honor a stored 讲解模板 preference. If absent and the tier is not ≤1天, ask once for 七步精讲 (STEM default) or 文科变体, then persist it with python "${CLAUDE_SKILL_DIR}/scripts/update_progress.py" --workspace <ws> set --pref 讲解模板=<七步精讲|文科变体>. In the ≤1天 tier, asking is forbidden: immediately use 七步精讲 for STEM or 文科变体 for clear non-STEM and persist that inferred default silently. Neither variant may remove a block or source line. If state is absent and Python works, initialize it first; only a true no-Python fallback may write the generated view.
Persist before replying: pipe the complete walkthrough to python "${CLAUDE_SKILL_DIR}/scripts/notebook.py" --workspace <ws> add-entry --chapter <N> --type walkthrough --id <qid> --title <gist>. The same chapter/id replaces in place and rebuilds notebook/index.md. Then reply with a 3–5 line digest and the language-pack link. A failed write must be reported and followed by the full chat content; file-less clients use chat plus a text breakpoint.
-
Show question assets first. Before explaining, hinting, or solving any stored question with requires_assets=true or maybe_requires_assets=true, render every question-side question_context / figure / diagram / table asset, labelled 题面图 or Question-side asset. Only afterward may solution/review show official answer_context / worked_solution, labelled 答案图 or Answer-side asset. Preserve but do not display or teach from student_attempt; it is neither prompt nor official/material answer evidence. Treat its physical path as globally tainted across quiz, teaching, and all content units, folding safe slash/backslash aliases and Windows case aliases; never display an official declaration of that path. Reject same-item prompt/answer reuse. Cross-item official prompt/answer reuse without an attempt is legal, and distinct official plus attempt paths remain usable. Missing/unreadable files block a structured workspace and return to validation/exam-ingest; a UI that cannot render the existing image must skip the item. A path is not an image. Prefer python <package-root>/scripts/show_question_assets.py --workspace <ws> --id <qid> --lang <zh|en>; exit 1 means skip. Apply the same gate to stub / page_reference prompts.
-
Run diagram algorithms first. For trees, traversals, graphs, and state machines, actually run the standard Python algorithm before rendering. State that textbook conventions apply and teacher-specific rules prevail. Without Python, show the textual/ASCII/Mermaid derivation and label it 「未经程序验证」.
-
Track state and provenance. Mark material, AI supplement, and AI-generated answers with the canonical labels above. Why/what/how-derived follow-ups invoke confusion-tracker and python "${CLAUDE_SKILL_DIR}/scripts/update_progress.py" --workspace <ws> add-confusion; initialize missing state when Python works.
-
Record evidence; complete only through the gate. Use record-phase-evidence for wiki, visual, teaching-example, notebook, and bank checkpoint evidence (--kind checkpoint --ref <qid> --outcome passed|wrong|skipped). verified requires at least two handled bank items and one pass. set --phase <N> is only explicit navigation/repair, never completion.
After all current-chapter material has persisted walkthroughs, invoke exam-study-guide to build, validate, and import the profile=full notebook/chNN.guide.json. Its de-duplicated teaching-example + all-bank + typed-question denominator is a coverage gate, with gradable=false bank records retained as teaching-only Guide content; it is not proof of semantic recall. Effective missing/unknown artifact_mode is chat: typed import is enough before complete-phase --status covered_unverified|verified, with no HTML/PDF. Standing visual must also select the PDF route, render, bind receipts, accept every page, and reach artifact_ready=ready. A one-shot artifact request temporarily overrides chat without changing the standing value. Never infer a subscription or install dependencies silently. Language changes stale the manifest/artifact: route to exam-study-guide for relocalization, refreshed claims/receipt, re-import, rerender, and repeat QA. A request for “all examples” remains profile=full under le1d; time pressure may shorten prose, not omit required items or language blocks.
-
Apply the time tier. Read mode and budget from state:
≤1天: no opening preference or reflective follow-up; teach now. This does not ban bank-backed drills or checkpoints. Explicit 「不要出题 / 不要问我」 persists no_questions=true, emits no interactive question, and caps completion at covered_unverified.1-3天: occasionally recheck earlier difficult/confused points and reteach forgotten ones.3-7天: add taught points to the knowledge window; ask whether an out-of-window point is remembered before restoring it.>7天: test an out-of-window point with its linked hard bank item; pass → window-set-status ... --status 已实测, fail → reteach. A point/index locator is required; add chapter for ambiguous names.
