/exam-help
备考教练的一屏速查卡:工作流、3×4 学习选择、产物偏好、工作区文件、6 大题型、来源规则与子技能路由。 用户问怎么用、有哪些模式、文件用途或支持题型时使用。
$ npx -y skills add ZeKaiNie/universal-examprep-skill --skill exam-help --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/exam-help
Context preview
The summary Claude sees to decide when to auto-load this skill.
备考教练的一屏速查卡:工作流、3×4 学习选择、产物偏好、工作区文件、6 大题型、来源规则与子技能路由。 用户问怎么用、有哪些模式、文件用途或支持题型时使用。
SKILL.md
exam-help.SKILL.mdname: exam-help
description: >
备考教练的一屏速查卡:工作流、3×4 学习选择、产物偏好、工作区文件、6 大题型、来源规则与子技能路由。
用户问怎么用、有哪些模式、文件用途或支持题型时使用。
license: MIT
exam-help — quick-reference card
Purpose
Render one read-only card covering the validated workflow, three modes, four time tiers, `lightweight|full`, `chat|visual`, workspace truth/views, six quiz types, provenance, and subskill routing.
Activation
Use only when the student asks how the suite works, which modes/types exist, or what workspace files mean.
Inputs
No files, arguments, or state reads. The caller supplies the selected language.
Workflow
1. Emit the matching static language-pack card: persisted `zh`, `en`, or `bilingual`, otherwise an explicit ad-hoc request. 2. Read no wiki, bank, plan, progress, or workspace file; run no script/subskill. 3. Stop without tutoring, quizzing, ingesting, grading, or initialization.
The card must say:
- `processing_mode=lightweight` is the default/recommended startup choice. It
inventories names, then visually processes only the current-phase PDF pages or definitely single-frame PNG/JPEG/BMP (maximum eight primary pages and one active batch). Overview contact sheets group at most four pages at roughly 768 px/tile; page/prompt/dependency detail and target-answer-only solution calls use source-qualified locations and canonical PNG evidence under `.lightweight/assets/`. Bind exact external answer pages with `register-answer-dependency`; dependency pages are locator/detail only. Figure prompt/answer crops stay distinct. An unfinished batch can close only through receipt-backed `abandon --reason`; taught progress cannot be abandoned, while `replace-taught --reason` preserves it as superseded history and plans an exact-slice successor. It keeps the page-batch / progress state machines and creates no Study Guide/PDF. `processing_mode=full` is explicit opt-in and opens the complete ingestion/review route. Input-token savings never shorten the teaching explanation.
- `artifact_mode` is independent from processing intensity and never inferred from
subscription. Missing/legacy/unknown means `chat`. In full mode, `chat` stops without PDF while standing `visual` additionally requires typed Guide, render, receipt hashes, every-page QA, and `artifact_ready=ready`. A one-shot artifact leaves stored state unchanged. In lightweight, a saved `visual` preference is dormant and effective output remains `chat`; it never builds a Study Guide.
- `answer_explanation_mode` is also independent. Its stored-schema fallback is
`ordinary`, and every full-Guide item still gets a detailed beginner-first explanation. At full-v2 Guide entry, a verified host-native child with a fresh independent context plus exact single-item input/tool restrictions makes `isolated` the default unless the learner opted out; tell the learner once about extra host quota/time, with no second API key or external upload. Missing or incomplete capability stays `ordinary` and is stated honestly. A separately billed external Provider is explicit-request-only and retains no-upload planning, current pricing/privacy disclosure, and exact-plan upload consent. A model name, subscription, key, `full`, or `visual` alone proves neither route.
- `ingest_course.py` is the full-mode build entry; exit 10 is process success with
blocked readiness, and teaching remains forbidden. `.ingest/` is full-mode build/review truth, `.lightweight/session.json` is on-demand page-batch truth, `study_state.json` is progress truth, and Markdown is a generated view.
- Lightweight completion uses current-phase taught-batch/notebook events and skips
typed Guide/full-build evidence; superseded predecessors/events remain history but leave the current denominator. `verified` needs revision-bound checkpoints from an unchanged bank that pre-existed lightweight initialization; startup captures only its immutable stat baseline. Routine health checks use metadata/physical identity, not stream hashes; exact hashes occur at transitions/completion or explicit `status --verify-live`. Older taught history is `unchecked_historical` until that phase is resumed.
- MinerU, Docling, and LangGraph are named-request-only and remote/cloud-only. Never
download, install, probe, import, or execute them locally.
- Provenance is exact: 🟢 来自资料 / 🟡 AI补充,可能与你老师讲的不完全一致 / ⚠️ AI生成答案,非老师/教材提供.
Output Contract
Output exactly one help card and mutate nothing. Student prose is English by default, Simplified Chinese for a Chinese opening, or explicit bilingual composition.
Language packs
- `中文` → [`../../locales/zh/skills/exam-help.md`](../../locales/zh/skills/exam-help.md)
- `English` → [`../../locales/en/skills/exam-help.md`](../../locales/en/skills/exam-help.md)
- `双语` → compose both blockwise, zh then `> EN:`, under [`docs/language-policy.md`](../../docs/language-policy.md)
Display aliases are normalized to `zh`, `en`, or `bilingual`.
Boundaries
This card is read-only. Route actual review to `exam-cram`.
Read more
name: exam-help description: > 备考教练的一屏速查卡:工作流、3×4 学习选择、产物偏好、工作区文件、6 大题型、来源规则与子技能路由。 用户问怎么用、有哪些模式、文件用途或支持题型时使用。 license: MIT
exam-help — quick-reference card
Purpose
Render one read-only card covering the validated workflow, three modes, four time tiers, `lightweight|full`, `chat|visual`, workspace truth/views, six quiz types, provenance, and subskill routing.
Activation
Use only when the student asks how the suite works, which modes/types exist, or what workspace files mean.
Inputs
No files, arguments, or state reads. The caller supplies the selected language.
Workflow
1. Emit the matching static language-pack card: persisted `zh`, `en`, or `bilingual`, otherwise an explicit ad-hoc request. 2. Read no wiki, bank, plan, progress, or workspace file; run no script/subskill. 3. Stop without tutoring, quizzing, ingesting, grading, or initialization.
The card must say:
- `processing_mode=lightweight` is the default/recommended startup choice. It
inventories names, then visually processes only the current-phase PDF pages or definitely single-frame PNG/JPEG/BMP (maximum eight primary pages and one active batch). Overview contact sheets group at most four pages at roughly 768 px/tile; page/prompt/dependency detail and target-answer-only solution calls use source-qualified locations and canonical PNG evidence under `.lightweight/assets/`. Bind exact external answer pages with `register-answer-dependency`; dependency pages are locator/detail only. Figure prompt/answer crops stay distinct. An unfinished batch can close only through receipt-backed `abandon --reason`; taught progress cannot be abandoned, while `replace-taught --reason` preserves it as superseded history and plans an exact-slice successor. It keeps the page-batch / progress state machines and creates no Study Guide/PDF. `processing_mode=full` is explicit opt-in and opens the complete ingestion/review route. Input-token savings never shorten the teaching explanation.
- `artifact_mode` is independent from processing intensity and never inferred from
subscription. Missing/legacy/unknown means `chat`. In full mode, `chat` stops without PDF while standing `visual` additionally requires typed Guide, render, receipt hashes, every-page QA, and `artifact_ready=ready`. A one-shot artifact leaves stored state unchanged. In lightweight, a saved `visual` preference is dormant and effective output remains `chat`; it never builds a Study Guide.
- `answer_explanation_mode` is also independent. Its stored-schema fallback is
`ordinary`, and every full-Guide item still gets a detailed beginner-first explanation. At full-v2 Guide entry, a verified host-native child with a fresh independent context plus exact single-item input/tool restrictions makes `isolated` the default unless the learner opted out; tell the learner once about extra host quota/time, with no second API key or external upload. Missing or incomplete capability stays `ordinary` and is stated honestly. A separately billed external Provider is explicit-request-only and retains no-upload planning, current pricing/privacy disclosure, and exact-plan upload consent. A model name, subscription, key, `full`, or `visual` alone proves neither route.
- `ingest_course.py` is the full-mode build entry; exit 10 is process success with
blocked readiness, and teaching remains forbidden. `.ingest/` is full-mode build/review truth, `.lightweight/session.json` is on-demand page-batch truth, `study_state.json` is progress truth, and Markdown is a generated view.
- Lightweight completion uses current-phase taught-batch/notebook events and skips
typed Guide/full-build evidence; superseded predecessors/events remain history but leave the current denominator. `verified` needs revision-bound checkpoints from an unchanged bank that pre-existed lightweight initialization; startup captures only its immutable stat baseline. Routine health checks use metadata/physical identity, not stream hashes; exact hashes occur at transitions/completion or explicit `status --verify-live`. Older taught history is `unchecked_historical` until that phase is resumed.
- MinerU, Docling, and LangGraph are named-request-only and remote/cloud-only. Never
download, install, probe, import, or execute them locally.
- Provenance is exact: 🟢 来自资料 / 🟡 AI补充,可能与你老师讲的不完全一致 / ⚠️ AI生成答案,非老师/教材提供.
Output Contract
Output exactly one help card and mutate nothing. Student prose is English by default, Simplified Chinese for a Chinese opening, or explicit bilingual composition.
Language packs
- `中文` → [`../../locales/zh/skills/exam-help.md`](../../locales/zh/skills/exam-help.md)
- `English` → [`../../locales/en/skills/exam-help.md`](../../locales/en/skills/exam-help.md)
- `双语` → compose both blockwise, zh then `> EN:`, under [`docs/language-policy.md`](../../docs/language-policy.md)
Display aliases are normalized to `zh`, `en`, or `bilingual`.
Boundaries
This card is read-only. Route actual review to `exam-cram`.
Turn your slides, homework, and past papers into a source-aware tutor that remembers your progress.
Other skills on universal-examprep-skill.
- /confusion-tracker
教学过程中自动捕获和记录学习者的概念疑难点("为什么/是什么/怎么推/什么意思"类型的问题),保存到进度文件的"概念疑难点记录"区,形成考前回顾清单。
Open skill - /exam-audit
只读检查一个已生成的备考工作区是否健康并报告问题,默认不做任何修改。核对 .ingest 原材料版本、 内容单元、接管队列与派生产物完整性,以及 wiki、题库、视觉证据、计划和进度的一致性。当用户怀疑 工作区有问题、建库 readiness 被阻断、或想在开始复习前体检时使用。
Open skill - /exam-cheatsheet
全员通关后把 错题本+笔记本+知识点窗口+wiki 编译成考前速记小抄 cheatsheet.md(每条要点带可溯源 锚点),并在视觉产物模式或用户明确要求 PDF/打印版时按指定页数渲染成打印级 PDF:按「必背结论/公式 → 有难度例题(必要时含题面图)→ 例题解答(代入公式、保留基础过程)→ 要点解释(同类题怎么办)」 四段组织。当复习收尾、用户要「考前小抄/速记/总结/打印版」时使用。
Open skill - /exam-cram
临考前的极速备考总教练。把课件、大纲、重点与真题建成分章 wiki 和标准题库,再组织惰性授课、 题库判分、错题与疑难复盘及可选考前小抄,并持久化进度。用于期末、备考、突击、刷题、划重点、 错题与考前复习;不用于长期规划或与考试无关的写作/编程。
Open skill - /exam-ingest
从学生上传的课件/大纲/老师勾的重点/真题,一键初始化并验证备考工作区:解析 PDF、DOCX、PPTX、 XLSX、常见独立图片与 txt/md,建立分章节 LLM Wiki、标准题库、结构化接管队列与进度状态;仅在 Python 确实无法运行时 明确降级为手动写盘。当工作区尚未建立、资料发生变化、或建库 readiness 被阻断时使用。
Open skill - /exam-quiz
从 references/quiz_bank.json 抽取本章题目并按标准答案判分,支持选择、主观、画图、填空、判断、代码; 主观题按 keywords 要点覆盖判分,连续错两次提供提示/跳过/归档。禁止现场编题。用于阶段检查或模考。
Open skill

