AugmentClaude
Lesson PlansTutoring

zh

By ZeKaiNie· ZeKaiNie/universal-examprep-skill· 0

Study smarter with AI-powered exam prep, tutoring, and practice quizzes.

Installation

  1. Make sure Claude is on your device and in your terminal.

    Skills load from ~/.claude/skills/ when Claude Code starts up — so you need it on your machine first. If you don't have it yet, install it once with the command below, then run claude in any terminal to verify.

    One-time setup
    npm i -g @anthropic-ai/claude-code

    Already have it? Skip ahead.

  2. Paste into Claude Code or into your terminal.
    Install
    Sign up to copy
    Sign up free to reveal

    This copies the whole skill folder into ~/.claude/skills/zh-zekainie/ — the SKILL.md plus any scripts, reference docs, or templates the skill ships with. Safe default: works for every skill.

    Faster alternative (instruction-only skills)

    Skips the clone and grabs only the SKILL.md file. Don't use this if the skill ships Python scripts, reference markdowns, or asset templates — they won't be downloaded and the skill will fail when it tries to load them.

    Quick install (SKILL.md only)
    Sign up to copy
    Sign up free to reveal
  3. Restart Claude Code.

    Quit and reopen Claude Code (or any other agent that loads from ~/.claude/skills/). New skills are picked up on startup.

  4. Just ask Claude.

    Skills auto-activate when your request matches the skill's description — no slash command needed. Trigger phrases live in the skill's own frontmatter; you can read them in the “What this skill does” section above.

Prefer to read the source first? Open on GitHub.

When Claude uses it

Claude activates this skill based on the context of your request.

What this skill does

极速备考教练——中文兼容入口

本文件是简体中文兼容入口，不是第二份流程手册。行为唯一事实源是 skills/exam-cram/SKILL.md 与当前子技能；文案派发见 docs/language-policy.md。

装载

先读总编排器，再只读当前需要的一项：exam-ingest、exam-tutor、exam-study-guide、exam-quiz、exam-review、exam-cheatsheet、exam-audit、exam-help 或 confusion-tracker。持久化语言值为 zh|en|bilingual；zh 使用纯简体中文，双语只能显式选择。

兼容安全钉

  • 断点状态锁定 (study_state.json)：本地操作前跑 update_progress.py workspace-list --json，确认材料/工作区绝对路径并先恢复状态；study_progress.md 只是生成视图。状态缺失且 Python 可用时，先跑 python "${CLAUDE_SKILL_DIR}/scripts/update_progress.py" --workspace <ws> init，再 set、set-check 等写入；不得把仓库或当前目录当工作区。
  • 首次把学习模式、时间宽裕度、回复语言一起设定。紧急开场可推断从头讲＋≤1天＋开场语言，绝不推断双语；明确不要提问时保存 no_questions=true，阶段上限为 covered_unverified。
  • 测验/判分只用 references/quiz_bank.json；常规选题用 select_questions.py，检查点用 select_hard_questions.py --chapter <当前章>。限定范围排除并计数无标签题；临时越界前说：⚠️ 临时覆盖你的 <范围> 范围偏好。
  • requires_assets=true 或 maybe_requires_assets=true 时，提问、提示、讲解、解答之前真实展示全部题面图；路径不算图片。答案图只能稍后显示；不能渲染就跳过。stub/page_reference 也须先显示原页上下文。
  • 实质内容先用 notebook.py 持久化；失败就说明并在对话给全文。缺失/未知 artifact_mode 按 chat；只有显式 visual 或一次性请求进入强类型教材、渲染与全页验收，不静默安装，也不猜订阅档位。

知识来源标注

  • 🟢 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
  • 无依据时说：“资料里没有这道题的答案”。
  • 重点题七步：① 题面图 → ② 这题在问什么 → ③ 图里要读的量 → ④ 核心公式 → ⑤ 逐步演算 → ⑥ 答案自检 → ⑦ 知识点溯源。
  • 来源块：题目来源：…｜答案来源：…｜<完整来源标签>；未知就写“来源未知”。

原始资料引文可在明确标注后保留原语言；智能体写的标题、解释、答案与总结仍遵守当前语言。

Related skills

A

Ajahn Chah

xr843

Learn Theravada Buddhist teachings and mindfulness practice in Ajahn Chah's voice.

MIT
E

en

ZeKaiNie

Study faster with AI-powered exam prep and practice questions.

A

Art History Movements

Tibsfox

Learn 12 major art movements from Renaissance to contemporary, their key artists, and historical context.

C

Color Theory

Tibsfox

Learn color properties, mixing systems, and schemes for art and design.