DeepTutor CLI
HKUDS/DeepTutor
Teaches the agent to set up and run DeepTutor from the command line: chat and capabilities, knowledge bases, partners, memory, sessions, notebooks and the server or Web app.
初中到高中的数学概念理解与重建(高中覆盖必修与选择性必修):学生不是卡在某道题,而是卡在"这个数学概念本身没懂"时用. An agent skill from qizhitang/xiaozhi-skills.
$ npx skills add qizhitang/xiaozhi-skills --skill xiaozhi-math-concept-explainer -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-math-concept-explainer --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/qizhitang/xiaozhi-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/student/math/xiaozhi-math-concept-explainer .claude/skills/xiaozhi-math-concept-explainer && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "xiaozhi-math-concept-explainer" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/student/math/xiaozhi-math-concept-explainer into .claude/skills/xiaozhi-math-concept-explainer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-math-concept-explainer", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/qizhitang/xiaozhi-skills/tree/main/student/math/xiaozhi-math-concept-explainerType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add qizhitang/xiaozhi-skills --skill xiaozhi-math-concept-explainer -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-math-concept-explainer --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/qizhitang/xiaozhi-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/student/math/xiaozhi-math-concept-explainer .agents/skills/xiaozhi-math-concept-explainer && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "xiaozhi-math-concept-explainer" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/student/math/xiaozhi-math-concept-explainer into .agents/skills/xiaozhi-math-concept-explainer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-math-concept-explainer", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add qizhitang/xiaozhi-skills --skill xiaozhi-math-concept-explainer -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-math-concept-explainer --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/qizhitang/xiaozhi-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/student/math/xiaozhi-math-concept-explainer .cursor/skills/xiaozhi-math-concept-explainer && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "xiaozhi-math-concept-explainer" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/student/math/xiaozhi-math-concept-explainer into .cursor/skills/xiaozhi-math-concept-explainer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-math-concept-explainer", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/qizhitang/xiaozhi-skills.git --path student/math/xiaozhi-math-concept-explainer--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add qizhitang/xiaozhi-skills --skill xiaozhi-math-concept-explainer -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-math-concept-explainer --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/qizhitang/xiaozhi-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/student/math/xiaozhi-math-concept-explainer .gemini/skills/xiaozhi-math-concept-explainer && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "xiaozhi-math-concept-explainer" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/student/math/xiaozhi-math-concept-explainer into .gemini/skills/xiaozhi-math-concept-explainer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-math-concept-explainer", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-math-concept-explainerInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add qizhitang/xiaozhi-skills --skill xiaozhi-math-concept-explainer -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/qizhitang/xiaozhi-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/student/math/xiaozhi-math-concept-explainer .github/skills/xiaozhi-math-concept-explainer && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "xiaozhi-math-concept-explainer" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/student/math/xiaozhi-math-concept-explainer into .github/skills/xiaozhi-math-concept-explainer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-math-concept-explainer", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add qizhitang/xiaozhi-skills --skill xiaozhi-math-concept-explainer -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-math-concept-explainer --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/qizhitang/xiaozhi-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/student/math/xiaozhi-math-concept-explainer .opencode/skills/xiaozhi-math-concept-explainer && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "xiaozhi-math-concept-explainer" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/student/math/xiaozhi-math-concept-explainer into .opencode/skills/xiaozhi-math-concept-explainer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-math-concept-explainer", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
xiaozhi-math-concept-explainer初中到高中的数学概念理解与重建(高中覆盖必修与选择性必修):学生不是卡在某道题,而是卡在"这个数学概念本身没懂"时用. An agent skill from qizhitang/xiaozhi-skills.
Xiaozhi Math Concept Explainer is an agent skill from qizhitang/xiaozhi-skills. 初中到高中的数学概念理解与重建(高中覆盖必修与选择性必修):学生不是卡在某道题,而是卡在"这个数学概念本身没懂"时用。 典型触发:"这个数学公式我知道但不明白为什么""负负为什么得正""一次函数和正比例有什么区别""几何题我脑子里建不起图形""这两个数学概念我总是混""用生活例子讲讲这个概念"。 核心方法:三种解释模型(生活类比 / 图解可视化 / 逐步拆分)+ 几何空间想象训练。 不处理:具体某道题怎么做(转 xiaozhi-math-problem-solving-coach)、应用题列式(转 xiaozhi-math-word-problem-coach)、错题收录与统计(转 xiaozhi-correction-notebook)、分层进阶练习(转 xiaozhi-math-gradient-trainer)。
Its SKILL.md is about 2.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 13 other files, including reference files (for example `references/analogy-bank.md`, `references/math-hs1-concepts.md` and `references/math-hs2-concepts.md`). Compatibility notes: WorkBuddy / SkillHub / OpenClaw / ClawHub
It sits in Education, covering Tutoring and explanations. The licence is MIT.
Read from SKILL.md and the folder at commit 3912b8f. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
WorkBuddy / SkillHub / OpenClaw / ClawHub
From compatibility in the SKILL.md frontmatter.
Xiaozhi Math Concept Explainer loads about 2.3k tokens when it runs, and up to ~18k if it reads all its reference files. Until then it costs about 99 tokens; SKILL.md has 306 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from qizhitang/xiaozhi-skills at commit 3912b8f, republished under its MIT licence (© qizhitang). 306 words, ~2,299 tokens.
.claude/skills/xiaozhi-math-concept-explainer/SKILL.md (or your agent's skills folder). This skill also uses 11 other files; get the full folder from GitHub.一句话定位: 不要记规则,要理解规律——
当你真正明白"为什么",公式就不需要死记了。
技术边界:本 SKILL 依赖能力 [M],无该能力时按 shared/platform-conventions.md 降级。 无跨会话记忆时不承诺"下次我还记得你哪个概念没通",请学生下次把上次的结论再发一次。 使用前提:小学学段须有家长或老师在场陪同使用(shared/vocab.md §8 规则 4);学生说明正在考试或测验中时,不讲该题、不给提示,约好考完再复盘(shared/hint-ladder.md §〇)。
⚠️ 危机例外(最高优先级):若对话中出现自伤/自残、轻生念头、遭受霸凌或伤害、持续严重绝望、家庭安全问题等超出学习范畴的信号,立即停止本 SKILL 的一切流程(含熔断、温情转化、数据展示、出题、家长摘要),按 shared/crisis-exception.md 处置:稳住不评判 → 说明 AI 边界 → 如实提示联系信任的成年人 → 按所在地区给出求助渠道(不确定地区时先问;中国大陆即时危险为 110/120,其他地区用当地紧急电话)。宁可误报,不可漏报;档案只记"已转介"的处置事实。
提示阶梯:本 SKILL 按 shared/hint-ladder.md 运行,默认最高级 L6——概念题本来就允许讲解; 但讲解之后必须让学生用自己的话复述一遍或举一个新例子,才算这一轮结束。
轮次预算: 一个概念一次讲透,单条 ≤120 字,追问 ≤3 轮;两轮无回复即收尾(留一句"这个概念的一句话版本"并归档)。
- 查看:「查看我的概念理解记录」
- 更正:「更正我的档案」
- 删除:「删除我的档案」(删除后不可恢复,会先确认一次)
- 暂停:「这次不要记忆」(本次会话不读取、不保存任何记录,也不发起回写与交接)/「暂停提醒」
- 共享控制:「不要共享给其他SKILL」/「不要给家长看」
- 导出:「导出我的档案」(以文本形式给出,便于转存)为什么死记公式无效:
背公式 → 考试时脑子空白,记不起来
背公式 → 换一种题型,不知道用哪个
背公式 → 以为学会了,做题却出错
根本原因:只记住了"结论",没有理解"为什么"。这个SKILL的解法:
先建立"生活中的直觉" → 再引入数学语言 → 再给出公式
当你理解了"为什么负负得正",
你就不需要记这条规则了——因为它在你的逻辑里是自然成立的。根据不同的概念类型,选择最合适的解释模型:
模型A 生活类比法
→ 适用于:运算规则、代数概念、统计概念
→ 方法:先用生活场景建立直觉,再引入数学定义
模型B 图解可视化法
→ 适用于:几何概念、函数图像、空间想象
→ 方法:引导学生在大脑中构建图形,用描述代替公式
模型C 逐步拆分法
→ 适用于:复杂定理、多条件判定、综合性公式
→ 方法:从最简单的情形出发,逐步加条件,每步追问Step 1:找到最贴切的生活场景
→ 不能牵强,要让学生"一听就明白"
→ 场景必须是学生熟悉的日常生活
Step 2:用生活场景建立直觉,暂时不引入数学符号
→ "不要告诉我公式,先用场景想一想"
Step 3:用追问确认直觉建立了
→ "在这个场景里,[X情况]会怎样?"
Step 4:现在引入数学语言
→ "你刚才说的[X],在数学里就是[公式/定义]"
Step 5:验证迁移
→ "用这个理解,你能解释[另一个相关概念]吗?"负数乘负数(负负得正):
生活场景:零花钱
"你每天花钱(负数)。
'减少花钱'(负的负数)就是省钱,
省钱对你的财务来说是好事(正数)。
追问:'少花'3天钱,等于'多了'多少钱?"
⚠️ 边界:这个类比帮助理解"相反的相反=原方向"(即 -(-a)=a),
是直觉铺垫、不是 (-a)×(-b) 的严格证明。
讲两个负数相乘时,配合"规律法"更稳:
3×(-2)=-6, 2×(-2)=-4, 1×(-2)=-2, 0×(-2)=0,
(-1)×(-2)=? 每次结果 +2 → 得 +2,(-2)×(-2)=+4。一次函数 y=kx+b:
生活场景:出租车计费
"出租车起步价是8元(这是b),
然后每公里加2元(这是k)。
你坐了x公里,总费用是 y = 2x + 8。
追问:如果起步价变成0,这是什么函数?
如果每公里也是0,这是什么函数?"绝对值:
生活场景:距离
"数轴上的绝对值就是这个点到原点的距离。
距离永远是非负的——不管你往左走还是往右走,
走了3步就是3步,不会是'负3步'。
追问:|-5|和|5|哪个更大?
|x|能等于-3吗?为什么?"概率(频率趋近概率):
生活场景:抛硬币
"如果你抛硬币10次,可能正面出现7次,
也可能出现3次——这是随机的。
但如果你抛1000次,正面大概是500次左右。
追问:抛10次正面出现7次,
正面朝上的概率就是0.7吗?
为什么不是?"平均增长率(连续增长场景):
生活场景:连续两年的产量
"某厂第一年产量 a,第二年比第一年增长 x,第三年又比第二年增长 x。
第二年:a(1+x)
第三年:a(1+x)(1+x) = a(1+x)²
追问①:第三年增长的时候,是拿第一年的 a 去乘 x,
还是拿第二年的 a(1+x) 去乘 x?
追问②:那 a(1+2x) 算的是什么?和 a(1+x)² 差在哪?
(展开:a(1+x)² = a(1+2x+x²),多出来的 ax²
就是'第二年多出来的那部分也参与了第三年的增长')"
⚠️ 这就是九年级"平均增长率"一元二次方程题的来源,
到 a(1+x)² 为止;再往下的通项与求和是高中选择性必修的数列内容(⚠高中 等比数列),初中不展开,高中学生见第十节。Step 1:实物锚定(先找生活中的实物)
→ 别直接看图,先找现实中对应的物体
→ 圆柱 = 水杯/罐头;正方体 = 骰子;棱锥 = 金字塔
→ "你手边有没有[XX形状的]东西?拿着它想一下。"
Step 2:动作模拟(在大脑里"动"起来)
→ 不要静态地看图,要想象"切开/展开/旋转"的动作
→ "如果你用刀沿着这条线切下去,截面是什么形状?"
→ "把这个立体图形用剪刀剪开铺平,是什么形状?"
Step 3:追问路径(用语言代替视觉)
→ 如果学生在大脑里"看不到",改用语言描述
→ "我不管你看不看得到图形——
告诉我:圆柱的侧面,宽度是哪里,高度是哪里?"圆柱/圆锥展开类:
"如果把圆柱的侧面沿一条直线剪开并展平,
展开后是什么形状?(不要先看答案,猜一猜)"
确认后追问:
"展开图的宽是圆柱的什么?高是什么?
所以侧面积的公式应该是什么?"正方体展开类:
"一个正方体有几个面?(6个)
把它展开,这6个面要排成什么样才能折回去?
有没有一个面是'不管怎么折都折不到正确位置'的摆法?"
→ 引导学生思考展开图的有效性截面类:
"用一个平面切正方体,截面可以是什么形状?
先猜:可以是三角形吗?可以是六边形吗?
给你一个提示:截面的边数=平面经过的面数。
那截面最多可以有几条边?"旋转体类:
"一个直角三角形,把它的直角边作为轴旋转一圈,
得到的立体是什么?
追问:如果旋转的是斜边而不是直角边,结果还一样吗?"适用概念: 复杂定理、多条件判定、综合性公式
Step 1:从最极简的情形开始
→ 去掉所有附加条件,只保留最核心的一层
→ "先忘掉所有特殊情况,就问最简单的版本"
Step 2:每加一个条件,追问一次
→ "现在加上条件[X],结论变了吗?怎么变的?"
Step 3:反例挑战
→ "有没有一个情况,满足了前面的条件但结论不成立?"
→ 这个步骤帮助确认定理的适用边界
Step 4:自己总结
→ "用一句话说,这个定理在说什么?"
→ 学生能用自己的话说出来,才算真正理解第1层(最简):
"如果两个三角形的一对角相等,它们一定相似吗?"
→ 不一定(只有一个条件不够)
第2层(加条件):
"如果两对角都相等,它们一定相似吗?"
→ 一定!因为第三个角也确定了(三角之和=180°)
拆分追问:
"为什么知道两个角就够了,不需要第三个角?"
→ 引导发现:三个角加起来是180°,知道两个就知道第三个
反例挑战:
"两个三角形,各有一个60°角,它们一定相似吗?"
→ 不一定(只有一组角相等不够)
自己总结:
"用一句话说AA定理在说什么?"
→ "两个三角形有**两组对应角分别相等**,就相似——
因为第三组角由内角和自然确定了。"
(注意措辞:是"两组对应角分别相等",不是"两个角相等";
同一个三角形里的两个角相等说的是等腰,那是另一回事。)概念讲解完成后,必须做以下验证:
验证①:换一个例子
"你来给我举一个[这个概念]的例子,
不能用我刚才讲的那个。"
→ 能举出新例子 = 真正理解了
验证②:反例判断
"[举一个不符合这个概念的情形],这个算不算[概念]?为什么?"
→ 能判断反例 = 边界清晰了
验证③:应用迁移
"用[这个概念]解这道题:[一道简单的直接应用题]"
→ 能做对 = 会用了
→ 这道题由 AI 现出时,生成前按 shared/ai-item-check.md 自检
(自解一遍、有解且唯一、数值友好、不超出初中学段)
验证④:联系旧知
"[这个概念]和你之前学过的[相关概念]有什么关系?"
→ 能建立联系 = 知识网络形成了| ❌ 禁止 | ✅ 替代 |
|---|---|
| 直接给公式和定义 | 先建立生活直觉,再引入公式 |
| 用数学语言解释数学(循环解释) | 用学生熟悉的非数学场景类比 |
| 说"这个你背下来就好了" | "你理解了为什么之后,就不需要背了" |
| 几何题直接给展开图 | 先追问学生的空间想象,再给答案 |
| 验证理解时只问"明白了吗" | 让学生举新例子或解一道题 |
数学概念解释器 SKILL
<-- xiaozhi-math-error-dna(B 类概念模糊错误转入,带 subtypeId)
<-- xiaozhi-math-problem-solving-coach(解题中发现概念本身没建立时转入)
<-- xiaozhi-math-gradient-trainer(某层卡住且属于概念问题时转入)
--> xiaozhi-learning-dna(profile_writeback:updateTarget=concept_graph,
masteryLevel 用三档 会复述/会解释/真正掌握;须 crossSkillSharing=true)
--> xiaozhi-im-reminder(仅 reminder_enqueue 入队,按 shared/vocab.md §9 合并;
本 SKILL 不承诺"我1天后提醒你")掌握度只用三档(shared/vocab.md §6):会复述(只能复述结论)/ 会解释(说得清为什么,迁移不稳)/ 真正掌握(能解释 + 能迁移到新题型)。
验证①②通过 → 会解释;验证③④也通过 → 真正掌握。
依据《普通高中数学课程标准日常修订版(2017 年版 2025 年修订)》必修主题一"预备知识"与主题二"函数"。学生说明在读高一,或初中毕业后做衔接预习时用本节。课标的教学提示指出,初中数学知识相对具体、高中相对抽象,所以每个高一概念都先从学生熟悉的初中内容讲起,再过渡到集合语言与符号语言。
| 概念 | 从哪里讲起 | 对应子类型 |
|---|---|---|
| 属于与包含 | 学生与班级、班级与学校 | B10 |
| 充分条件与必要条件 | "下雨 ⇒ 地面湿",再说清数学只看能不能推出 | B11 |
| 全称量词命题的否定 | "全班都交了作业"的否定是"至少一人没交" | B12 |
| 一元二次不等式的解集 | 解集就是函数图像在 x 轴上方(或下方)那一段所对应的 x;口诀只在二次项系数为正时成立 | B18 |
| 函数是对应关系 | 初中"两个变量的依赖关系"→ 集合之间的对应关系;定义域是函数的一部分 | B13 |
| 单调性、奇偶性 | 从"图像上升""图像对称"过渡到符号语言;奇偶性先看定义域是否关于原点对称 | B14 |
| 指数与对数 | 同一个关系的"问与答":2³ = 8 与 log₂8 = 3 | B15 |
| 弧度制与单位圆 | 用半径量弧;从锐角的边比过渡到单位圆上的坐标 | B16 |
| 零点 | 零点是方程 f(x) = 0 的解,是一个数,不是一个点 | B05 |
| 零点存在定理 | 从河的一岸走到另一岸,一路不跳就一定要过河;反过来不成立,也可能过河不止一次 | B17 |
三种模型照用:生活类比必须写明讲得到哪儿、讲不到哪儿,越过边界的部分回到定义;每讲完一个概念,用一个检验问题确认学生会解释、能迁移(第六节)。类比、边界、检验问题与验算断言见 references/math-hs1-concepts.md。必修后半与选择性必修的概念见第十节。
依据《普通高中数学课程标准日常修订版(2017 年版 2025 年修订)》必修主题三"几何与代数"、主题四"概率与统计",以及选择性必修的"函数""几何与代数""概率与统计"三个主题。学业水平考试考必修,高考考必修与选择性必修。选修课程(A~E 类)和必修、选择性必修以外的方法(如洛必达法则),如实说明本 SKILL 不覆盖。
| 概念 | 从哪里讲起 | 对应子类型 |
|---|---|---|
| 数量积 | 力做的功:力和位移是向量,功是一个数;消去律、结合律不能照搬 | B19 |
| 投影向量、夹角为钝角 | 向量的"影子";a·b < 0 还包括两个向量反向共线的情形 | B19 |
| 共线与垂直的坐标条件 | 分别从 b = λa 与 a·b = 0 推出来,不靠死记 | B19 |
| 正弦定理解的个数 | 以 C 为圆心画弧,看弧与角的另一边有几个交点 | B20 |
| 余弦定理 | 勾股定理的推广:C = 90° 时回到 c² = a² + b² | B20 |
| 复数 | 数系的扩充:为了让 x² = −1 有解;复数与复平面上的点、向量一一对应;除法类比分母有理化 | B21 |
| 空间位置关系 | 借助长方体:判定定理的条件缺一不可,平面里的结论到了空间要先找反例 | B22 |
| 柱、锥、台、球的体积 | 倒水实验看出 1/3;球的体积 = (1/3) × 表面积 × 半径 | B23 |
| 古典概型 | 给两枚硬币编号:样本点先要等可能 | B24 |
| 互斥、对立与独立 | "不能同时发生"与"互不影响概率"是两回事,用 P(AB) = P(A)P(B) 验证 | B25 |
| 频率分布直方图、百分位数 | 面积才是频率;百分位数是"大约 p% 的数据不超过它" | B26 |
| 数列 | 一类特殊的函数:等差对一次函数,等比对指数函数;由 Sₙ 求 aₙ 要单独看 n = 1 | B27 |
| 导数 | 里程表与速度表:从平均变化率到瞬时变化率;"在点 P 处"与"过点 P"的切线 | B28 |
| 导数与单调性、极值 | 爬山:山顶不一定是全程最高点;导数为 0 不一定是极值点 | B29 |
| 求导公式与法则 | 长方形两边各长一点:(uv)′ = u′v + uv′;(1/x)′ = −1/x² 这类公式也要会 | B30 |
| 法向量与空间角 | 线面角用正弦,二面角看图判断锐钝 | B31 |
| 倾斜角与斜率 | 竖直的直线没有斜率 | B32 |
| 圆锥曲线 | 钉子和绳子画椭圆;椭圆 a 最大、双曲线 c 最大;抛物线先化成标准方程 | B33 |
| 排列与组合 | 交换顺序算不算不同的结果;平均分组要除以组数的阶乘 | B34 |
| 二项式定理 | 通项是第 r + 1 项;二项式系数与项的系数不同 | B35 |
| 条件概率 | 已知 A 发生,样本空间缩小了 | B36 |
| 二项分布与超几何分布 | 有没有放回 | B37 |
| 相关、回归与独立性检验 | 相关不等于因果;预测值是估计值;推断可能犯错 | B38 |
数学归纳法(多米诺骨牌;课标标*的选学内容,不作为考试要求)、均值与方差、正态分布等没有专门错因编码的概念,也收在参考资源里。三种模型照用:类比写明讲得到哪儿、讲不到哪儿,越过边界的部分回到定义;每讲完一个概念,用一个检验问题确认学生会解释、能迁移(第六节)。类比、边界、检验问题与验算断言:必修后半见 references/math-hs2-concepts.md,选择性必修见 references/math-hs3-concepts.md;检验问题若需新编,按 shared/ai-item-check.md 自检后再给出。
references/math-hs1-concepts.md — 高一衔接段(预备知识与函数)的概念类比、边界与检验问题(含 CI 验算断言)references/math-hs2-concepts.md — 高中必修后半(平面向量及其应用、复数、立体几何初步、概率、统计)的概念类比、边界与检验问题(含 CI 验算断言)references/math-hs3-concepts.md — (高中)选择性必修(数列、导数、空间向量与立体几何、平面解析几何、计数原理、概率、统计)的概念类比、边界与检验问题(含 CI 验算断言)references/analogy-bank.md — 初中数学全概念生活类比素材库(按章节整理)💡 小智说:
"数学不是需要死记的规则集合。
每一条公式背后都有一个'为什么'——
那个'为什么'才是真正的数学。
当你懂了'为什么',公式就变成了你自己的东西——
一时想不起来,你也能自己把它推回来。"
© qizhitang, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 11 other files (references) in student/math/xiaozhi-math-concept-explainer of qizhitang/xiaozhi-skills.
Open the folder on GitHubat commit 3912b8f
Xiaozhi Math Concept Explainer next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Xiaozhi Math Concept Explainer this skillqizhitang/xiaozhi-skills | 105 | — | ~2.3k | Automated safety check: Pass | MIT | |
| DeepTutor CLIHKUDS/DeepTutor | 41k | — | ~2.8k | Automated safety check: Pass | Apache-2.0 | |
| AI Engineering Project Tutorrohitg00/ai-engineering-from-scratch | 66k | — | ~1.6k | Automated safety check: Pass | MIT | |
| Hung-Yi Lee Teaching Stylevoidful/hung-yi-lee-skill | 1.3k | — | ~13k | Automated safety check: Pass | None | |
| Claude Certification Tutorrohitg00/ai-engineering-from-scratch | 66k | — | ~3k | Automated safety check: Pass | MIT | |
| StudyVault Quiz Tutorbevibing/tutor-skills | 1.3k | — | ~1.4k | Automated safety check: Pass | MIT |
HKUDS/DeepTutor
Teaches the agent to set up and run DeepTutor from the command line: chat and capabilities, knowledge bases, partners, memory, sessions, notebooks and the server or Web app.
rohitg00/ai-engineering-from-scratch
Tutors a learner through one stage of a hands-on AI engineering project per session: lesson, prediction, code, grader run and reflection, with hints but never full solutions.
voidful/hung-yi-lee-skill
Explains machine learning, LLMs, AI agents and speech modeling in a Hung-Yi Lee-inspired teaching style, drawing on a knowledge base built from his lectures and research references.
rohitg00/ai-engineering-from-scratch
Guides a learner through one of four independent Claude certification tracks with onboarding, lessons, practice labs, mock exams and remediation.
bevibing/tutor-skills
Quizzes you on the notes in an Obsidian StudyVault, tracks proficiency per concept and drills weak areas in four-question rounds.
THU-MAIC/OpenMAIC
Designs a review-and-practice lesson around an independent first attempt, targeted feedback, supported practice, a fresh independent check and a next step.
qizhitang/xiaozhi-skills
生物图表与材料题教练:陪学生读懂当前这道题里的曲线、示意图、系谱图、数据表和材料——先看轴、看点、看线,再联系教材原理作答;覆盖初中学业水平考试(会考)的识图题与高中必修、选择性必修的图表(选择性必修只对选考生物的学生讲)。
qizhitang/xiaozhi-skills
生物概念网络构建器:帮学生把零散的生物概念连成网——按"大概念 → 重要概念 → 次位概念"分层,用结构与功能、物质与能量等生命观念串起来,理清基因与染色体、光合作用与呼吸作用这类最易混的概念关系;高中覆盖必修与选择性必修的概念层级(选择性必修只对选考生物的学生)。
qizhitang/xiaozhi-skills
初中到高中的生物错题根因分析与档案:按生物六维(概念网络、结构与功能、图表识读、变量与实验设计、表述与术语、遗传与数据计算)定位子类型,给出弱项报告;高中覆盖必修与选择性必修(维度表第八、十一、十二节)。
qizhitang/xiaozhi-skills
遗传推理教练:陪学生做当前这道遗传题——定性状、定基因组成、画遗传图解、算概率;初中讲显性与隐性、基因组成和性别决定,高中必修讲分离定律、自由组合定律、伴性遗传与系谱图判断,以及 DNA 复制与基因表达的计算、可遗传变异、基因频率。
qizhitang/xiaozhi-skills
生物实验探究教练:讲清探究的步骤、对照实验怎么设计、每一步为什么这样做、结论怎么写,覆盖初中常见实验与实验操作考试备考,以及高中必修与选择性必修的学生活动与实验设计题。
qizhitang/xiaozhi-skills
初高衔接规划:中考结束到高一上学期,诊断语文、数学、物理、化学、英语、生物各自的衔接缺口,排出暑假与高一开学头几周的衔接计划,再把具体内容交给对应的学科技能。
Categories
初中到高中的数学概念理解与重建(高中覆盖必修与选择性必修):学生不是卡在某道题,而是卡在"这个数学概念本身没懂"时用. An agent skill from qizhitang/xiaozhi-skills. Xiaozhi Math Concept Explainer is an agent skill from qizhitang/xiaozhi-skills.
Xiaozhi Math Concept Explainer fits situations like: tasks that involve Tutoring and explanations.
Run `npx skills add qizhitang/xiaozhi-skills --skill xiaozhi-math-concept-explainer -a claude-code`. Or copy the skill folder (student/math/xiaozhi-math-concept-explainer in qizhitang/xiaozhi-skills) into .claude/skills/xiaozhi-math-concept-explainer in your project. Claude Code loads it when a task matches its description.
Run `npx skills add qizhitang/xiaozhi-skills --skill xiaozhi-math-concept-explainer -a codex`. Or copy the skill folder (student/math/xiaozhi-math-concept-explainer in qizhitang/xiaozhi-skills) into .agents/skills/xiaozhi-math-concept-explainer in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add qizhitang/xiaozhi-skills --skill xiaozhi-math-concept-explainer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/xiaozhi-math-concept-explainer, .gemini/skills/xiaozhi-math-concept-explainer, .github/skills/xiaozhi-math-concept-explainer and .opencode/skills/xiaozhi-math-concept-explainer in your project.
SKILL.md names no scripts, command-line tools or credentials: Xiaozhi Math Concept Explainer is instructions for the agent only. Compatibility (from SKILL.md): WorkBuddy / SkillHub / OpenClaw / ClawHub.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Xiaozhi Math Concept Explainer is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.3k tokens (SKILL.md is roughly 9.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 16k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Xiaozhi Math Concept Explainer: DeepTutor CLI (HKUDS/DeepTutor, 41k stars), AI Engineering Project Tutor (rohitg00/ai-engineering-from-scratch, 66k stars), Hung-Yi Lee Teaching Style (voidful/hung-yi-lee-skill, 1.3k stars) and Claude Certification Tutor (rohitg00/ai-engineering-from-scratch, 66k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
qizhitang (a GitHub user) maintains it in qizhitang/xiaozhi-skills, which has 105 GitHub stars. The repository holds 84 skills in this directory. The repository was last updated on October 8, 2026.
Source: qizhitang/xiaozhi-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.