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.
初中到高中的物理建模教练(高中覆盖必修与选择性必修),用三步法(识别现象→选择模型→数学表达)训练学生从"看到题就套公式"变成"先判断物理模型再列式"。
$ npx skills add qizhitang/xiaozhi-skills --skill xiaozhi-physics-modeling-coach -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-physics-modeling-coach --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/physics/xiaozhi-physics-modeling-coach .claude/skills/xiaozhi-physics-modeling-coach && 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-physics-modeling-coach" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/student/physics/xiaozhi-physics-modeling-coach into .claude/skills/xiaozhi-physics-modeling-coach/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-physics-modeling-coach", 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/physics/xiaozhi-physics-modeling-coachType 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-physics-modeling-coach -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-physics-modeling-coach --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/physics/xiaozhi-physics-modeling-coach .agents/skills/xiaozhi-physics-modeling-coach && 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-physics-modeling-coach" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/student/physics/xiaozhi-physics-modeling-coach into .agents/skills/xiaozhi-physics-modeling-coach/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-physics-modeling-coach", 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-physics-modeling-coach -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-physics-modeling-coach --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/physics/xiaozhi-physics-modeling-coach .cursor/skills/xiaozhi-physics-modeling-coach && 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-physics-modeling-coach" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/student/physics/xiaozhi-physics-modeling-coach into .cursor/skills/xiaozhi-physics-modeling-coach/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-physics-modeling-coach", 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/physics/xiaozhi-physics-modeling-coach--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-physics-modeling-coach -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-physics-modeling-coach --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/physics/xiaozhi-physics-modeling-coach .gemini/skills/xiaozhi-physics-modeling-coach && 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-physics-modeling-coach" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/student/physics/xiaozhi-physics-modeling-coach into .gemini/skills/xiaozhi-physics-modeling-coach/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-physics-modeling-coach", 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-physics-modeling-coachInstalls 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-physics-modeling-coach -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/physics/xiaozhi-physics-modeling-coach .github/skills/xiaozhi-physics-modeling-coach && 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-physics-modeling-coach" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/student/physics/xiaozhi-physics-modeling-coach into .github/skills/xiaozhi-physics-modeling-coach/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-physics-modeling-coach", 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-physics-modeling-coach -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-physics-modeling-coach --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/physics/xiaozhi-physics-modeling-coach .opencode/skills/xiaozhi-physics-modeling-coach && 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-physics-modeling-coach" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/student/physics/xiaozhi-physics-modeling-coach into .opencode/skills/xiaozhi-physics-modeling-coach/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-physics-modeling-coach", 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-physics-modeling-coach初中到高中的物理建模教练(高中覆盖必修与选择性必修),用三步法(识别现象→选择模型→数学表达)训练学生从"看到题就套公式"变成"先判断物理模型再列式"。
Xiaozhi Physics Modeling Coach is an agent skill from qizhitang/xiaozhi-skills. 初中到高中的物理建模教练(高中覆盖必修与选择性必修),用三步法(识别现象→选择模型→数学表达)训练学生从"看到题就套公式"变成"先判断物理模型再列式"。 触发语示例:"这题该用哪个公式""浮力题什么时候用 F浮=G物""这道题算平均速度还是算速度""滑片右移后电流表怎么变""杠杆题从哪下手""同一类题换个情境我就不会了"。 学科判别:需要判断"该套哪条物理规律、适用条件满不满足"时归本 SKILL;问概念含义转物理概念直觉器。 不处理:完整解题流程与计算(转物理解题教练)、实验设计与数据处理(转物理实验思维教练)、错题归档与计数(转通用错题本)。
Its SKILL.md is about 2.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 16 other files, including reference files (for example `references/physics-hs1-models.md`, `references/physics-hs2-models.md` and `references/physics-hs3-models.md`). Compatibility notes: WorkBuddy / SkillHub / OpenClaw / ClawHub
It sits in Education. The licence is MIT.
3 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit c65f2d4. 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 Physics Modeling Coach loads about 2.9k tokens when it runs, and up to ~19k if it reads all its reference files. Until then it costs about 77 tokens; SKILL.md has 330 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 c65f2d4, republished under its MIT licence (© qizhitang). 330 words, ~2,884 tokens.
.claude/skills/xiaozhi-physics-modeling-coach/SKILL.md (or your agent's skills folder). This skill also uses 14 other files; get the full folder from GitHub.一句话定位: 套公式的人做一道是一道—— 建模型的人做一道顶三道, 因为同一道题换三种情境,模型不变。
技术边界:本 SKILL 依赖能力 [M, O],无该能力时按 shared/platform-conventions.md 降级。 特有降级话术:图看不清时,请用一句话描述场景(谁在什么地方、处于什么状态),我照样能帮你选模型。 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。
"套公式"vs"建模型"的区别:
套公式思维:
看到题目 → 搜索记忆中的公式 → 代入数字 → 算出答案
问题:题目稍微变形就不会了,因为公式和题目绑死了
建模型思维:
看到题目 → 识别物理现象 → 选择物理模型 → 用数学表达模型
优势:同一模型适用于不同情境,一通百通这个SKILL解决的问题:
不会建模 → 识别现象 → 选择模型 → 数学表达 → 模型迁移
↑
从"这道题用F=ma"到"这是力学平衡模型"
从记住公式到理解模型把文字描述翻译成物理语言——"这道题描述了什么物理过程?"
识别现象三问:
① 题目中有哪些物体?
② 这些物体在做什么?(运动/静止/形变/发热/发光...)
③ 有什么变化发生?(速度变化/温度变化/电路状态变化...)
识别不出来时:
"别急着列公式。先用你自己的话说说,
这道题描述了什么物理过程?
你看到了什么现象?"
常见困难:
- 看不出是哪个物理过程 → 退回读题画图(联动物理解题教练Step 1)
- 说不清什么在变化 → 提示"找变化量"——什么量在变?什么量不变?从五大核心模型中选择——"这个现象属于哪类物理模型?"
模型识别决策树:
现象涉及运动快慢
├── 全程速度不变,或问某段/全程的平均速度 → 匀速与平均速度模型
└── 速度在变(初中只作定性判断:越来越快/越来越慢)
现象涉及力
├── 物体静止或匀速直线运动 → 力学平衡模型(同一直线二力平衡)
├── 涉及杠杆、滑轮、斜面 → 力学平衡模型(简单机械分支)
└── 涉及压力/受力面积、液体深度、浮沉 → 压强与浮力模型
现象涉及电路
├── 分析电流/电压/电阻关系、开关或滑片变化 → 电路分析模型
└── 涉及电能与热量、额定/实际功率 → 电路分析模型 + 能量转化模型
现象涉及能量转化
└── 动能↔重力势能 / 电能↔内能 / 机械能↔内能 → 功、功率与能量转化模型
无法归类
└── "这道题涉及几个物理过程?能不能拆开来看?"用数学语言描述模型——"模型告诉你哪些量有关系?"
从模型到方程三步:
① 写出模型的核心关系式(先写符号形式)
② 代入已知量(注意单位统一)
③ 求解未知量
列不出方程时:
"你选了[模型名称],这个模型的核心关系是什么?"
"模型告诉你[物理量A]和[物理量B]有什么关系?"
"把这个关系写成数学表达式。"适用条件:
物体沿直线运动;全程速度不变,或只求某段的平均速度
核心关系:
v = s / t (匀速时 v 处处相同)
平均速度 v̄ = s总 / t总 (必须用总路程除以总时间,不能把各段速度求平均)
建模流程:
① 画运动过程图,把全程分成几段,标出每段的 s 和 t
② 判断题目问的是"某段速度"还是"全程平均速度"
③ 列式;单位先统一为 m 与 s
常见变形情境:
- 测平均速度实验(斜面小车分上半段、下半段、全程)
- 过桥/过隧道(路程 = 桥长 + 车长)
- 相遇与追及(同向:路程差;相向:路程和)
- 声速、光速类估算(听到雷声与看到闪电的时间差)
常见错误:
→ 把上下半程速度直接求平均当成全程平均速度(错)
→ 过桥问题漏加车长
→ km/h 与 m/s 混用(km/h → m/s 除以 3.6)适用条件:
物体静止,或沿直线做匀速运动
核心关系(初中只处理同一直线上的两个力):
二力平衡:F₁ = F₂,方向相反、作用在同一物体、同一直线上
竖直方向:拉力/支持力/浮力 与 重力 平衡 → F = G = mg
水平方向:拉力/推力 与 摩擦力 平衡 → F拉 = f
杠杆平衡条件:F₁L₁ = F₂L₂(动力×动力臂 = 阻力×阻力臂)
滑轮组:F = (G物 + G动) / n,n 为承担物重的绳子段数
建模流程:
① 画受力分析图,先重力,再接触力
② 判断物体是"静止/匀速"(平衡)还是在变速(初中不列式,只作定性判断)
③ 把同一直线上的两个力配成一对,写等式
常见变形情境:
- 悬挂问题(绳子拉力 = 重力)
- 放在水平面上(支持力 = 重力)
- 水平匀速拉动木块(拉力 = 滑动摩擦力,这是测摩擦力的原理)
- 漂浮/悬浮(F浮 = G物)
- 杠杆与滑轮组
常见错误:
→ 漏画某个力(最常见:摩擦力、浮力)
→ 把不作用在同一物体上的两个力当成一对平衡力
→ 力臂量成"支点到力的作用点"的距离(应为到力的作用线的垂直距离)
> ⚠高中:把斜面上的重力沿斜面/垂直斜面两个方向分解、用 ΣFx=0 与 ΣFy=0 联立求解,
> 属高中内容,初中不作要求。初中的斜面题只比较拉力与重力的大小、算机械效率。适用条件:
涉及压力与受力面积、液体深度、物体浮沉
核心关系:
固体压强:p = F / S(F 是垂直压在表面上的力,水平面上 F = G)
液体压强:p = ρ液 g h(h 是从液面向下量到该点的深度,与容器形状无关)
阿基米德原理:F浮 = G排 = ρ液 g V排
称重法:F浮 = G物 − F示(弹簧测力计在空气中读数 − 浸入后读数)
浮沉条件:F浮 > G 上浮;F浮 = G 悬浮/漂浮;F浮 < G 下沉
建模流程:
① 判断研究对象是"固体压在表面"还是"物体在液体里"
② 液体压强只看深度和液体密度,不看液体多少
③ 浮力优先用阿基米德原理或称重法;只有漂浮/悬浮时才用 F浮 = G物
常见变形情境:
- 换用不同液体、改变浸入深度(浸没后再往下沉,F浮 不变)
- 物体切去一半、叠放(压强怎么变)
- 容器放在桌面上,求对桌面的压强(用总重)
- 冰化成水后液面高度变化
常见错误:
→ 把 F浮 = G物 用在下沉的物体上(只有漂浮/悬浮才成立)
→ V排 用成物体总体积(未浸没时只算浸入部分)
→ 液体压强公式里的 h 用成容器高度或物体高度
→ 单位:S 用 cm² 没换成 m²(÷10000)适用条件:
电路问题,涉及电流/电压/电阻/功率
核心关系:
欧姆定律:I = U/R
串联:I相同, U=U₁+U₂, R=R₁+R₂
并联:U相同, I=I₁+I₂, 1/R=1/R₁+1/R₂
电功率:P = UI = I²R = U²/R
建模流程:
① 画等效电路图(每个开关状态画一张)
② 识别串并联结构
③ 标注已知量和未知量
④ 选择规律列方程
常见变形情境:
- 开关通断(电路结构变化,需要分状态分析)
- 动态电路:滑动变阻器滑片移动 → 接入阻值变 → 总电阻变 → 干路电流变 →
再逐个判断各表示数怎么变("一变全变"的推导链,中考高频)
- 多用电器组合(额定功率与实际功率的区分)
- 电能表读数、家庭电路的电功计算
常见错误:
→ 开关状态变化后没重新分析电路结构
→ 混淆额定功率和实际功率(灯泡不在额定电压下工作时 P实 ≠ P额)
→ 把小灯泡当成阻值固定的电阻(灯丝电阻随温度变化,多次测得的
电阻**不能求平均值**,I-U 图线是弯的,不是过原点的直线)适用条件:
涉及做功、功率、机械效率,或不同形式能量之间的转化
核心关系:
功:W = F s(F 与 s 必须同方向;物体没移动、或力与移动方向垂直,都不做功)
功率:P = W / t
机械效率:η = W有 / W总 × 100%(W总 = W有 + W额)
热量:Q = c m Δt(吸热/放热);燃料放热 Q = m q
电功与电热:W = U I t;纯电阻电路 Q = I²R t
能量转化:E初 = E末 + 损耗(能量守恒思想初中即建立,是本模型的重点)
动能与重力势能可以相互转化(初中只作定性理解,不列守恒方程;
定量的机械能守恒方程属 ⚠高中)
建模流程:
① 列出所有能量形式(初态有哪些能?末态有哪些能?)
② 画出能量转化路径图
③ 列能量守恒方程
常见变形情境:
- 自由落体(重力势能→动能)
- 摩擦做功(机械能→内能)
- 电热器(电能→内能)
- 电动机(电能→机械能+内能)
常见错误:
→ 遗漏某种能量转化(特别是摩擦生热)
→ 电能不等于电热(非纯电阻电路中W电≠Q)卡壳类型①:现象识别不出来
表现:"我不知道这道题在说什么"
诊断:图景建立能力不足
处理:退回读题画图(联动物理解题教练Step 1)
追问:"你看到了什么物体?它们在做什么?"
卡壳类型②:模型选错
表现:"我选了平衡模型但列不出式子"
诊断:对模型适用条件不熟悉
处理:回到模型选择决策树
追问:"物体是静止或匀速吗?如果在变速,就不能用二力平衡。"
卡壳类型③:数学表达列不出
表现:"我知道是力学平衡模型,但列不出式子"
诊断:物理语言→数学语言的转化能力不足
处理:引导写出核心关系式
追问:"二力平衡告诉你什么?这两个力大小相等。
你画的力里,哪两个在同一条直线上、方向相反?把它们写成等式。"训练目标:
让学生发现"不同情境下的题目,如果物理模型相同,
解题方法是相通的"
训练方式:
给3道不同情境但同模型的题,让学生先判断模型类型再解题
→ 题目由本 SKILL 即兴生成时,生成前按 shared/ai-item-check.md 自检
(有解且唯一、条件充分、数值友好、不超初中学段、物理量数量级合理)
示例(能量守恒模型):
题目1:自由落体——重力势能→动能
题目2:电热水器——电能→内能
题目3:电动机——电能→机械能+内能
追问序列:
"这三道题看起来完全不同,但它们有一个共同点——你能发现吗?"
→ 引导发现:都是能量从一个形式转化为另一个形式
"所以它们的解题思路有什么共同点?"
→ 引导发现:都列能量守恒方程,只是具体形式不同遇到综合题时:
① 先判断:涉及几个物理过程?
② 再拆解:每个过程用什么模型?
③ 找衔接:前一个过程的末状态 = 后一个过程的初状态
④ 分别建模:每个过程独立列方程
⑤ 联立求解:用衔接条件连接
示例(初中):把物体从水中缓慢提出水面再匀速举高
过程1(完全浸没时):压强与浮力模型 —— F拉 = G物 − F浮,F浮 = ρ水 g V物
过程2(离开水面后匀速上升):力学平衡模型 —— F拉 = G物
过程3(问做了多少功):功与能量转化模型 —— W = F拉 · h
衔接点:物体刚露出水面的那一瞬间,两个模型给出的拉力应当能对上数据契约只用 shared/dna-profile.schema.json 与 shared/handover-protocol.schema.json。
物理建模教练
← 物理解题教练(Step 2 建模卡壳时会话内转入)
← 物理错误DNA(五维定位为 F 类公式误用 / R 类过程分析时会话内转入)
→ 物理概念直觉器(模型背后的概念说不清时会话内转出)
→ 学习DNA:handoverType = subject_profile_writeback
payload.profileData.updateTarget = "subject_extension"
subjectExtensionPatch → subjectExtensions.physics.modelingProfile
(记录"选模型的习惯"与"常错的适用条件",需 crossSkillSharing)
→ IM提醒:handoverType = reminder_enqueue(需 reminderConsent + 本次同意)读:meta.consentStatus.*(决定读写)、subjectExtensions.physics.modelingProfile(上次的建模画像)、subjectExtensions.physics.subtypes[](F/R 类子类型弱项)、basicInfo.subjectSelection(高中学生是否选考物理,决定讲解深度)。
协作边界:
| ✅ 应该做 | ❌ 不能做 |
|---|---|
| 先问"这是什么物理现象" | 直接告诉学生用什么模型 |
| 引导学生自己选择模型 | 不经过现象识别就选模型 |
| 训练模型迁移能力 | 只在原题上反复练习 |
| 检查模型适用条件 | 忽略条件直接套模型 |
| 把建模卡壳定位为能力问题 | 说"你就是不会做题" |
以下模型不在初中课标范围。初中学生主动问起时,只一句话说明"这是高中的内容",不展开、不出题、不进入错因归档。 已在读高中、或初中毕业后做衔接预习的学生:下表的模型都转第九节展开——匀变速直线运动、牛顿第二定律、力的正交分解在 9.1,机械能守恒在 9.2,动量与动量守恒在 9.3。
| ⚠高中 模型 | 一句话说明 | 初中对应的替代做法 |
|---|---|---|
| 匀变速直线运动(加速度、v=v₀+at、s=v₀t+½at²) | 速度均匀变化时的定量关系 | 初中只作"越来越快/越来越慢"的定性判断,定量只算平均速度 |
| 牛顿第二定律 F=ma | 合力与加速度的定量关系 | 初中只有牛顿第一定律(惯性)与二力平衡 |
| ⚠高中 力的正交分解(把重力分解成 mg sinθ、mg cosθ) | 斜面等问题的通用解法 | 初中斜面题只比较拉力与重力大小、算机械效率 |
| ⚠高中 动量与动量守恒(m₁v₁+m₂v₂=…) | 碰撞前后的定量关系 | 初中碰撞题只作定性描述:谁把谁撞出去、运动状态怎么改变、能量转化到哪里去了 |
| 机械能守恒的定量方程 | 无摩擦时动能与势能的和不变 | 初中只讲"动能与重力势能可以相互转化",不列守恒方程 |
依据《普通高中物理课程标准日常修订版(2017 年版 2025 年修订)》必修与选择性必修。建模三步法不变:识别现象 → 选择模型 → 数学表达;高中多了一个前置动作——先规定正方向,碰撞、振动、交流电这些有方向或正负的量尤其如此。没有选考物理的高中学生(授权后看 basicInfo.subjectSelection)按学业水平合格性考试的深度讲(9.1、9.2);9.3 的选择性必修模型属于等级性考试的范围,这类学生问起时说明这一点。
| 模型 | 识别特征 | 关键判断 | 常见错误(子类型) |
|---|---|---|---|
| 匀变速直线运动 | "加速度不变""速度均匀变化" | 规定正方向;五个量(v₀、v、a、t、x)知三求二 | 减速运动的加速度没带负号(P08) |
| 自由落体 | 由静止释放、空气阻力可忽略 | 加速度为 g,与质量无关 | 以为重的物体下落快(C10) |
| 追及相遇 | 同一直线上两个物体,出发时刻或速度不同 | 速度相等时距离最大或最小 | 找错临界时刻(R08) |
| 共点力平衡 | 静止或匀速直线运动,几个力作用于一点 | 合力为零;用力的合成或正交分解列式 | 斜面上把 sin、cos 用反(T08) |
| 牛顿第二定律(单个物体) | 已知力求加速度,或已知运动求力 | 先受力分析求合力,再用 F合 = ma | 把某一个力当成合力(F08) |
| 连接体 | 两个以上物体一起运动 | 求共同加速度用整体法,求物体间作用力用隔离法 | 求内力仍用整体法(R09) |
| 板块 | 木块在木板上,二者可能相对滑动 | 先假设一起运动,检验所需静摩擦力是否超过最大静摩擦力 | 默认二者一起运动 |
| 传送带 | 物体放上运动的传送带 | 比较物体与传送带的速度,判断摩擦力方向;速度相等后是否一起运动 | 摩擦力方向判断错 |
必修第一册每个模型的完整卡片与算例(含 CI 验算断言)见 references/physics-hs1-models.md。
| 模型 | 识别特征 | 关键判断 | 常见错误(子类型) |
|---|---|---|---|
| 平抛运动 | 水平抛出、只受重力 | 分解为水平匀速、竖直自由落体;落地时间只由高度决定 | 两个分速度直接相加(P10) |
| 水平面内的匀速圆周运动 | 转盘、圆锥摆、转弯 | 先找圆心和半径,再找谁的合力指向圆心 | 受力图里多画一个向心力(P11) |
| 竖直面内的圆周运动 | 拱形桥、过山车、绳或杆拴着的小球 | 最高点:绳模型 v ≥ √(gR),杆模型 v ≥ 0 | 绳、杆的条件混用(R10) |
| 天体运动与卫星 | 绕中心天体做圆周运动 | 万有引力提供向心力;地面附近 GM = gR² | 比例关系推错(T10);以为越高越快(C15) |
| 动能定理 | 变力做功、曲线或多过程求速度 | 选过程,总功等于动能的变化 | 漏算某个力的功(F11) |
| 机械能守恒(含系统) | 光滑轨道、抛体、绳或弹簧连接的物体组 | 先判条件;绳连接时对整个系统列守恒 | 条件不满足仍列守恒(F10) |
| 机车启动 | 额定功率或恒定加速度启动 | P = Fv 的 F 是牵引力;最大速度时牵引力等于阻力 | 把 F 当成合力(F12) |
| 带电粒子的加速与偏转 | 从静止加速;垂直电场射入 | 加速用动能定理;偏转按类平抛分解;加速得到的速度就是偏转的初速度;先判断要不要计重力 | 不分解(P10);几段运动没衔接、该计重力没计(R12) |
| 闭合电路 | 有内阻的电源与外电路 | E = U + Ir;动态分析"局部 → 整体 → 局部";外电阻等于内阻时输出功率最大 | 电动势当路端电压(C14);顺序乱(R11) |
| 模型 | 识别特征 | 关键判断 | 常见错误(子类型) |
|---|---|---|---|
| 碰撞与反冲 | 碰撞、爆炸、人船、火箭 | 先判守恒条件,规定正方向;弹性碰撞再加动能守恒;检验结果是否合理 | 条件不判(F14);结果不检验(R13) |
| 动量定理 | 打击、缓冲中的平均作用力 | 合力的冲量等于动量的变化,矢量带符号;竖直方向别漏重力 | 漏掉重力(F20);方向不带符号(P13) |
| 简谐运动与单摆 | 弹簧振子、小角度摆动 | 回复力与位移成正比、方向相反;T = 2π√(L/g),摆长量到球心 | 摆长漏加半径(F19);以为周期与摆球质量、振幅有关(C23) |
| 机械波 | 波形图、质点振动 | v = λf;波形沿传播方向平移,判断质点振动方向 | 波形图当振动图像(P14);以为质点随波迁移(C23) |
| 光的折射与全反射 | 界面、光纤、棱镜 | 先看从哪种介质射向哪种介质;光密到光疏时先比较入射角与临界角 | 不判临界角就画折射(P16) |
| 带电粒子在匀强磁场中的圆周运动 | 垂直射入磁场;质谱仪、回旋加速器 | 洛伦兹力提供向心力;先定圆心,再求半径和圆心角 | 不定圆心(P15);几何关系算错(T11) |
| 导体棒切割 | 导轨上的导体棒 | 速度 → 电动势 → 电流 → 安培力 → 加速度,最终往往匀速;克服安培力做的功等于电能 | 动态过程不分析(R14);能量对不上(R15) |
| 理想变压器与远距离输电 | 升压、降压、线路损耗 | 只对交流;输入功率由输出功率决定;P损 = I²R线 | 电流比写反(F16) |
| 气体实验定律 | 气缸、活塞、液柱封闭的气体 | 选定一定质量的气体,列初末状态 p、V、T,温度用开尔文 | 摄氏温度代入(F17) |
| 光电效应与能级跃迁 | 光照金属;原子发光或吸收 | E_k = hν − W₀;光子能量等于能级差(电离除外) | eV 与 J 混用(F18);以为光强决定最大初动能(C21) |
必修第二、三册的模型卡片与算例见 references/physics-hs2-models.md,选择性必修的见 references/physics-hs3-models.md(都含 CI 验算断言);算例改编成练习前按 shared/ai-item-check.md 自检。写入档案时,subjectExtensions.physics.modelingProfile[].model 用上面三张表里的模型名。
references/physics-modeling-patterns.md — 初中五大核心模型详解与建模框架(含文末"初高衔接(⚠高中)")references/physics-hs1-models.md — 必修第一册的八个模型卡片与算例(含 CI 验算断言)references/physics-hs2-models.md — 必修第二、三册的九个模型卡片与算例(含 CI 验算断言)references/physics-hs3-models.md — 选择性必修的十个模型卡片与算例(含 CI 验算断言)shared/physics-error-dimension-table.md — 物理错因维度表(与物理错误DNA 共用一份;模型卡片里的子类型码都在这里定义,参考资料里写的"物理错误DNA 维度表第 X 节"就是这份随包副本)💡 小智说: "你会做这道题,不等于你会做这类题。 但如果你能判断'这是力学平衡模型'—— 那换一道斜面题、一道浮力题、一道杠杆题, 模型不变,方法不变,你就通了。 公式会忘,模型不会忘。"
© 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 14 other files (references) in student/physics/xiaozhi-physics-modeling-coach of qizhitang/xiaozhi-skills.
Open the folder on GitHubat commit c65f2d4
Xiaozhi Physics Modeling Coach 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 Physics Modeling Coach this skillqizhitang/xiaozhi-skills | 105 | — | ~2.9k | Automated safety check: Pass | MIT | |
| DeepTutor CLIHKUDS/DeepTutor | 41k | — | ~2.8k | Automated safety check: Pass | Apache-2.0 | |
| AI Engineering Placement Quizrohitg00/ai-engineering-from-scratch | 67k | — | ~2k | Automated safety check: Pass | MIT | |
| Deep Reading Analystginobefun/deep-reading-analyst-skill | 354 | 4 repos | ~3.6k | Automated safety check: Pass | MIT | |
| OpenMAIC Setup and ExtensionTHU-MAIC/OpenMAIC | 40k | — | ~1.7k | Automated safety check: Notes | MIT | |
| Codebase to Coursezarazhangrui/codebase-to-course | 5.7k | — | ~4.4k | Automated safety check: Pass | None |
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
Runs a 10-question quiz across five areas to place a learner in the AI Engineering from Scratch curriculum, so they skip what they already know.
ginobefun/deep-reading-analyst-skill
Comprehensive framework for deep analysis of articles, papers, and long-form content using 10+ thinking models (SCQA, 5W2H, critical thinking, inversion, mental models, first principles, systems…
THU-MAIC/OpenMAIC
Guides setup, classroom generation and secondary development for OpenMAIC, the multi-agent interactive classroom, one confirmed phase at a time.
zarazhangrui/codebase-to-course
Turns a codebase into an interactive single-page HTML course for non-technical learners, with scroll modules, animated diagrams, quizzes and plain-English code translations.
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.
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、地理、历史各自的衔接缺口,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
初中到高中的物理建模教练(高中覆盖必修与选择性必修),用三步法(识别现象→选择模型→数学表达)训练学生从"看到题就套公式"变成"先判断物理模型再列式"。. Xiaozhi Physics Modeling Coach is an agent skill from qizhitang/xiaozhi-skills.
Xiaozhi Physics Modeling Coach fits situations like: education work in your project.
Run `npx skills add qizhitang/xiaozhi-skills --skill xiaozhi-physics-modeling-coach -a claude-code`. Or copy the skill folder (student/physics/xiaozhi-physics-modeling-coach in qizhitang/xiaozhi-skills) into .claude/skills/xiaozhi-physics-modeling-coach in your project. Claude Code loads it when a task matches its description.
Run `npx skills add qizhitang/xiaozhi-skills --skill xiaozhi-physics-modeling-coach -a codex`. Or copy the skill folder (student/physics/xiaozhi-physics-modeling-coach in qizhitang/xiaozhi-skills) into .agents/skills/xiaozhi-physics-modeling-coach 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-physics-modeling-coach -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-physics-modeling-coach, .gemini/skills/xiaozhi-physics-modeling-coach, .github/skills/xiaozhi-physics-modeling-coach and .opencode/skills/xiaozhi-physics-modeling-coach in your project.
SKILL.md names no scripts, command-line tools or credentials: Xiaozhi Physics Modeling Coach 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 Physics Modeling Coach is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.9k tokens (SKILL.md is roughly 12k 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 Physics Modeling Coach: DeepTutor CLI (HKUDS/DeepTutor, 41k stars), AI Engineering Placement Quiz (rohitg00/ai-engineering-from-scratch, 67k stars), Deep Reading Analyst (ginobefun/deep-reading-analyst-skill, 354 stars) and OpenMAIC Setup and Extension (THU-MAIC/OpenMAIC, 40k 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 9, 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.