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.
把"单向讲授"变成有追问、有参与路径的课堂. An agent skill from qizhitang/xiaozhi-skills.
$ npx skills add qizhitang/xiaozhi-skills --skill xiaozhi-teach-classroom-coach -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-teach-classroom-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/teacher/general/xiaozhi-teach-classroom-coach .claude/skills/xiaozhi-teach-classroom-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-teach-classroom-coach" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/teacher/general/xiaozhi-teach-classroom-coach into .claude/skills/xiaozhi-teach-classroom-coach/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-teach-classroom-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/teacher/general/xiaozhi-teach-classroom-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-teach-classroom-coach -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-teach-classroom-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/teacher/general/xiaozhi-teach-classroom-coach .agents/skills/xiaozhi-teach-classroom-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-teach-classroom-coach" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/teacher/general/xiaozhi-teach-classroom-coach into .agents/skills/xiaozhi-teach-classroom-coach/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-teach-classroom-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-teach-classroom-coach -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-teach-classroom-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/teacher/general/xiaozhi-teach-classroom-coach .cursor/skills/xiaozhi-teach-classroom-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-teach-classroom-coach" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/teacher/general/xiaozhi-teach-classroom-coach into .cursor/skills/xiaozhi-teach-classroom-coach/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-teach-classroom-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 teacher/general/xiaozhi-teach-classroom-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-teach-classroom-coach -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-teach-classroom-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/teacher/general/xiaozhi-teach-classroom-coach .gemini/skills/xiaozhi-teach-classroom-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-teach-classroom-coach" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/teacher/general/xiaozhi-teach-classroom-coach into .gemini/skills/xiaozhi-teach-classroom-coach/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-teach-classroom-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-teach-classroom-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-teach-classroom-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/teacher/general/xiaozhi-teach-classroom-coach .github/skills/xiaozhi-teach-classroom-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-teach-classroom-coach" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/teacher/general/xiaozhi-teach-classroom-coach into .github/skills/xiaozhi-teach-classroom-coach/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-teach-classroom-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-teach-classroom-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-teach-classroom-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/teacher/general/xiaozhi-teach-classroom-coach .opencode/skills/xiaozhi-teach-classroom-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-teach-classroom-coach" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/teacher/general/xiaozhi-teach-classroom-coach into .opencode/skills/xiaozhi-teach-classroom-coach/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-teach-classroom-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-teach-classroom-coach把"单向讲授"变成有追问、有参与路径的课堂. An agent skill from qizhitang/xiaozhi-skills.
Xiaozhi Teach Classroom Coach is an agent skill from qizhitang/xiaozhi-skills. 把"单向讲授"变成有追问、有参与路径的课堂。 当老师说"这节课怎么互动"、"学生答不上来怎么追问"、"数学课冷场了怎么办"、"小组活动怎么分组、几分钟汇报"、"怎么让基础薄弱的学生也敢开口"、"高二走班的教学班,小组怎么分"时,建议激活此 SKILL。 工作流:读目标与分层 → 候场追问 → 小组活动与计时 → 冷场应对 → 课后观察记录。 本 SKILL 不写教案、不出题、不算学情:教案与提问链草案由 xiaozhi-teach-lesson-planner 出,命题转 xiaozhi-teach-exam-designer,学情统计转 xiaozhi-teach-student-analyzer。初中、高中实验课的分组、器材与安全组织转学科技能。
Its SKILL.md is about 4.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 13 other files, including reference files (for example `references/group-task-card-and-scripts.md`, `references/post-class-record-template.md` and `references/questioning-strategies.md`). Compatibility notes: WorkBuddy / SkillHub / OpenClaw / ClawHub
It sits in Education. The licence is MIT.
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 Teach Classroom Coach loads about 4.5k tokens when it runs, and up to ~7.7k if it reads all its reference files. Until then it costs about 90 tokens; SKILL.md has 409 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). 409 words, ~4,538 tokens.
.claude/skills/xiaozhi-teach-classroom-coach/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: 好课堂不是老师讲得好,而是学生想得深——互动设计是关键。
技术边界:本 SKILL 依赖能力 [M, C],无该能力时按
shared/platform-conventions.md降级。 特有降级:无C(精确计时)时,小组活动的计时由老师或计时员用教室的钟表执行,本 SKILL 只给出时长建议; 本 SKILL 没有课堂录音/录像/语音分析能力,课堂观察由老师在课后 5 分钟内补录。
教学主体边界:本 SKILL 只给老师出草稿、做分析,不替老师上课,不代老师回答学生的问题,也不代老师评价学生;面向学生或家长的内容,一律由老师审定后再用(教育部《中小学生成式人工智能使用指南(2025 年版)》)。
内容边界:道德与法治、思想政治只给讨论与互动的组织方法,不生成政治论点、点评或辩驳稿;议题从教材与课标取,时政材料由老师从权威来源选取并注明来源与日期,本 SKILL 不检索、不点评时事;不设以政治立场为正反方的辩论;课堂记录只记"讨论偏离教材"这类事实,不记学生的观点(原话、转述都不记),也不评价学生的政治观点。历史、地理课的讨论与辩论不以版图领土、民族、宗教、中国共产党历史与新中国史的评价、战争性质为正反方议题,按课标与教材的表述组织(高中见 4.2)。
⚠️ 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。
输入:读 classWorkspace.lessonPlans(本节课目标与提问链草案)、classWorkspace.studentTiers(分层)、
classWorkspace.classProfile(班额与课时长度)。缺其中任一项时输出"通用版互动模板",并说明缺什么、补上会更准。
叫学生发言的边界:本 SKILL 输出的冷场应对与参与路径仅供老师参考;点谁、什么时候点,由老师决定,AI 不替老师点名。心理健康、减压类主题课(班会、心理课)的分享用匿名、可以不参加的方式,不点名,不安排学生当众讲述自己的心理困扰、家庭情况或创伤经历,课后记录不写学生分享的内容与心理状况;出现危机信号按上面的危机例外处置。
不出题:课堂练习题请转 xiaozhi-teach-exam-designer 或学科教师端 SKILL。课上临时需要一道更简单的例子说明概念时,
生成前按 shared/ai-item-check.md 自检,口头使用即可,不入库;若要入库须标注【AI 生成,入库前请人工验算】。
课堂互动的三个常见误区:
误区① 满堂灌:把"讲清楚"当作教学目标,
实际学生只是"听了",没有"想"。
误区② 表面热闹:满堂问"对不对""是不是",
学生只需要点头,没有思维深度。
误区③ 冷场尴尬:抛出好问题后无人回应,
老师要么自问自答,要么换简单的,
真正的好问题被错过。本 SKILL 要解决的是:
| 触发场景 | 示例语句 |
|---|---|
| 互动设计 | "这节课怎么互动" / "如何让学生主动思考" |
| 提问设计 | "帮我设计课堂提问" |
| 学生不发言 | "学生不发言怎么办" / "课堂冷场" |
| 小组活动 | "怎么分组" / "小组合作怎么设计" |
| 沉闷课堂 | "这节课太沉闷" / "活跃度低" |
| 主动发言 | "怎么让基础学生也敢发言" |
| 反馈机制 | "如何让学生知道自己答得对不对" |
| 候场追问 | "学生答不上来怎么办" |
| 课后记录 | "课后 5 分钟记点什么" |
| 高中课堂 | "高二走班的教学班,小组怎么分" / "政治课讨论跑偏了怎么拉回来"(见 4.2) |
本 SKILL 不接的相邻请求:
| 老师说 | 转给 |
|---|---|
| "帮我写这节课的教案 / 排环节时间 / 出提问链" | xiaozhi-teach-lesson-planner(出草案),本 SKILL 接着做候场追问与实施 |
| "出一道课堂练习题 / 变式题" | xiaozhi-teach-exam-designer 或学科教师端 SKILL |
| "算一下这次的得分率、谁该分到哪一层" | xiaozhi-teach-student-analyzer |
| "课后作业怎么留" | xiaozhi-teach-assignment-designer |
| 初中、高中的"实验课 40 个人 8 套器材怎么分组" / 实验的器材与安全组织 | 物理实验教学指导、化学实验教学指导;生物学生实验转生物教案设计(见 4.2 的转交表);小学科学课的分组仍由本 SKILL 按 §6.1 给通用方法,器材与安全由任课老师按学校规程定 |
┌──────────────────────────┐
│ ① 输入确认 │
│ 教学目标/学情/班级规模 │
└────────────┬─────────────┘
↓
┌──────────────────────────┐
│ ② 互动模式选择 │
│ 全班/小组/同桌/独立 │
└────────────┬─────────────┘
↓
┌──────────────────────────┐
│ ③ Bloom 分层提问链设计 │
│ 6-8 问,候场追问 1-2 │
└────────────┬─────────────┘
↓
┌──────────────────────────┐
│ ④ 小组合作活动设计 │
│ 角色/规则/计时/汇报 │
└────────────┬─────────────┘
↓
┌──────────────────────────┐
│ ⑤ 冷场应对与候场 │
│ 预设 3 种沉默情境 │
└────────────┬─────────────┘
↓
┌──────────────────────────┐
│ ⑥ 即时反馈机制 │
│ 集体反馈/同伴互评/教师 │
└────────────┬─────────────┘
↓
┌──────────────────────────┐
│ ⑦ 课后观察记录回写 │
│ → student-analyzer │
└──────────────────────────┘┌────────┬────────────────────────┬────────────┬──────────────┐
│ 模式 │ 适用场景 │ 持续时间 │ 思维深度 │
├────────┼────────────────────────┼────────────┼──────────────┤
│ 全班互动│ 关键概念建构/复习 │ 5-10 分钟 │ 中-深 │
│ 小组合作│ 综合应用/探究任务 │ 10-20 分钟 │ 深 │
│ 同桌互讲│ 概念辨析/复述 │ 3-5 分钟 │ 中 │
│ 独立思考│ 难题/迁移题/开放题 │ 3-8 分钟 │ 深 │
└────────┴────────────────────────┴────────────┴──────────────┘下面按 classProfile.periodMinutes = 45(初中基线)给出;
小学 40 分钟档把小组合作压到 10 分钟、独立思考压到 2-3 分钟;
高中 40 分钟档压小组合作与汇报,不压独立思考(见 4.2);
其他档位见 shared/grade-bands.md 三与 lesson-planner SKILL.md §5.1。
新授课(45 分钟):
全班互动 5min + 独立思考 3min + 小组合作 12min + 全班互动 5min
复习课(45 分钟):
同桌互讲 5min + 独立思考 5min + 小组合作 15min + 全班互动 5min
讲评课(45 分钟):
独立思考 5min + 全班互动 10min + 同桌互讲 5min
(讲哪几道题由 exam-designer 或学科测评技能的讲评错题清单决定,课时结构由 lesson-planner 或学科教案技能排)高中的互动设计先确认四件事:
① 一节课多少分钟
· 读 classProfile.periodMinutes(各地 40 或 45 分钟),读不到就先问,不默认 45
② 是不是走班的教学班
· 学生来自几个行政班、座位固定不固定——决定怎么分组
③ 这个班考哪一种
· 合格考班还是等级考班,由老师说明,不从成绩推断——
只用来定参与路径的门槛与情境,不用来分组
④ 本课的课型与教案
· 读 lessonPlans 的目标与提问链草案;讲评课先确认卷子已经考完40 分钟档压小组合作与汇报,不压独立思考:高中单次专注 25-40 分钟(shared/grade-bands.md 二),难题、迁移题真正发生在独立思考的那几分钟,不压;少掉的时间先从小组合作和汇报里出。以 §4.1 的新授课为例(经验值,按课型调整):
新授课(40 分钟):
全班互动 5min + 独立思考 3min + 小组合作 8-10min + 全班互动(含汇报)3-5min
· 汇报仍按 §6.3 先算组数;40 分钟的课少抽几组上台,其余组把结论写在任务卡上交
· 连堂 90 分钟(实验、通用技术)中段安排一次活动切换,课时伸缩表见 lesson-planner SKILL.md §5.1走班的教学班:
高中的互动形式:§四 的四种模式照用,可以补第五种"议题研讨与辩论":
思想政治课讨论的组织边界:学生说出偏激或敏感的言论、全班起哄时,本 SKILL 只给组织建议——先稳住秩序(暂停讨论,请大家回到任务上),不当众批评或嘲笑这个学生;由老师用教材原文把讨论拉回课标与教材的表述;课后私下和这个学生沟通。
本 SKILL 不生成政治论点、点评或辩驳稿。
课后记录里,interactionLogs 只写"讨论偏离教材、已拉回"这类事实,不写学生的观点原话,也不写是谁说的。
私下反馈:高中学生当众发言的顾虑更重——纠错多用私下反馈(巡视时低声提示、写在任务卡上),表扬说具体行为、不过度公开;不在课堂上评论学生的选科与名次。高三疲劳期的互动更短、更聚焦。
讲评课:联考、模拟考只讲已经考完的卷——跨校联考等参加的学校全部考完,分几天、分批进行的考试等全部批次、全部场次考完,同一份卷子还有学生补考的等补考考完再讲;讲哪几道由测评设计师或学科测评技能的讲评错题清单定;数学、物理、化学、生物学、地理、历史的讲评课整节由该学科的教案设计排(历史的答题规范讲评仍看历史命题与答题规范指导),语文、英语等其余学科的课时结构由教案设计器排(语文的作文讲评转写作教学指导)。
高中转学科技能:
| 老师要的 | 转给 |
|---|---|
| 实验课的分组、器材分配与安全组织 | 物理实验教学指导(xiaozhi-teach-physics-experiment-coach);化学实验教学指导(xiaozhi-teach-chemistry-lab-guide);生物学生实验的组织与安全定档转生物教案设计(xiaozhi-teach-biology-lesson-planner) |
| 地理野外考察、社会调查的组织 | 地理教案设计(xiaozhi-teach-geography-lesson-planner) |
| 口语课的任务与纠错;听力课 | 英语口语活动设计(xiaozhi-teach-english-speaking-designer);英语听力材料设计(xiaozhi-teach-english-listening-designer) |
| 思辨阅读、群文讨论;作文讲评课;文言文课堂 | 阅读教学指导(xiaozhi-teach-chinese-reading-guide);写作教学指导(xiaozhi-teach-chinese-writing-guide);文言文教学指导(xiaozhi-teach-chinese-classical-guide) |
| 史料研读的问题链 | 历史教案设计(xiaozhi-teach-history-lesson-planner) |
| 数学概念辨析的提问 | 数学教案设计(xiaozhi-teach-math-lesson-planner) |
| 物理讲题课的追问 | 物理解题教学指导(xiaozhi-teach-physics-problem-guide) |
| 通用的候场追问、冷场、分组与汇报、课后记录 | 本 SKILL |
没有学科技能的五科:思想政治、信息技术、通用技术、艺术、体育与健康本库没有学科技能,本 SKILL 照常给互动组织的方法,思想政治、道德与法治的边界见本 SKILL 开头的内容边界一行。本 SKILL 另守一条:体育课与室外活动的分组、口令、保护与帮助,通用技术、信息技术实践课的工位与设备安全,都由任课老师按学校规程定,本 SKILL 不写操作步骤(§6.3 的汇报流程在体育课上大多不适用);艺术课的表演影像不记录。
分工:提问链草案由
xiaozhi-teach-lesson-planner在备课时生成,写在classWorkspace.lessonPlans[].questionChain。本 SKILL 的职责是课堂实施: 给每个问题配候场追问、决定谁来答、冷场怎么办、答偏了怎么拉回来。已有草案时,§5.1 直接读草案、只做补齐与调序;没有草案时才现场生成一版, 并提示老师"这版没有教案目标做锚,建议回 lesson-planner 补一次目标"。
命名说明:按认知层级预先排出的问题序列,本质是"提问的认知梯度";真正的苏格拉底式追问 是课堂上顺着学生自己的推理即时追问、暴露矛盾(见 §5.2),二者配合:先搭台阶,再深挖。
每节课至少 6-8 个核心提问,覆盖认知层级至少 4 档。 写进教案的层级标签用课标四级(了解/理解/掌握/运用),下面的六层是备课时的思维参照。
第 1 问(记忆):让所有学生跟得上
→ "X 的定义是什么?"
第 2-3 问(理解):让基础学生解释给同桌
→ "你能用一句话给同桌解释 X 吗?"
→ "X 和 Y 有什么相同和不同?"
第 4-5 问(应用):中等学生主战场
→ "用 X 解决这个具体问题"
→ "X 在这个情境下会怎样变化?"
第 6 问(分析):让提升学生展示思维过程
→ "为什么用 A 方法而不是 B 方法?"
第 7 问(评价):拔尖学生评方案优劣
→ "这两种解法你选哪个?为什么?"
第 8 问(创造):开放性,鼓励所有学生尝试
→ "用 X 设计一个 Y 方案"每个问题必须配 1-2 个候场追问,用于冷场或答案偏浅时递进。
候场 A:从"是不是"到"为什么"
原问:y=kx+b 中 k 表示什么?
候场:k 的正负决定什么?
候场 B:边界条件探查
原问:k 是什么?
候场:如果 k=0 呢?这变成什么函数?
候场 C:迁移到生活
原问:一次函数图象是什么样子?
候场:你能举一个生活中 y=kx 的例子吗?
候场 D:让基础学生也参与
原问:X 公式的物理意义?
候场(变简单):"想象你在 [生活场景],X 是什么?"
候场 E:让拔尖学生更深入
原问:X 是怎么来的?
候场(变深):"如果 Y 变化,X 会怎么变?"每节课至少留 2-3 分钟让学生"问老师"。
不是"有没有问题",而是:
"我刚才讲的,最让你困惑的是哪一步?"
"你能用这个问题反过来考我吗?"
这种"反向提问"对中等和拔尖学生尤其有效,
能暴露老师讲解中的盲点。分层标签沿用 classWorkspace.studentTiers 的口径,不另起一套:
A = 需补基础,B = 达标,C = 可拓展(依据近 3 次测评平均得分率)。
标准规模:4 人一组(4 个人,4 个角色,一人一职)
· 1 个 C 层(可拓展)
· 2 个 B 层(达标)
· 1 个 A 层(需补基础)
当某层人数不够时,就近替补,不要为了凑结构把学生贴标签。
异质分组(最常用):
· 按 studentTiers 混合,促进互助
· 适合:综合应用、难题探究
同质分组(特定场景):
· 同一层一组
· 适合:C 层拓展 / A 层补缺
随机分组(活跃气氛):
· 抽签 / 报数 / 拼图分组
· 适合:班级气氛沉闷时主持人:组织讨论节奏(不一定是组长)
记录员:把讨论结论写在任务卡上
汇报员:向全班汇报本组结论(轮流)
计时员:监控任务进度(提醒剩余时间)
⚠️ 规则:
· 4 人组正好 4 个角色,一人一职;上一版把"记录员"额外列了一遍,
造成 4 人 5 职,实际执行时必然有人身兼两职或有人闲置。
· 5 人组:加"质疑员"(专门问"为什么");3 人组:主持人兼计时员。
· 每节课轮换不同角色,避免固定化。
· A 层学生可先担任计时员或记录员等低门槛角色,但不要长期固定在低门槛角色上。
· 不允许"组长包办",所有组员至少发言 1 次。小组汇报最容易失控的地方是:组数 × 每组时长 早就超过了这节课能给的时间。 先算清楚再定,不要拍脑袋。
第 1 步:算组数
组数 = ⌈classProfile.classSize ÷ 每组人数⌉
例:45 人 ÷ 4 = 11.25 → 12 组(不是 11 组)
第 2 步:算"全组汇报"要多久
全组汇报总时长 = 组数 × 每组汇报时长 + 组数 × 15 秒(换人、走位的碎时间)
例:12 组 × 1 分钟 + 12 × 15 秒 = 15 分钟 —— 一节 45 分钟的课放不下
第 3 步:按班额选汇报方式
┌─────────────┬──────────────────────────────────────────┐
│ 组数 ≤ 6 │ 全组汇报,每组 1.5-2 分钟 │
│ (班额≤24) │ 总计 ≈ 10-13 分钟 │
├─────────────┼──────────────────────────────────────────┤
│ 组数 7-10 │ 抽 3-4 组汇报(每组 1.5 分钟), │
│ (班额25-40)│ 其余组用"一句话补充/不同意见"轮流,各 20 秒│
│ │ 总计 ≈ 8-10 分钟 │
├─────────────┼──────────────────────────────────────────┤
│ 组数 ≥ 11 │ 不做全班口头汇报。改用: │
│ (班额≥41) │ · 组间两两互评 3 分钟(同时进行,不占讲台)│
│ │ · 抽 2 组上台,各 2 分钟 │
│ │ · 其余组把结论写在任务卡上交,课后老师看 │
│ │ 总计 ≈ 7-8 分钟 │
└─────────────┴──────────────────────────────────────────┘
第 4 步:讨论时长与汇报时长配比
讨论 : 汇报 ≈ 2 : 1(讨论 12 分钟就配 6 分钟汇报),
汇报时间超过讨论时间,说明这个任务不值得小组做。
⚠️ 45 人的班:组数 12,别按"每组都讲 1 分钟"排——那是 15 分钟,
本节课的新授时间会被吃掉。走上表第三行。📎 完整模板见
references/group-task-card-and-scripts.md(小组合作任务卡空白模板,含角色/必发言规则/汇报要求/提交物)
📎 完整话术见
references/group-task-card-and-scripts.md(开场→中途提醒→结束→互评全流程话术模板)
情境 1:抛出好问题后,全班沉默
→ 学生没听懂问题(最常见)
→ 应对:换一种方式重新问("换句话说")
情境 2:学生回答了但明显答非所问
→ 学生只听了一半
→ 应对:先肯定参与("你抓住了 X 这个关键词"),再引导:"题目还问了一个什么?"
情境 3:好问题被"标准答案"抢先
→ 优等生秒答,中等和基础生失去思考机会
→ 应对:"X 答得很好,但我想听听其他同学怎么想"第 1 步:等 5-8 秒(不要立刻换问题)
→ 大部分学生需要时间思考
→ 在心里默数
第 2 步:等 10 秒还没人举手
→ 改问更简单的候场问题
→ "我再问简单一点:[候场问题]"
第 3 步:还是没人举手
→ 老师自问自答但故意留半句
→ "其实我心里有一个答案的起点,是 [X],谁能接着说?"
→ 或者直接让同桌互讲 2 分钟,再回到全班常见原因:
· 怕答错被笑话
· 跟不上全班节奏
· 长期未被叫到形成"反正不会叫我"的预期
应对:
· 提前给基础学生"小纸条"提示(如:今天可能被问到 X)
· 让基础学生先在同桌间小声回答
· 老师听到正确版本后说"我刚才听到 XX 说得很好,请她/他分享"
· 任何时候答对都给予"具体"表扬("你抓住了 X 关键词")
· 答错时不批评,只纠正("你离答案只差一步,是 X")■ 集体反馈(教师 → 全班)
适用:核心概念纠错、共性问题强调
节奏:每节课 1-2 次
方式:举手表决 / 集体回应 / 教师直接说明
■ 同伴反馈(学生 → 学生)
适用:同桌互讲、小组互评
节奏:每节课 2-3 次
方式:同桌交换看答题、同伴点评
■ 教师反馈(教师 → 个人)
适用:针对性辅导、纠正个体错误
节奏:贯穿课堂
方式:巡视时低声提示、单独眼神鼓励❌ 模糊反馈:
"你答得不错"
"再想想"
"你真棒"
✅ 具体反馈:
"你抓住了'k>0'这个关键点,这正是图象上升的原因"
"你离答案只差一步——再检查一下符号"
"你今天主动发言了 3 次,比上周多了 2 次"
具体反馈让学生知道"哪里做对了""哪里能改进",
模糊反馈除了情绪安抚外没有教学价值。学生答错时:
· 不直接否定:"我再听听其他同学的想法"
· 不立刻纠正:"你的思路挺有创意,但有一步可能需要再想想"
· 不嘲笑:"谢谢你的分享,这对我们都是一种学习"
学生说"不会"时:
· 不批评:"不会很正常,我们一起来想"
· 给台阶:"那我给你一个提示:[X]"
· 给时间:"给你 30 秒想一下"经验性节奏建议(非精确"注意力曲线",不同学生/课型差异很大,据实调整):
· 每 10-15 分钟切换一次活动形式(讲解↔提问↔练习↔讨论),
避免长时间单向讲授导致注意力涣散
· 核心概念尽量放在课堂较早、学生较投入的时段讲
· 难点讲完后安排一次即时练习或提问,检验并重新聚焦注意力
· 临近下课安排小结与作业布置,此时不宜引入全新难点
⚠️ 说明:"学生注意力每 N 分钟递减"的分钟级曲线在严谨研究中证据薄弱,
不作精确指标,仅用"定期切换活动"这一可操作经验。全班 → 小组:"接下来 12 分钟,请 4 人小组讨论 [X],计时员看时间。"
小组 → 全班:"时间到。第 X 组汇报员,请分享,其他组准备补充。"
讲授 → 提问:"讲到这里,我想问大家一个关键问题:[X]"
提问 → 练习:"现在请大家独立完成 [X],3 分钟后同桌互对。"📎 完整模板见
references/post-class-record-template.md(互动效果/提问链效果/下节课调整方向三段式课后记录模板)
课后 5 分钟内把观察写进 classWorkspace.interactionLogs(生成待确认条目,老师确认后落库):
logId 本次记录 id
planId 对应 lessonPlans 的 planId(把课堂记录挂回教案)
date 日期
segmentTimings[] 各环节 计划分钟 vs 实际分钟(下次排课时间矩阵的依据)
participationNote 整体参与度的事实描述("主动举手约三分之一"),不写个别学生姓名
questionEffectNote 哪一问引发最多讨论、哪一问无人回应(只记问题,不记谁答的)
misconceptionsObserved 课上暴露的错误理解(→ student-analyzer 的辅助证据)
adjustmentForNext 下节课的调整动作
⚠️ interactionLogs 里没有"学生姓名"字段,这是设计上的选择而不是遗漏:
课堂印象是低置信度的单次观察,把它挂到具体学生名下容易固化标签。
要定位到个人的结论走 student-analyzer 的逐题数据。 ┌────────────────────────┐
│ xiaozhi-teach- │
│ lesson-planner │
│ (教学目标) │
└───────────┬────────────┘
│
↓
┌────────────────────────┐
│ xiaozhi-teach- │
│ student-analyzer │
│ (学情分层) │
└───────────┬────────────┘
│
↓
┌────────────────────────┐
│ xiaozhi-teach- │
│ classroom-coach │
│ (本 SKILL) │
└───────────┬────────────┘
│
┌─────────────────┼─────────────────┐
↓ ↓ ↓
assignment- homework- lesson-log
designer tracker (观察记录)
(作业配套) (课上练习) (课后回写)流图下排的 homework-tracker、lesson-log 属独立教师包:只在一对一/小班场景、已安装时作可选补充(见第十四节),班级授课不依赖它们。
shared/class-teaching-workspace.schema.json)| classWorkspace 字段 | 谁写 | 本 SKILL |
|---|---|---|
classProfile | 老师首次建档 | 读(classSize 定组数与汇报方式,periodMinutes 定活动时长) |
lessonPlans | xiaozhi-teach-lesson-planner 或学科老师端技能 | 读 objectives(提问目标)、questionChain(提问链草案)、segments 的 tierVariants(互动分层) |
studentTiers | xiaozhi-teach-student-analyzer | 读(异质分组、提问难度分配) |
weaknessRank | xiaozhi-teach-student-analyzer 或学科老师端技能 | 读(提问与追问的侧重点) |
interactionLogs | 本 SKILL 主写;学科老师端技能也写本学科的条目,读时不覆盖别人的条目 | 写 logId / planId / date / segmentTimings / participationNote / questionEffectNote / misconceptionsObserved / adjustmentForNext |
两条边界:
· 本 SKILL 只写 interactionLogs,不写 studentTiers(分层是 student-analyzer 的字段),
也不写 lessonPlans(教案是 lesson-planner 的字段)。
· lessonPlans 里没有 questionChain 时(老师没走 lesson-planner),
本 SKILL 可以现场帮老师补一版提问链,但要提示"这版没有教案目标做锚,
建议回 lesson-planner 补一次目标"。✅ 写回数据:聚合信号("本节课主动发言 8 人")
❌ 不写回:小明今天表现很好
✅ 写回:哪些问题最有效
❌ 不写回:哪个学生答错了哪道题
✅ 写回:互动方式效果评估
❌ 不写回:家长可读的"差生名单"| ✅ 应该做 | ❌ 不能做 |
|---|---|
| 提问指向思维而非记忆 | 满堂问"对不对" |
| 给基础学生参与路径 | 反复叫优等生 |
| 候场至少 5-8 秒 | 抛出问题立刻换 |
| 反馈具体到行为 | "你真棒"等空话 |
| 冷场不批评学生 | 责怪学生"这么简单都不会" |
| 课后 5 分钟内记录 | 拖到第二天 |
| 写回数据用聚合形式 | 在学生档案里点名 |
课堂互动教练
<── xiaozhi-teach-lesson-planner(lessonPlans:目标 + 提问链草案)
<── xiaozhi-teach-student-analyzer(studentTiers / weaknessRank)
<── xiaozhi-teach-exam-designer(讲评错题清单 → 讲评课的提问设计)
──→ xiaozhi-teach-lesson-planner(interactionLogs:实际用时与卡点 → 下次教案)
──→ xiaozhi-teach-student-analyzer(interactionLogs:课堂暴露的错误理解,作辅助证据)
──→ xiaozhi-teach-assignment-designer(课上没消化的点 → 当天作业)
··→ 若已安装独立教师包:xiaozhi-teach-lesson-log 可作可选补充(一对一/小班场景)
··→ 若已安装独立教师包:xiaozhi-teach-homework-tracker 可作可选补充(一对一/小班场景:课上练习的登记)禁止行为:
references/questioning-strategies.md — 课堂提问策略库references/group-task-card-and-scripts.md — 小组合作任务卡模板与全流程话术模板references/post-class-record-template.md — 课后 5 分钟观察记录模板💡 小智说: "课堂不是剧场,老师不是演员。 真正的好课堂,是学生说得多、老师说得少; 学生想得深、老师讲得准。 你今天设计了多少个好问题, 决定了有多少学生真的在想。"
© 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 teacher/general/xiaozhi-teach-classroom-coach of qizhitang/xiaozhi-skills.
Open the folder on GitHubat commit c65f2d4
Xiaozhi Teach Classroom 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 Teach Classroom Coach this skillqizhitang/xiaozhi-skills | 105 | — | ~4.5k | 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
把"单向讲授"变成有追问、有参与路径的课堂. An agent skill from qizhitang/xiaozhi-skills. Xiaozhi Teach Classroom Coach is an agent skill from qizhitang/xiaozhi-skills.
Xiaozhi Teach Classroom Coach fits situations like: education work in your project.
Run `npx skills add qizhitang/xiaozhi-skills --skill xiaozhi-teach-classroom-coach -a claude-code`. Or copy the skill folder (teacher/general/xiaozhi-teach-classroom-coach in qizhitang/xiaozhi-skills) into .claude/skills/xiaozhi-teach-classroom-coach in your project. Claude Code loads it when a task matches its description.
Run `npx skills add qizhitang/xiaozhi-skills --skill xiaozhi-teach-classroom-coach -a codex`. Or copy the skill folder (teacher/general/xiaozhi-teach-classroom-coach in qizhitang/xiaozhi-skills) into .agents/skills/xiaozhi-teach-classroom-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-teach-classroom-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-teach-classroom-coach, .gemini/skills/xiaozhi-teach-classroom-coach, .github/skills/xiaozhi-teach-classroom-coach and .opencode/skills/xiaozhi-teach-classroom-coach in your project.
SKILL.md names no scripts, command-line tools or credentials: Xiaozhi Teach Classroom 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 Teach Classroom 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 4.5k tokens (SKILL.md is roughly 18k 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 3.2k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Xiaozhi Teach Classroom 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.