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.
英语口语活动设计:把"读课文、背对话"变成有任务、有情境、有反馈的口语课. An agent skill from qizhitang/xiaozhi-skills.
$ npx skills add qizhitang/xiaozhi-skills --skill xiaozhi-teach-english-speaking-designer -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-teach-english-speaking-designer --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/english/xiaozhi-teach-english-speaking-designer .claude/skills/xiaozhi-teach-english-speaking-designer && 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-english-speaking-designer" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/teacher/english/xiaozhi-teach-english-speaking-designer into .claude/skills/xiaozhi-teach-english-speaking-designer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-teach-english-speaking-designer", 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/english/xiaozhi-teach-english-speaking-designerType 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-english-speaking-designer -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-teach-english-speaking-designer --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/english/xiaozhi-teach-english-speaking-designer .agents/skills/xiaozhi-teach-english-speaking-designer && 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-english-speaking-designer" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/teacher/english/xiaozhi-teach-english-speaking-designer into .agents/skills/xiaozhi-teach-english-speaking-designer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-teach-english-speaking-designer", 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-english-speaking-designer -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-teach-english-speaking-designer --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/english/xiaozhi-teach-english-speaking-designer .cursor/skills/xiaozhi-teach-english-speaking-designer && 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-english-speaking-designer" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/teacher/english/xiaozhi-teach-english-speaking-designer into .cursor/skills/xiaozhi-teach-english-speaking-designer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-teach-english-speaking-designer", 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/english/xiaozhi-teach-english-speaking-designer--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-english-speaking-designer -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-teach-english-speaking-designer --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/english/xiaozhi-teach-english-speaking-designer .gemini/skills/xiaozhi-teach-english-speaking-designer && 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-english-speaking-designer" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/teacher/english/xiaozhi-teach-english-speaking-designer into .gemini/skills/xiaozhi-teach-english-speaking-designer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-teach-english-speaking-designer", 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-english-speaking-designerInstalls 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-english-speaking-designer -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/english/xiaozhi-teach-english-speaking-designer .github/skills/xiaozhi-teach-english-speaking-designer && 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-english-speaking-designer" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/teacher/english/xiaozhi-teach-english-speaking-designer into .github/skills/xiaozhi-teach-english-speaking-designer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-teach-english-speaking-designer", 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-english-speaking-designer -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-english-speaking-designer --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/english/xiaozhi-teach-english-speaking-designer .opencode/skills/xiaozhi-teach-english-speaking-designer && 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-english-speaking-designer" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/teacher/english/xiaozhi-teach-english-speaking-designer into .opencode/skills/xiaozhi-teach-english-speaking-designer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-teach-english-speaking-designer", 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-english-speaking-designer英语口语活动设计:把"读课文、背对话"变成有任务、有情境、有反馈的口语课. An agent skill from qizhitang/xiaozhi-skills.
Xiaozhi Teach English Speaking Designer is an agent skill from qizhitang/xiaozhi-skills. 英语口语活动设计:把"读课文、背对话"变成有任务、有情境、有反馈的口语课。 触发语:"口语课怎么上"、"学员不敢开口"、"口语活动怎么设计"、"信息差任务怎么做"、"口语任务怎么分层"、"口语怎么纠错"、"口语评分表怎么用"、"高中口语课怎么设计"。 核心工作流:口语目标(流利/准确/得体)→ 输入准备 → 任务型活动 → 输出练习 → 反馈与纠正 → 写回班级工作空间。任务时长按班额与课时排;高中加得体表达、概述与评判观点的任务,口语测评按课标口径。 不处理:整卷四维测评的设计与能力画像(转英语综合测评)、听力材料选编与听法训练(转英语听力材料设计)、学员一对一的 AI 陪练对话(学生端英语口语陪练负责)。
Its SKILL.md is about 3.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 16 other files, including reference files (for example `references/error-correction-strategies.md`, `references/feedback-phrases.md` and `references/speaking-profile-template.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 English Speaking Designer loads about 3.8k tokens when it runs, and up to ~12k if it reads all its reference files. Until then it costs about 87 tokens; SKILL.md has 264 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). 264 words, ~3,839 tokens.
.claude/skills/xiaozhi-teach-english-speaking-designer/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: 口语不是教学生"发音标准",而是教学生"用英语做事"——任务型活动是核心。
技术边界:本 SKILL 依赖能力 [M, X, F],无该能力时按 shared/platform-conventions.md 降级。 无 X 时不输出跨次的口语能力变化统计,只呈现本次数据;无 F 时请老师粘贴评分表格。
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)》)。
本 SKILL 不做的三件事:
xiaozhi-english-speaking-coach 负责)。copyrightStatus(自有 / 改编 / 公开可引用 / 仅存索引);不复制未授权材料。⚠️ 发音评价的能力前提:老师现场听学员说话时,发音判断由老师做。
本 SKILL 输出的是任务与评分框架,不对录音做音素级判断;
学生端要做发音反馈需平台具备语音评测能力(shared/platform-conventions.md 能力代号 S),
仅有语音转写(A)时转写会把发音归一化掉,不得据此判定发音。
AI 生成的任务卡与题目:按 shared/ai-item-check.md 自检(情境成立、角色分工清楚、
双方确有信息差、语言点不超该学段),输出时标注 【AI 生成,入库前请人工验算】。
⚠️ 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。
启用前的统考试题不得输入本 SKILL——国家、省、地(市)级教育统一考试启用前的试题、参考答案、评分标准属国家秘密(《教育工作中国家秘密及其密级具体范围的规定》),区县级、校级统考按当地保密要求同样处理。外语听说考试同样适用:本地考试说明公开发布的题型、样题与评分标准,照常用来设计口语任务与模拟练习;没有公开的考题,全部批次、全部场次考完之前都按启用前处理(这类考试常分几天、分批进行,本班、本校考完不等于考完)。题型、样题公开与否,前几批考到的题目都不接收,也不据此给后面批次的学生针对性地练。跨校联考要等参加的学校全部考完;同一套考题还有学生补考的,补考考完才算考完;考后不公开试卷的考试(如用题库命题、机考的),考完也只按本地公布的样题与评分维度讲共性问题,不据学生回忆还原原题。 老师说明正在为统考或统一组织的外语听说考试命题时,本 SKILL 只提供口语任务的设计方法与自编练习,不接收、不生成、不审改该次考试的具体试题与评分细则;本校自己组织的模拟练习照常设计;已经考完的可以正常分析与讲评。 依据《中小学生成式人工智能使用指南(2025年版)》教师一节:“严禁将个人信息、考试试题等敏感数据输入AI工具”。
英语口语教学常见的三个误区:
误区① 口语=背诵:让学员背"对话范文",
学员说得"流利"但没有真实交际。
误区② 口语=纠错:老师不停纠正学员的错,
学员不敢开口,焦虑上升。
误区③ 口语=读课文:让学员读课文/对话,
学员没有"自己说话"的机会。本 SKILL 要解决的是:
| 触发场景 | 示例语句 |
|---|---|
| 口语课设计 | "口语课怎么上" |
| 学员不敢开口 | "学员不敢开口" |
| 口语活动 | "口语活动怎么设计" |
| 对话练习 | "对话练习怎么设计" |
| 口语任务 | "口语任务怎么设计" |
| 发音纠正 | "发音怎么纠正" |
| 口语评估 | "口语怎么打分" |
| 学员口语弱 | "学员口语弱" |
┌──────────────────────────┐
│ ① 口语目标 │
│ 流利/准确/得体 │
└────────────┬─────────────┘
↓
┌──────────────────────────┐
│ ② 输入准备 │
│ 听力/词汇/情境 │
└────────────┬─────────────┘
↓
┌──────────────────────────┐
│ ③ 任务型活动 │
│ 信息差/角色/辩论 │
└────────────┬─────────────┘
↓
┌──────────────────────────┐
│ ④ 输出练习 │
│ 独白/对话/讨论 │
└────────────┬─────────────┘
↓
┌──────────────────────────┐
│ ⑤ 反馈与纠正 │
│ 重述式/同伴纠错 │
└────────────┬─────────────┘
↓
┌──────────────────────────┐
│ ⑥ 口语能力档案 │
│ → 学员档案 │
└────────────┬─────────────┘
↓
┌──────────────────────────┐
│ ⑦ 写回 student-analyzer │
│ 口语能力维度 │
└──────────────────────────┘┌──────────┬────────────────────────┬──────────────┐
│ 维度 │ 描述 │ 学员表现 │
├──────────┼────────────────────────┼──────────────┤
│ 流利 │ 说得顺畅/不卡顿 │ 自然停顿少 │
│ 准确 │ 用词/语法/发音正确 │ 错误少 │
│ 得体 │ 适合场合/对象 │ 礼貌/合适 │
└──────────┴────────────────────────┴──────────────┘■ 基础层
· 流利优先:敢开口 > 准确
· 重点:敢说
■ 中等层
· 流利 + 准确并重
· 重点:说得"对"
■ 提升层
· 三维并重
· 重点:说得"得体"· 启蒙期:敢说(流利)
· 成长期:说对(准确)
· 提升期:说好(得体)┌──────────┬────────────────────────┬──────────────┐
│ 输入 │ 描述 │ 任务 │
├──────────┼────────────────────────┼──────────────┤
│ 听力 │ 听地道英语 │ 模仿语调/结构 │
│ 词汇 │ 关键场景词汇 │ 词→句→情境 │
│ 情境 │ 真实/模拟情境 │ 角色代入 │
└──────────┴────────────────────────┴──────────────┘■ 选材
· 首听可懂约 90%(生词 ≤2-3%),语速按学段(小学高段 90-100 / 初一 100 /
初二 110 / 初三 120 词/分钟,与听力设计 SKILL 同一套口径)
· 长度:30 秒-2 分钟(作为口语任务的输入,不宜过长)
· 主题:贴近生活,且与后面的口语任务同一话题
■ 听法
· 第一遍:泛听,抓主旨
· 第二遍:精听,抓细节
· 第三遍:模仿,复述
■ 资源(每条填 copyrightStatus,见 shared/vocab.md §11)
· 教材配套音频(按学校授权范围课堂内使用)
· 条款允许教学使用的公开材料 → 记 `公开可引用`,存链接不存文件
· 老师自录 / 自有改编材料 → 记 `自有` / `改编`■ 关键场景词汇
· 餐厅:order, menu, bill, ...
· 机场:flight, gate, boarding, ...
· 购物:price, size, discount, ...
■ 学习路径
· 词 → 词组 → 句子
· 例:order → order food → I'd like to order...
■ 不只背单词
· 在情境中学
· 在使用中记■ 真实情境
· 学员生活中的真实场景
· 学员感兴趣的领域
■ 模拟情境
· 社团招新面试(初中版;求职面试属 ⚠高中及以上情境)
· 模拟旅行、问路
· 模拟购物
· 班级演讲
■ 学员代入
· 让学员"成为"角色
· 让学员"在意"结果任务(Task)=
· 用目标语言做事
· 有明确的结果
· 关注意义 > 关注形式┌──────────┬────────────────────────┬──────────────┐
│ 类型 │ 描述 │ 例子 │
├──────────┼────────────────────────┼──────────────┤
│ 信息差 │ 两人信息不同,需要交流 │ 找差异/拼图 │
│ 角色扮演 │ 扮演角色完成任务 │ 店员顾客 │
│ 辩论 │ 不同立场讨论 │ 校园话题 │
└──────────┴────────────────────────┴──────────────┘■ 定义
· 两人/多人有不同信息
· 必须交流才能完成任务
■ 例子
· 任务 1:两人各持一张图,描述给对方,让对方画出来
· 任务 2:两人各持一份活动表,找出不同点
· 任务 3:一人有地图,一人问路
■ 优势
· 学员必须说话
· 学员有"目的"说话
· 自然产生对话■ 定义
· 学员扮演不同角色
· 完成特定任务
■ 例子
· 任务 1:餐厅点餐(顾客/服务员)
· 任务 2:酒店入住(客人/前台)
· 任务 3:电话咨询(客户/客服)
· 任务 4:社团招新面试(社长/申请者)——求职面试属 ⚠高中及以上情境
■ 优势
· 学员"成为"角色
· 自然使用礼貌用语
· 适应不同场合■ 定义
· 学员持不同观点
· 用英语论证
■ 例子(选学员真的有话说的议题)
· 任务 1:手机该不该带进校园(正方/反方)
· 任务 2:作业该不该分层布置
· 任务 3:课间十分钟该怎么用
■ 难度
· 较高(需要论证)
· 适合已能连续说 5-6 句的学员;基础层先做信息差任务
■ 课堂可行性(排辩论前先算这一步)
· 一节课 45 分钟,除去组织与讲评,可用于辩论的约 25-30 分钟
· 50 人班分 4-6 人一组 = 8-12 组,每组都上台不可能
· 三种可行排法:
① 全班分组同时辩(推荐):8-12 组同时进行,老师巡视
准备 5 分钟 + 组内辩论 10 分钟 + 全班分享 2 组 × 3 分钟 = 21 分钟
优点:每个学员都在说;缺点:老师只能抽听
② 两组示范 + 其余观察记录:2 组上台各 8 分钟,
其余学员用观察表记录"哪句论证有力",之后 5 分钟讨论
优点:可控;缺点:多数人这节课没开口,需下一节补
③ 分两节课:第一节全班分组辩,第二节各组派代表复述本组结论
· ⚠️ 一组"自由辩论 10 分钟"只在排法②里成立;
排法①里 8-12 组同时说,10 分钟的自由辩论会失控,改为 6-8 分钟并给发言顺序卡■ 有明确结果
· 学员知道"要做什么"
· 有"产出"(图/表/答案/决定)
■ 信息差/观点差
· 必须交流才能完成
· 不会"无话可说"
■ 难度适中
· 略高于学员水平
· 不太简单,不太难
■ 真实/模拟情境
· 学员有代入感
· 不是"为说而说"📎 完整样板见
references/task-design-sample-restaurant.md("餐厅点餐"任务设计范例:任务/输入准备/任务流程/词汇/输出)
┌──────────┬────────────────────────┬──────────────┐
│ 类型 │ 描述 │ 适合 │
├──────────┼────────────────────────┼──────────────┤
│ 独白 │ 一人讲话 │ 自我介绍/演讲 │
│ 对话 │ 两人交流 │ 日常对话 │
│ 讨论 │ 多人讨论 │ 课堂讨论 │
└──────────┴────────────────────────┴──────────────┘■ 自我介绍
· 1-2 分钟
· 个人基本信息/兴趣/梦想
■ 演讲
· 2-3 分钟
· 观点+论证
■ 故事讲述
· 复述故事
· 看图说话■ 配对对话
· 学员两两配对
· 围绕主题对话
■ 角色对话
· 一人扮演一个角色
· 围绕情境对话
■ 自由对话
· 不指定话题
· 自由交流■ 小组讨论(大班的默认形式)
· 3-5 人一组,全班同时进行
· 围绕主题讨论;老师巡视,抽听 3-5 组
■ 圆桌讨论
· 全班一起讨论,老师引导
· ⚠️ 40-50 人班里,一节课能发言的不超过 10 人——
只用于收尾汇总,不作为主要的开口机会
■ 立场讨论
· 学员持不同立场,用英语论证
· 时长与分组按 references/task-based-template.md §9 算┌──────────┬────────────────────────┬──────────────┐
│ 方式 │ 描述 │ 适用 │
├──────────┼────────────────────────┼──────────────┤
│ 即时反馈 │ 立刻纠正 │ 关键错误 │
│ 延时反馈 │ 课后/活动后 │ 重要错误 │
│ 学员自评 │ 学员自己发现 │ 培养意识 │
│ 同伴反馈 │ 学员互相反馈 │ 培养敏感度 │
└──────────┴────────────────────────┴──────────────┘■ 做法:老师用**正确形式把学员的话复述一遍**,继续对话,不评判对错
· 学员:"I go to school yesterday."
· 老师:"Oh, you **went** to school yesterday! What did you do there?"
→ 复述时把 went 说重一点,然后用一个**推进内容**的问题接下去
■ ❌ 常见的错误示范
· 学员:"I go to school yesterday."
老师:"Oh, you went to school yesterday? When?"
问题在哪:学员已经说了 yesterday,再问 When? 逻辑上说不通,
学员会以为自己的**内容**没说清,转去重复时间,反而注意不到动词被改了。
· 重述必须紧跟原句、只改错的那一处、其余照搬;
追问要推进到新信息,不能问学员刚说过的东西。
■ 重述的局限(老师需要知道)
· 学员常把重述当成"老师在回应内容",不一定注意到语言被改了
· 所以:重述适合流利度优先的任务型活动;
要确保学员注意到,改用引导式纠错或元语言提示(§3.3 / §3.4)
■ 让学员在"对话"中自己发现
· 不打断学员说话
· 重述后如果学员自己改了口,明确肯定一句■ 不打断
· 学员说话流畅性 > 准确性
· 错的不影响意思,先不管
■ 关注"可懂"
· 让学员"说清楚"
· 不要求"完美"
■ 关键错误
· 影响交际的错误要纠正
· 学员已掌握的规则错要纠正📎 完整话术库见
references/feedback-phrases.md(肯定/重述/引导/不直接说"错"四类反馈话术)
┌──────────┬────────────────────────┐
│ 维度 │ 描述 │
├──────────┼────────────────────────┤
│ 流利度 │ 说话速度/停顿/犹豫 │
│ 准确度 │ 用词/语法/发音 │
│ 得体度 │ 适合场合/对象 │
│ 词汇量 │ 主动使用词汇量 │
│ 句式 │ 主动使用句式 │
│ 发音 │ 音准/语调/连读 │
│ 互动 │ 回应/倾听/协商 │
│ 自信 │ 敢开口/不怕错 │
└──────────┴────────────────────────┘📎 完整模板见
references/speaking-profile-template.md(口语档案填写模板:流利度/准确度/得体度/词汇量/句式/发音/互动/自信 8 维打分)
┌────────────────────────┐
│ xiaozhi-teach- │
│ lesson-planner │
│ (口语任务嵌入教案) │
└───────────┬────────────┘
│
↓
┌────────────────────────┐
│ 课堂(口语活动) │
└───────────┬────────────┘
│
↓
┌────────────────────────┐
│ xiaozhi-teach- │
│ english-speaking- │
│ designer(本 SKILL) │
└───────────┬────────────┘
│
┌─────────────────┼─────────────────┐
↓ ↓ ↓
student-analyzer resource-library parent-communication
(口语能力维度) (口语素材入库) (独立教师的家长反馈)shared/class-teaching-workspace.schema.json)读:
classWorkspace.classProfile → 学段、班额、课时(决定任务时长与分组方式)
classWorkspace.lessonPlans[] → 本课教案与 segments(口语任务嵌在哪一段)
classWorkspace.interactionLogs[] → 上一次课堂的实际用时与参与度
classWorkspace.itemScores[] → 口语题得分(能力画像的唯一来源)
classWorkspace.studentTiers[] → A/B/C 分层,用于给任务配难度变式
写(均为待老师确认的条目,确认后落库):
classWorkspace.lessonPlans[].segments[] → 口语活动的环节与分钟数
classWorkspace.lessonPlans[].segments[].tierVariants → A/B/C 三档任务变式
classWorkspace.examBlueprints[].items[] → 口语评分条目(itemType = "口语")
AI 生成题 aiGenerated=true,
老师验算后才可 verifiedByTeacher=true
classWorkspace.interactionLogs[] → 活动实际用时与观察到的共性问题
(participationNote 只写整体,不点名)
classWorkspace.weaknessRank[] → 由口语表现归纳出的班级弱项
· weaknessId / knowledgePoint / errorRate / dimension / evidenceExamIds[] / lastUpdated
(不写 .stubbornCount——顽固计数由 xiaozhi-teach-student-analyzer 唯一累加)
写回学生档案(可选,需授权):
handoverType = "teacher_writeback",recipient = xiaozhi-learning-dna
前置:交接体中的授权快照 teacherWritebackConsent 必须为 true,否则丢弃并告知老师
内容:weakKnowledgePointUpdates 列表(subject = "英语",
knowledgePoint 写具体语言点如"口语·第三人称单数"),note 只写低敏事实描述
❌ 不写等级、不写学员真实姓名、不写"某某不爱说话"这类人格评价
❌ 不写发音判断(本 SKILL 不做音素级判定)✅ 口语档案用化名
✅ 学员口语录音脱敏
❌ 禁止:公开"某学员的口语差"
❌ 禁止:未授权公开学员口语录音
✅ 口语素材可入库(脱敏后)| ✅ 应该做 | ❌ 不能做 |
|---|---|
| 任务型活动 | 口语=背诵 |
| 真实/模拟情境 | 口语=读课文 |
| 重述式纠正 | 直接说"错" |
| 学员敢说 > 准确(基础层) | 因为怕错就不让学员开口 |
| 口语能力档案累积 | 学员不积累 |
| 学员化名 | 公开批评学员口语 |
英语口语活动设计
<── xiaozhi-teach-lesson-planner(口语任务嵌入教案)
<── xiaozhi-teach-student-analyzer(学情/弱项)
──→ xiaozhi-teach-student-analyzer(口语能力维度;学校班级的家长版,由它核对 parentSharingConsent)
──→ xiaozhi-teach-resource-library(口语素材入库)
──→ xiaozhi-teach-parent-communication(独立教师:口语进步反馈)
──→ 学生端 xiaozhi-english-speaking-coach(学员视角;发音判定的能力前提两端一致)禁止行为:
teacherWritebackConsent 写回学生档案依据《普通高中英语课程标准日常修订版(2017 年版 2025 年修订)》表 3、表 8、表 10 与"学业水平考试与高考建议"。老师说明带的是高中班时用本节。
references/task-based-template.md §9。references/task-based-template.md — 任务型活动模板(5 类任务样板)references/speaking-rubric.md — 口语评估评分细则(5 维度 + CEFR 等级)references/error-correction-strategies.md — 纠错策略参考(4 时机 + 5 方法)references/task-design-sample-restaurant.md — 任务设计样板(餐厅点餐范例)references/feedback-phrases.md — 反馈话术库(肯定/重述/引导/不直接说"错")references/speaking-profile-template.md — 学员口语档案模板(8 维打分)💡 小智说: "口语不是'发音标准', 是'用英语做事'。 当学员能用英语点餐、问路、面试、辩论, 那才是真的'会英语'—— 不仅是考试分数,更是'我能行'。"
© 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 teacher/english/xiaozhi-teach-english-speaking-designer of qizhitang/xiaozhi-skills.
Open the folder on GitHubat commit c65f2d4
Xiaozhi Teach English Speaking Designer 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 English Speaking Designer this skillqizhitang/xiaozhi-skills | 105 | — | ~3.8k | 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
英语口语活动设计:把"读课文、背对话"变成有任务、有情境、有反馈的口语课. An agent skill from qizhitang/xiaozhi-skills. Xiaozhi Teach English Speaking Designer is an agent skill from qizhitang/xiaozhi-skills.
Xiaozhi Teach English Speaking Designer fits situations like: education work in your project.
Run `npx skills add qizhitang/xiaozhi-skills --skill xiaozhi-teach-english-speaking-designer -a claude-code`. Or copy the skill folder (teacher/english/xiaozhi-teach-english-speaking-designer in qizhitang/xiaozhi-skills) into .claude/skills/xiaozhi-teach-english-speaking-designer in your project. Claude Code loads it when a task matches its description.
Run `npx skills add qizhitang/xiaozhi-skills --skill xiaozhi-teach-english-speaking-designer -a codex`. Or copy the skill folder (teacher/english/xiaozhi-teach-english-speaking-designer in qizhitang/xiaozhi-skills) into .agents/skills/xiaozhi-teach-english-speaking-designer 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-english-speaking-designer -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-english-speaking-designer, .gemini/skills/xiaozhi-teach-english-speaking-designer, .github/skills/xiaozhi-teach-english-speaking-designer and .opencode/skills/xiaozhi-teach-english-speaking-designer in your project.
SKILL.md names no scripts, command-line tools or credentials: Xiaozhi Teach English Speaking Designer 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 English Speaking Designer is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.8k tokens (SKILL.md is roughly 15k 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 8.3k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Xiaozhi Teach English Speaking Designer: 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.