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.
英语听力教学设计:把"放一遍录音对答案"变成有目标、有策略、有微技能训练的听力课. An agent skill from qizhitang/xiaozhi-skills.
$ npx skills add qizhitang/xiaozhi-skills --skill xiaozhi-teach-english-listening-designer -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-teach-english-listening-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-listening-designer .claude/skills/xiaozhi-teach-english-listening-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-listening-designer" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/teacher/english/xiaozhi-teach-english-listening-designer into .claude/skills/xiaozhi-teach-english-listening-designer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-teach-english-listening-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-listening-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-listening-designer -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-teach-english-listening-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-listening-designer .agents/skills/xiaozhi-teach-english-listening-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-listening-designer" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/teacher/english/xiaozhi-teach-english-listening-designer into .agents/skills/xiaozhi-teach-english-listening-designer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-teach-english-listening-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-listening-designer -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-teach-english-listening-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-listening-designer .cursor/skills/xiaozhi-teach-english-listening-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-listening-designer" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/teacher/english/xiaozhi-teach-english-listening-designer into .cursor/skills/xiaozhi-teach-english-listening-designer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-teach-english-listening-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-listening-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-listening-designer -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-teach-english-listening-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-listening-designer .gemini/skills/xiaozhi-teach-english-listening-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-listening-designer" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/teacher/english/xiaozhi-teach-english-listening-designer into .gemini/skills/xiaozhi-teach-english-listening-designer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-teach-english-listening-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-listening-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-listening-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-listening-designer .github/skills/xiaozhi-teach-english-listening-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-listening-designer" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/teacher/english/xiaozhi-teach-english-listening-designer into .github/skills/xiaozhi-teach-english-listening-designer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-teach-english-listening-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-listening-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-listening-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-listening-designer .opencode/skills/xiaozhi-teach-english-listening-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-listening-designer" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/teacher/english/xiaozhi-teach-english-listening-designer into .opencode/skills/xiaozhi-teach-english-listening-designer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-teach-english-listening-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-listening-designer英语听力教学设计:把"放一遍录音对答案"变成有目标、有策略、有微技能训练的听力课. An agent skill from qizhitang/xiaozhi-skills.
Xiaozhi Teach English Listening Designer is an agent skill from qizhitang/xiaozhi-skills. 英语听力教学设计:把"放一遍录音对答案"变成有目标、有策略、有微技能训练的听力课。 触发语:"听力课怎么上"、"听力材料选什么"、"学员听不懂"、"听力策略怎么教"、"听力微技能怎么练"、"精听泛听怎么分"、"听填信息怎么训练"、"高中听力课怎么上"。 核心工作流:听力目标 → 材料选编(来源/难度/版权)→ 听前预测 → 听中分层 → 听后任务 → 微技能训练 → 写回班级工作空间。初中题型按中考听力四节结构排;高中按课标的语篇类型与本地考试说明排。 不处理:整卷四维测评的设计与能力画像(转英语综合测评)、口语活动与纠错策略(转英语口语活动设计)、通用命题的难度配比(转 xiaozhi-teach-exam-designer)、考后的难度与区分度统计(转 xiaozhi-teach-student-analyzer)。
Its SKILL.md is about 4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 16 other files, including reference files (for example `references/listening-material-sources.md`, `references/listening-rubric.md` and `references/micro-skill-training.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 Listening Designer loads about 4k tokens when it runs, and up to ~12k if it reads all its reference files. Until then it costs about 102 tokens; SKILL.md has 284 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). 284 words, ~3,982 tokens.
.claude/skills/xiaozhi-teach-english-listening-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: 听力不是教学生"听懂每个词",而是教学生"用英语获取信息"——微技能训练是核心。
技术边界:本 SKILL 依赖能力 [M, V, X, F],无该能力时按 shared/platform-conventions.md 降级。 无 V(语音合成)时不生成音频,只给文本 + 朗读要点,由老师或录音朗读; 无 X 时不输出跨次的听力能力变化统计,只呈现本次数据。
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:
copyrightStatus(自有 / 改编 / 公开可引用 / 仅存索引);不复制未授权音频。AI 生成的听力材料与题目:按 shared/ai-item-check.md 自检(答案在录音里能直接听到、
干扰项来自原文的相近信息、词汇不超该学段词表),输出时一律标注
【AI 生成,入库前请人工验算】;未经老师确认不得入库或进卷
(对应 classWorkspace.examBlueprints[].items[].aiGenerated / verifiedByTeacher)。
⚠️ 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。 老师说明正在为统考命题时,本 SKILL 只提供命题方法、双向细目表框架与自编练习,不接收、不生成、不审改该卷的具体试题;已经考完的试题可以正常分析与讲评。跨校联考要等参加的学校全部考完,外语听说考试这类分几天、分批进行的考试要等全部批次、全部场次考完;同一份卷子还有学生补考的,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。 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”。
英语听力教学常见的三个误区:
误区① 听力=刷题:让学员做大量听力题,
学员只关注"对错",没关注"听懂"。
误区② 听力=逐字听:让学员听写每个词,
学员压力大,没建立"听"的整体感。
误区③ 听力=只听不教:只放录音、对答案,
没教听力策略、没训练微技能。本 SKILL 要解决的是:
| 触发场景 | 示例语句 |
|---|---|
| 听力教学 | "听力怎么教" |
| 听力材料 | "听力材料选什么" |
| 学员听不懂 | "学员听不懂" |
| 听力策略 | "听力策略怎么教" |
| 听力微技能 | "听力微技能" |
| 精听/泛听 | "精听/泛听" |
| 听写训练 | "听写怎么练" |
| 学员听力弱 | "学员听力弱" |
┌──────────────────────────┐
│ ① 听力目标 │
│ 主旨/细节/推断/观点 │
└────────────┬─────────────┘
↓
┌──────────────────────────┐
│ ② 材料选编 │
│ 来源/难度/主题 │
└────────────┬─────────────┘
↓
┌──────────────────────────┐
│ ③ 听前预测 │
│ 标题/图片/问题 │
└────────────┬─────────────┘
↓
┌──────────────────────────┐
│ ④ 听中分层 │
│ 主旨/细节/推断 │
└────────────┬─────────────┘
↓
┌──────────────────────────┐
│ ⑤ 听后任务 │
│ 复述/讨论/写 │
└────────────┬─────────────┘
↓
┌──────────────────────────┐
│ ⑥ 微技能训练 │
│ → 学员档案 │
└────────────┬─────────────┘
↓
┌──────────────────────────┐
│ ⑦ 写回 student-analyzer │
│ 听力能力维度 │
└──────────────────────────┘排题型时按中考听力的实际结构走,不用托福/雅思式的"主旨/细节/推断/观点"四分法命题。 那四类是能力目标,中考的四节是题型载体——目标藏在题型里,不单独成节。
┌──────────────────┬──────────────────────┬────────────────────────┐
│ 中考听力节次 │ 主要考的能力目标 │ 材料形态 │
├──────────────────┼──────────────────────┼────────────────────────┤
│ 第一节 听句选图/ │ 细节(关键词捕捉) │ 单句或一问一答,读两遍 │
│ 短对话选答语 │ │ │
│ 第二节 对话理解 │ 细节 + 关系/意图 │ 2-3 段对话,每段 3-4 问 │
│ 第三节 短文理解 │ 主旨 + 细节 + 推断 │ 1-2 篇短文 │
│ 第四节 听填信息 │ 细节(精确到词形拼写)│ 表格/笔记填空,读三遍 │
└──────────────────┴──────────────────────┴────────────────────────┘
语速:约 100-120 词/分钟(各地中考听力的常见区间)。
观点/态度题在中考里通常并入短文理解,不单设一节;课堂训练可单练,命题不必单列。
⚠️ 第四节"听填信息"最容易被省掉,但它是唯一无法靠排除法蒙对的题型——
最能区分"真听懂了"和"猜对了"。设计整卷时不要省。■ 基础层
· 抓主旨 + 关键细节
· 关键词识别
■ 中等层
· 主旨 + 细节 + 简单推断
· 数字/时间/地点
■ 提升层
· 主旨 + 细节 + 推断 + 观点
· 言外之意/讽刺┌──────────────┬────────────────────────┬──────────────┐
│ copyrightStatus │ 说明 │ 适用 │
├──────────────┼────────────────────────┼──────────────┤
│ 自有 │ 老师自录 / 原创文本 │ 针对本班 │
│ 改编 │ 在自有或公开材料上改编 │ 调难度用 │
│ 公开可引用 │ 明确允许教学使用的公开材料 │ 拓展 │
│ 仅存索引 │ 教辅原题、历年真题 │ 只记出处,不复制内容 │
└──────────────┴────────────────────────┴──────────────┘
教材配套音频:按学校获得的授权范围在课堂内使用,不外传、不入公开资源库。■ 可懂率:**首次听后能听懂约 90%**(全库唯一口径)
· 换算成生词:生词密度 ≤ 2-3%,约 3-8 个新词
· 依据:词汇覆盖率低于 95% 时,学员无法靠上下文补全,
只能猜整段大意,练的就不是听力了
· ⚠️ 不使用"可懂 70%"这一档:三成内容听不懂时,
学员在课堂上的实际反应是放弃跟读,不是"跳一跳"
■ 语速:按学段取(与学生端听力训练师同一套)
· 小学高段 90-100 / 初一 100 / 初二 110 / 初三 120 词/分钟
· 上限就是中考语速;练得比中考快没有意义
■ 难度的四个可调项(先调前两项,再考虑后两项)
· 生词个数 → 语速 → 句长 → 话题熟悉度┌──────────┬────────────────────────┬────────────────────┐
│ 类型 │ 例子 │ 对应中考节次 │
├──────────┼────────────────────────┼────────────────────┤
│ 短对话 │ 问路/买东西/约时间 │ 第一、二节 │
│ 长对话 │ 计划活动/讨论问题 │ 第二节 │
│ 独白/短文 │ 通知/介绍/个人经历 │ 第三节 │
│ 信息型 │ 表格式通知/日程/天气 │ 第四节(听填信息) │
│ 故事 │ 短篇故事 │ 第三节的拓展 │
│ 影视片段 │ 动画/纪录片节选 │ 课堂拓展,不进测评 │
└──────────┴────────────────────────┴────────────────────┘■ 主题贴近学员
· 学员生活相关
· 学员兴趣相关
■ 难度略高于水平
· 首听可懂约 90%(生词 ≤2-3%),语速按学段(§5.2)
· 有"跳一跳"感,但不是"够不着"
■ 类型多样
· 对话 + 独白 + 新闻 + 故事
· 不同口音/语速
■ 来源合法
· 标注 copyrightStatus
· 不复制未授权材料✅ 每条材料入库时必须填 copyrightStatus(自有 / 改编 / 公开可引用 / 仅存索引)
✅ 教辅原题与历年真题一律 `仅存索引`:只记出处与题号,不复制内容进资源库
✅ 教材配套音频:按学校授权范围在课堂内使用
❌ 禁止:未授权复制音频文件
❌ 禁止:未授权转载 podcast、把付费内容录下来分发
❌ 禁止:把来源不明的音频放进班级共享资料┌──────────┬────────────────────────┐
│ 方法 │ 描述 │
├──────────┼────────────────────────┤
│ 标题 │ 看标题预测内容 │
│ 图片 │ 看图预测场景 │
│ 问题 │ 看问题预测答案 │
└──────────┴────────────────────────┘📎 完整样板见
references/pre-listening-prediction-sample.md(听前预测样板:材料/预测/听前活动/听中目标)
■ 激活背景知识
· 学员已有知识
· 让学员"有准备"
■ 降低焦虑
· 学员不是"完全陌生"
· 有"可预测"
■ 提升专注
· 学员"想知道对不对"
· 听的时候更专注■ 第一遍(泛听)
· 抓主旨
· 不查细节
· 让学员有"整体感"
■ 第二遍(精听)
· 抓细节
· 关键词
· 数字/时间/地点
■ 第三遍(推断)
· 推断
· 言外之意
· 说话人态度┌──────────┬────────────────────────┐
│ 听法 │ 任务 │
├──────────┼────────────────────────┤
│ 泛听 │ 主旨题 │
│ 精听 │ 细节题 │
│ 推断 │ 推断题/观点题 │
└──────────┴────────────────────────┘📎 完整样板见
references/while-listening-task-sample.md(三遍听法对应的听中任务设计样板)
■ 抓关键词
· 不强求"每个词都懂"
· 抓住"实词"
■ 记笔记
· 数字/时间/地点
· 关键信息
■ 预测验证
· 听前预测对吗?
· 听到什么?┌──────────┬────────────────────────┐
│ 任务 │ 描述 │
├──────────┼────────────────────────┤
│ 复述 │ 学员用自己的话讲 │
│ 讨论 │ 围绕主题讨论 │
│ 写 │ 写读后感/概要 │
└──────────┴────────────────────────┘■ 关键词复述(最常用,负担最低)
· 老师给 3-5 个关键词,学员据此复述
· 一条指令说完:"用这几个词,说说他们在聊什么。"
· 适合大部分课堂情境
■ 概要复述
· 学员用自己的话讲主要内容,2-3 句
· 适合短文材料
■ 角色复述
· 学员扮演材料中的一方,用第一人称讲
· 适合对话材料
⚠️ 不要求"逐字复述":逐字复述考的是短时记忆容量,不是听力理解,
而且失败率高、挫败感强。要检查细节请用听填信息,不要用逐字复述。
⚠️ 一次只给一条指令。"用自己的话说 3-5 句、不要翻译原文、说你记住的就好、
不要求完整"——四条要求叠在一起,学员的负担比听力本身还大。■ 围绕主题
· 学员讨论材料主题
· 联系自己的生活
■ 角色讨论
· 学员扮演材料中的角色
· 表达观点■ 概要
· 学员写 100-200 字概要
■ 读后感
· 学员写"我的看法"
■ 同主题写作
· 学员围绕同主题写本表是唯一的微技能清单。
references/micro-skill-training.md的训练法、references/listening-rubric.md的评分、student-listening-profile-template.md的档案栏位 都按这一套走,不再另立第二套名称。
┌────┬──────────────┬────────────────────────┬──────────────────┐
│ 编号│ 微技能 │ 描述 │ 主要在哪一节考 │
├────┼──────────────┼────────────────────────┼──────────────────┤
│ M1 │ 抓主旨 │ 听出"整段在讲什么" │ 第三节 短文理解 │
│ M2 │ 抓细节 │ 听出具体信息 │ 第一、二节 │
│ M3 │ 抓数字/时间 │ 听准数字、时间、价格 │ 第二、四节 │
│ M4 │ 抓转折 │ 听出 but / however 之后 │ 第二、三节 │
│ M5 │ 抓连接 │ 听出 first/then/finally │ 第三、四节 │
│ M6 │ 抓语气 │ 听出说话人态度与意图 │ 第二、三节 │
│ M7 │ 推断 │ 听出没有明说的信息 │ 第三节 │
│ M8 │ 记笔记 │ 边听边记关键词 │ 第四节 听填信息 │
└────┴──────────────┴────────────────────────┴──────────────────┘
⚠️ 旧版曾出现过第二套名称("预测/猜测词义/理解意图/捕捉主旨"),已废弃。
"听前预测"是**教学环节**(§六),不是微技能;
"猜测词义"归入词汇,由词汇教学处理,不占听力微技能的位置。■ M1 抓主旨:听前预测 → 听首尾句 → 一句话说主题(不查细节)
■ M2 抓细节:先看题干圈关键词 → 带着问题听 → 只记实词
■ M3 抓数字/时间:先提示"这段有 3 个数字" → 专门听 → 听后核对
■ M4 抓转折:先只听 but / however / although,再听它后面的内容
■ M5 抓连接:听 first / then / next / finally,排出事件顺序
■ M6 抓语气:同一句话用三种语气读,让学员判断态度
■ M7 推断:先说出"我猜他会…",听后修正,并说"我是从哪句听出来的"
■ M8 记笔记:只记名词、数字、动词原形,用符号缩写;听后互看笔记
训练顺序:M2 → M3 → M1 → M5 → M4 → M6 → M8 → M7(由具体到综合)■ 听写三阶段
· 阶段 1:听写短句(5-10 词)
· 阶段 2:听写长句(15-25 词)
· 阶段 3:听写段落(50-100 词)
■ 听写法
· 听 1 遍:抓主旨
· 听 2-3 遍:补全
· 对照原文
· 学员自己发现错误
■ 听写频率
· 每周 1-2 次
· 不频繁(学员压力大)┌──────────────┬────────────────────────────────┐
│ 栏位 │ 记什么 │
├──────────────┼────────────────────────────────┤
│ M1-M8 微技能 │ 每项标 ✓/✗ 或 [N]/5,来源是逐题得分 │
│ 舒适语速 │ 该学员能稳定听懂的语速档(词/分钟) │
│ 弱项状态 │ 按 shared/vocab.md §4 五档记录 │
└──────────────┴────────────────────────────────┘
⚠️ 不记"听力词汇量 N 词"——课堂上没有可靠的测量手段,填了就是编数字。
要描述词汇,就写"哪一类词听不出来"(如"数字连读听不出""人名地名一带而过就丢")。📎 完整模板见
references/student-listening-profile-template.md(听力档案模板:四维评分/微技能/词汇量/听音速度/进步记录)
┌────────────────────────┐
│ xiaozhi-teach- │
│ lesson-planner │
│ (听力任务嵌入教案) │
└───────────┬────────────┘
│
↓
┌────────────────────────┐
│ 课堂(听力教学) │
└───────────┬────────────┘
│
↓
┌────────────────────────┐
│ xiaozhi-teach- │
│ english-listening- │
│ designer(本 SKILL) │
└───────────┬────────────┘
│
┌─────────────────┼─────────────────┐
↓ ↓ ↓
student-analyzer resource-library parent-communication
(听力能力维度) (听力素材入库) (独立教师的家长反馈)shared/class-teaching-workspace.schema.json)读:
classWorkspace.classProfile → 学段、班额、课时(决定语速档与听力时长)
classWorkspace.lessonPlans[] → 本课教案与 segments(听力任务嵌在哪一段)
classWorkspace.itemScores[] → 听力各题得分(微技能强弱的唯一来源;
只有总分时不得生成微技能画像)
classWorkspace.itemStats[] → 听力题的难度 P / 区分度 D
classWorkspace.weaknessRank[] → 班级听力弱项排序
classWorkspace.reviewPlans[] → 同一场考试是否已有复习计划(有就在原计划上补充)
写(均为待老师确认的条目,确认后落库):
classWorkspace.lessonPlans[].segments[] → 听前/听中/听后三段的活动与分钟数
classWorkspace.examBlueprints[].items[] → 听力题条目(itemType = "听力")
AI 生成题 aiGenerated=true,
老师验算后才可 verifiedByTeacher=true
classWorkspace.weaknessRank[] → 由听力题得分归纳出的弱项条目
· weaknessId / knowledgePoint / errorRate / dimension / evidenceExamIds[] / lastUpdated
(不写 .stubbornCount——顽固计数由 xiaozhi-teach-student-analyzer 唯一累加)
classWorkspace.reviewPlans[] → 微技能训练的排布,只写英语听力条目;
同一场考试已有复习计划时在原计划上补充,不另起一份;
写入守复习规划师的三道门:老师确认、只用化名、不写个体分数与名次
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 写微技能名如"听力·听填信息"),note 只写低敏事实描述
❌ 不写等级、不写学员真实姓名、不写"某某听力差"这类评价✅ 听力档案用化名
✅ 学员听力测试脱敏
❌ 禁止:公开"某学员的听力差"
❌ 禁止:未授权公开听力材料
✅ 听力素材可入库(脱敏后)| ✅ 应该做 | ❌ 不能做 |
|---|---|
| 听力目标(主旨/细节/推断/观点) | 听力=刷题 |
| 材料首听可懂约 90% | 听写=逐字复述 |
| 听前预测 | 只听不教 |
| 三遍听法 | 一遍就完事 |
| 微技能训练 | 学员不学策略 |
| 听力档案累积 | 学员不积累 |
| 学员化名 | 公开批评学员听力 |
英语听力材料设计
<── xiaozhi-teach-lesson-planner(听力任务嵌入教案)
<── xiaozhi-teach-student-analyzer(学情/弱项)
──→ xiaozhi-teach-student-analyzer(听力能力维度;学校班级的家长版,由它核对 parentSharingConsent)
──→ xiaozhi-teach-resource-library(听力素材入库)
──→ xiaozhi-teach-parent-communication(独立教师:听力进步反馈)
──→ 学生端 xiaozhi-english-listening-trainer(学员视角;语速档与生词密度两端一致)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 的语篇类型、表 10 的理解性技能与"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;初中仍按第四至十节。
references/listening-material-sources.md — 听力材料来源清单(5 类来源 × 学段矩阵)references/micro-skill-training.md — 微技能训练法(8 个微技能 + 训练步骤)references/listening-rubric.md — 听力评估评分细则(4 题型 + CEFR 等级)references/pre-listening-prediction-sample.md — 听前预测样板references/while-listening-task-sample.md — 听中任务设计样板references/student-listening-profile-template.md — 学员听力档案模板💡 小智说: "听力不是'听每个词', 是'用英语获取信息'。 当学员能听懂一段对话的'意思', 能听出言外之意, 能感受到说话人的态度—— 那才是真的'会听英语'。"
© 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-listening-designer of qizhitang/xiaozhi-skills.
Open the folder on GitHubat commit c65f2d4
Xiaozhi Teach English Listening 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 Listening Designer this skillqizhitang/xiaozhi-skills | 105 | — | ~4k | 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
英语听力教学设计:把"放一遍录音对答案"变成有目标、有策略、有微技能训练的听力课. An agent skill from qizhitang/xiaozhi-skills. Xiaozhi Teach English Listening Designer is an agent skill from qizhitang/xiaozhi-skills.
Xiaozhi Teach English Listening Designer fits situations like: education work in your project.
Run `npx skills add qizhitang/xiaozhi-skills --skill xiaozhi-teach-english-listening-designer -a claude-code`. Or copy the skill folder (teacher/english/xiaozhi-teach-english-listening-designer in qizhitang/xiaozhi-skills) into .claude/skills/xiaozhi-teach-english-listening-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-listening-designer -a codex`. Or copy the skill folder (teacher/english/xiaozhi-teach-english-listening-designer in qizhitang/xiaozhi-skills) into .agents/skills/xiaozhi-teach-english-listening-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-listening-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-listening-designer, .gemini/skills/xiaozhi-teach-english-listening-designer, .github/skills/xiaozhi-teach-english-listening-designer and .opencode/skills/xiaozhi-teach-english-listening-designer in your project.
SKILL.md names no scripts, command-line tools or credentials: Xiaozhi Teach English Listening 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 Listening 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 4k tokens (SKILL.md is roughly 16k 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 Listening 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.