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.
英语综合测评设计:帮英语老师把"一张卷子"变成听说读写四维的能力测评与画像;高中按合格性考试与高考的课标口径设计. An agent skill from qizhitang/xiaozhi-skills.
$ npx skills add qizhitang/xiaozhi-skills --skill xiaozhi-teach-english-assessment -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-teach-english-assessment --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-assessment .claude/skills/xiaozhi-teach-english-assessment && 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-assessment" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/teacher/english/xiaozhi-teach-english-assessment into .claude/skills/xiaozhi-teach-english-assessment/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-teach-english-assessment", 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-assessmentType 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-assessment -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-teach-english-assessment --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-assessment .agents/skills/xiaozhi-teach-english-assessment && 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-assessment" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/teacher/english/xiaozhi-teach-english-assessment into .agents/skills/xiaozhi-teach-english-assessment/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-teach-english-assessment", 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-assessment -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-teach-english-assessment --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-assessment .cursor/skills/xiaozhi-teach-english-assessment && 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-assessment" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/teacher/english/xiaozhi-teach-english-assessment into .cursor/skills/xiaozhi-teach-english-assessment/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-teach-english-assessment", 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-assessment--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-assessment -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-teach-english-assessment --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-assessment .gemini/skills/xiaozhi-teach-english-assessment && 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-assessment" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/teacher/english/xiaozhi-teach-english-assessment into .gemini/skills/xiaozhi-teach-english-assessment/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-teach-english-assessment", 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-assessmentInstalls 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-assessment -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-assessment .github/skills/xiaozhi-teach-english-assessment && 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-assessment" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/teacher/english/xiaozhi-teach-english-assessment into .github/skills/xiaozhi-teach-english-assessment/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-teach-english-assessment", 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-assessment -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-assessment --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-assessment .opencode/skills/xiaozhi-teach-english-assessment && 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-assessment" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/teacher/english/xiaozhi-teach-english-assessment into .opencode/skills/xiaozhi-teach-english-assessment/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-teach-english-assessment", 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-assessment英语综合测评设计:帮英语老师把"一张卷子"变成听说读写四维的能力测评与画像;高中按合格性考试与高考的课标口径设计. An agent skill from qizhitang/xiaozhi-skills.
Xiaozhi Teach English Assessment is an agent skill from qizhitang/xiaozhi-skills. 英语综合测评设计:帮英语老师把"一张卷子"变成听说读写四维的能力测评与画像;高中按合格性考试与高考的课标口径设计。 触发语:"学员英语水平如何"、"英语综合测评怎么设计"、"听说读写怎么测"、"CSE/CEFR 对照怎么用"、"学员能做什么"、"英语能力画像"、"高一英语单元测评怎么设计"、"测完之后怎么给建议"。 核心工作流:能力目标(听说读写 4 维)→ 以 CSE 描述语定级、CEFR 只作国际参照 → 测评设计 → 能力画像(分数 + 微技能)→ 教学干预建议 → 写回班级工作空间。 不处理:听力材料的选编与听法训练(转英语听力材料设计)、口语活动与纠错策略(转英语口语活动设计)、通用命题的双向细目表(转 xiaozhi-teach-exam-designer)、考后的信度与区分度统计(转 xiaozhi-teach-student-analyzer)。
Its SKILL.md is about 4.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 19 other files, including reference files (for example `references/assessment-template.md`, `references/cefr-can-do-statements.md` and `references/cefr-four-skill-descriptors.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 (its code samples are json).
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 Assessment loads about 4.1k tokens when it runs, and up to ~15k if it reads all its reference files. Until then it costs about 105 tokens; SKILL.md has 419 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). 419 words, ~4,120 tokens.
.claude/skills/xiaozhi-teach-english-assessment/SKILL.md (or your agent's skills folder). This skill also uses 17 other files; get the full folder from GitHub.一句话定位: 英语测评不是给学员"打分数",而是给教学"画能力地图"——以 CSE 为主、CEFR 为参照的能力框架是核心。
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 时不输出跨次的等级变化统计,只呈现本次测评数据;无 F 时请老师粘贴逐题分数表格。
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:
copyrightStatus(自有 / 改编 / 公开可引用 / 仅存索引);不复制未授权材料。AI 生成的题目:按 shared/ai-item-check.md 自检后输出,且一律标注
【AI 生成,入库前请人工验算】;未经老师确认不得写入资源库或试卷
(对应 classWorkspace.examBlueprints[].items[].aiGenerated / verifiedByTeacher)。
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,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”。
英语综合测评常见的三个误区:
误区① 测评=笔试:只测读写,
学员"会做卷"但"不会用"。
误区② 测评=分数:只关心分数,
没看学员"能做什么"。
误区③ 测评=一刀切:所有学员同一份卷,
没考虑学员的实际水平。本 SKILL 要解决的是:
| 触发场景 | 示例语句 |
|---|---|
| 学员英语水平 | "学员英语水平如何" |
| 英语综合测评 | "英语综合测评" |
| 听说读写 | "听说读写怎么测" |
| 能力等级对照 | "CSE/CEFR 对照怎么用" |
| 学员能做什么 | "学员能做什么" |
| 英语水平档案 | "英语水平档案" |
| 英语能力评估 | "英语能力评估" |
| 学员英语弱 | "学员英语弱" |
┌──────────────────────────┐
│ ① 能力目标 │
│ 听说读写 4 维 │
└────────────┬─────────────┘
↓
┌──────────────────────────┐
│ ② 等级对照 │
│ CSE 为主,CEFR 参照 │
└────────────┬─────────────┘
↓
┌──────────────────────────┐
│ ③ 综合测评设计 │
│ 听/口/读/写 │
└────────────┬─────────────┘
↓
┌──────────────────────────┐
│ ④ 学员能力画像 │
│ 4 维 + 微技能 │
└────────────┬─────────────┘
↓
┌──────────────────────────┐
│ ⑤ 教学干预建议 │
│ 班级+个体 │
└────────────┬─────────────┘
↓
┌──────────────────────────┐
│ ⑥ 写回 student-analyzer │
│ 英语能力维度 │
└──────────────────────────┘┌──────────┬────────────────────────┬──────────────┐
│ 维度 │ 描述 │ 能力 │
├──────────┼────────────────────────┼──────────────┤
│ 听 │ 听懂英语 │ 输入-听觉 │
│ 说 │ 用英语说话 │ 输出-口语 │
│ 读 │ 读懂英语 │ 输入-视觉 │
│ 写 │ 用英语写 │ 输出-书面 │
└──────────┴────────────────────────┴──────────────┘■ 输入 vs 输出
· 听 + 读 = 输入
· 说 + 写 = 输出
■ 输入与输出关系
· 学员需要先有输入
· 才有输出
■ 4 维协同
· 4 维不能割裂
· 综合使用■ 基础层
· 听:听懂简单句
· 说:能用单词/短句
· 读:看懂短文
· 写:能写简单句
■ 中等层
· 听:听懂日常对话
· 说:能流利对话
· 读:看懂中长文
· 写:能写短文
■ 提升层
· 听:听懂复杂材料
· 说:能表达观点
· 读:看懂专业文章
· 写:能写各类文章口径说明: 对 K12 应以《中国英语能力等级量表》(CSE,GF 0018—2024,九级;2018 年首次发布,修订版 2024 年 11 月 26 日发布、2025 年 3 月 1 日起实施,代替 2018 年版)为主标准,CEFR 只作国际参照。切勿把等级对标定得过高——常见误区是把"初中毕业"标成 B1、"高中毕业"标成 B2。按量表发布时的通行解读,中考约当 CSE 三级,高考约当 CSE 四级,大学英语四级约当五级,大学英语六级约当六级。CSE 与 CEFR 的对接随技能不同而有差异;以写作能力的对接研究为例,CSE 三级约当 A2,四级、五级都约当 B1,六级约当 B2,七级约当 C1。
┌──────────┬────────────────────────────┬──────────────────────┐
│ CSE │ 学段 / 考试(约当) │ CEFR 参照(写作为例) │
├──────────┼────────────────────────────┼──────────────────────┤
│ 一至二级 │ 小学(二级约当小学毕业) │ A1 │
│ 三级 │ 初中毕业 / 中考 │ A2 │
│ 四级 │ 高中毕业 / 高考 │ B1 │
│ 五级 │ 大学英语四级 │ B1 │
│ 六级 │ 大学英语六级、英语专业四级 │ B2 │
│ 七级 │ 研究生、英语专业八级 │ C1 │
│ 八至九级 │ 高端外语人才 │ C1—C2 及以上 │
└──────────┴────────────────────────────┴──────────────────────┘
(都是"约当"关系,不是等值;CEFR 一列只是写作能力对接研究的结果,别的技能、不同来源的对接结果都可能差一档;定级以 CSE 描述语原文为准)❌ 禁止:由卷面分数或正确率直接换算等级
(如"70 分 = B2""正确率 55-69% = B1")。
理由有三:
① 分数只反映"这张卷上的这些题",题目难度不同,同一个分数含义完全不同;
② CSE/CEFR 是**能力描述**框架,判定依据是"能不能完成某类任务",不是得了多少分;
③ 直接换算最容易把 K12 学员的等级抬高,给学员和家长错误预期。
✅ 正确做法(三步):
Step 1 看逐题得分(classWorkspace.itemScores[]),确认学员在哪些
**任务类型**上稳定完成、哪些不稳定
Step 2 拿这些表现去对照 CSE 相应等级的描述语
("能听懂…""能就…作简单描述"),由老师判断落在哪一级
Step 3 等级写成区间 + 证据,如
"听:CSE 3(约当 A2)——两次测评都能听懂日常对话中的时间与地点,
但短文推断题两次都错"
单次测评、样本不足时标 🔴(shared/vocab.md §7),只作参考不入档案
分数的用途:定位强弱维度、看进退步、决定下一步教什么——不是用来贴等级的。📎 CSE 各级描述语以教育部发布的量表原文(现行 2024 年修订版)为准;
references/cefr-four-skill-descriptors.md提供 CEFR 侧的四维简表,仅作国际参照。
⚠️ 旧版有两张对照表,都已订正并合成 §5.1 一张:
- 中考 / 初中毕业 ≈ CSE 三级(约当 A2),不是 B1,也不是"CSE 3-4";
- 高考 / 高中毕业 ≈ CSE 四级(约当 B1),不是 B2;旧版写的"高考约 CSE 5"偏高一级——CSE 五级约当大学英语四级;
- 大学英语四级 ≈ CSE 五级(约当 B1),不是 B2;
- 英语专业八级 ≈ CSE 七级(约当 C1),不是 CSE 8。 对 K12 学员定级时优先用 CSE 描述语,避免因 CEFR 定标过高而对学员/家长造成不合理预期。
┌──────────┬────────────────────────┬──────────────┐
│ 类型 │ 描述 │ 时机 │
├──────────┼────────────────────────┼──────────────┤
│ 诊断性 │ 查起点 │ 学期初、单元开始 │
│ 形成性 │ 给反馈、看进步 │ 单元教学过程中 │
│ 终结性 │ 评掌握 │ 期中、期末(高中另含单元末测验) │
└──────────┴────────────────────────┴──────────────┘义务教育阶段:单元的形成性评价用单元练习(随堂练习:穿插在课堂教学里,单次一般不超过 20 分钟,不组织成考试、不计总分、不排名,反馈写知识点诊断),诊断性摸底也用随堂练习做;考试只有期末(初中可加一次期中,九年级在总复习阶段可有 1—2 次模拟考试)。(与 xiaozhi-teach-exam-designer §四 同一口径)
■ 听力(题型按中考听力结构排,不用托福/雅思式分类)
· 时长:20-25 分钟(含播音)
· 题型:听句选图(或短对话选答语)→ 对话理解 → 短文理解 → 听填信息
· 语速:约 100-120 词/分钟(中考听力常见区间)
· 详细题型设计见「英语听力材料设计」SKILL
■ 口语(校内班级测评的现实约束见下)
· 时长:单人 3-5 分钟(不是 10-15 分钟)
· 题型:朗读 → 情景问答 → 看图/话题连续表达
· 组织:分批或分组进行,见下方"班额可行性"
■ 阅读
· 时长:30-40 分钟
· 题型:细节 → 主旨 → 推断 → 词义猜测(按中考阅读的题型比重)
· 难度:略高于日常教学材料
■ 写作
· 时长:20-25 分钟
· 题型:以应用文(书信/邮件/通知)与记叙文为主;
议论文只在初三下学期按本地中考题型需要时才考
· 字数:初中 80-100 词口语测评的班额可行性(先算,再排)
所需课时 ≈ 班额 × 单人时长 ÷ 并行考场数 ÷ 45 分钟
例:50 人班,单人 4 分钟,1 位老师逐个考
→ 50 × 4 = 200 分钟 ≈ 4.5 节课,不现实
可行的三种排法(老师选一种,本 SKILL 不替老师决定):
① 双人同考:两名学员一组做对话任务,单组 5 分钟
→ 25 组 × 5 = 125 分钟 ≈ 3 节课,仍偏多,适合期末的口语测评(照学校安排)
② 抽样 + 全员录音:课上抽 8-10 人现场考(作为定标样本),
其余学员在校内(课内或课后在学校里)按同一套任务录音,老师按同一份 rubric 评;
不要求学生回家用手机录音提交
→ 课上约 40 分钟,1 节课内完成
③ 分组轮转:全班分 4-5 组,一组做口语任务、其余组做笔试部分,轮换
→ 1-2 节课内完成,需另一位老师或助教协助计时
义务教育阶段整班的口语测评放在期末(初中可在期中),照学校安排;单元里的口语练习按随堂练习做,
每次一般不超过 20 分钟,不整节课考。
⚠️ 若排不出时间:宁可缩短单人时长或降低频次,
也不要把 25 分的口语分改成"平时印象分"——那不是测评。⚠️ 本 SKILL 是通用
xiaozhi-teach-exam-designer的英语学科细化,不是替代。 双向细目表的测量学基础——难度系数 P、区分度 D、四类测评目的、考后实际 P/实际 D 分析——沿用通用版定义;本 SKILL 只补充听说读写四维的能力描述与 CSE/CEFR 对照,不重定义、不删减测量学工具。
■ 听力双向细目表
· 主旨 + 细节 + 推断 + 观点
■ 口语双向细目表
· 流利 + 准确 + 得体
■ 阅读双向细目表
· 字面理解 + 推断理解 + 评价理解
■ 写作双向细目表
· 内容 + 结构 + 语言 + 规范📎 完整样板见
references/comprehensive-assessment-sample.md(听/说/读/写 4 维加权的综合测评结构示例)
┌──────────┬────────────────────────┐
│ 维度 │ 描述 │
├──────────┼────────────────────────┤
│ 听 │ 听力能力 │
│ 说 │ 口语能力 │
│ 读 │ 阅读能力 │
│ 写 │ 写作能力 │
│ 词汇 │ 词汇量 │
│ 语法 │ 语法能力 │
│ 等级判定 │ 由老师对照 CSE 描述语给出(不由分数换算) │
│ 强项 │ 强维度 │
│ 弱项 │ 弱维度 │
└──────────┴────────────────────────┘📎 完整模板见
references/student-ability-profile-template.md(4 维等级 + 微技能 + 词汇/语法 + 强弱项的填写模板)
听
│ ┌───
│ / 5
│ /
│/_____
说 读
│ ╲
│ ╲
│ ╲
写┌──────────┬────────────────────────┐
│ 弱维度 │ 干预 │
├──────────┼────────────────────────┤
│ 听 │ 听力材料+微技能训练 │
│ 说 │ 任务型活动+情境练习 │
│ 读 │ 阅读策略+分级阅读 │
│ 写 │ 写作模板+过程引导 │
└──────────┴────────────────────────┘分档依据:2022 版义教英语课标三级词汇表约 1600 词(中考范围);
高中课标附录 2 共 3100 词(含义教 1600 词;必修累计约 2100、选择性必修累计约 3100)⚠高中。
· 课标 1600 词内、掌握不足 → 先把这部分补齐(中考绝大多数考点在此范围)
做法:按话题成组补(校园/健康/环保/文化/成长),不按字母表背
· 课标 1600 词已基本掌握 → 补中考语篇里的高频超纲词(只求读到时认得出)
做法:从近年本地中考真题语篇里取词,不另找词表
· 已超出中考需求、学员主动要求 → 高中课标词表 ⚠高中
做法:说明这是高中内容,按学员意愿安排,不计入本学段的达标判断
❌ 不用 AWL 分级 ⚠高中(大学学术写作场景才用得着;高中学员同样不用):AWL 取自英语学术论文语料,
与义教课标、中考语篇的词频分布不一致,对初中生会把方向带偏。
❌ 不用"主动词汇 N 词"这类估计值做分档依据——课堂上没有可靠的测量手段。📎 完整样板见
references/intervention-suggestion-sample.md(短/中/长期干预建议 + 资源推荐 + 复测评估示例)
■ 每次测评
· 更新 4 维档案
· 标记进步/退步
■ 每月复盘
· 4 维能力变化
· 强项弱项变化
· 调整教学📎 完整样板见
references/english-growth-archive-sample.md(时间轴 + 4 维进步 + 持续弱项 + 教学调整示例)
┌────────────────────────┐
│ xiaozhi-teach- │
│ student-analyzer │
│ (学员 4 维能力数据) │
└───────────┬────────────┘
│
↓
┌────────────────────────┐
│ xiaozhi-teach- │
│ english-assessment │
│ (本 SKILL) │
└───────────┬────────────┘
│
┌─────────────────┼─────────────────┐
↓ ↓ ↓
student-analyzer lesson-planner resource-library
(4 维能力画像) (教学干预计划) (4 维素材)shared/class-teaching-workspace.schema.json)读:
classWorkspace.classProfile → 学段、班额、课时、常用满分
classWorkspace.itemScores[] → 逐题得分(能力画像的唯一来源;
只有总分时不得生成逐维度画像)
classWorkspace.itemStats[] → 各题难度 P / 区分度 D
classWorkspace.classSummaries[] → 班级均分、得分率、分布
classWorkspace.weaknessRank[] → 班级顽固弱项排序
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.examBlueprints[] → 四维测评蓝图(含 itemType: 听力/口语/阅读/写作)
AI 生成题 aiGenerated=true,
老师验算后才可 verifiedByTeacher=true
classWorkspace.weaknessRank[] → 由四维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[] → 干预建议转成的复习排布,只写英语条目;
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 / knowledgePoint /
status / masteryLevel),note 只写低敏事实描述
掌握度转换(shared/vocab.md §6):老师端五档 → 学生端三档,写回时必须转换
已掌握 → 真正掌握 / 基本理解 → 会解释 / 仍需巩固 → 会复述
需要重讲 → 会复述(并在 note 里注明"复述也不完整")
证据不足 → 不写入这一条
❌ 不写 CSE/CEFR 等级、不写学员真实姓名、不写心理标签写回学生档案的交接示例(与 handover-protocol.schema.json v2.1 一致):
{
"sessionId": "sess-teach-eng-assess-001",
"protocolVersion": "2.11.1",
"handoverType": "teacher_writeback",
"sender": "xiaozhi-teach-english-assessment",
"recipient": "xiaozhi-learning-dna",
"consent": { "crossSkillSharing": true, "teacherWritebackConsent": true },
"payload": {
"teacherWritebackData": {
"teacherSkill": "xiaozhi-teach-english-assessment",
"studentAlias": "E-007",
"weakKnowledgePointUpdates": [
{ "subject": "英语", "knowledgePoint": "听力·听填信息", "status": "初步弱项", "masteryLevel": "会复述" }
],
"note": "两次测评中听填信息题得分率明显低于同卷其他听力题型"
}
},
"timestamp": "2026-09-03T18:00:00+08:00"
}✅ 能力画像用化名
✅ 班级报告用编号
❌ 禁止:公开"某学员的英语等级"
❌ 禁止:未授权公开测评材料
✅ 测评结果可入档案(脱敏后)| ✅ 应该做 | ❌ 不能做 |
|---|---|
| 4 维综合(听说读写) | 测评=笔试 |
| 对照 CSE 描述语判等级 | 分数直接换算等级 |
| 能力画像 | 测评=一刀切 |
| 4 维差异 | 单一分数 |
| 教学干预 | 测完就完事 |
| 学员化名 | 公开学员等级 |
英语综合测评
<── xiaozhi-teach-student-analyzer(4 维能力)
<── xiaozhi-teach-lesson-planner(教学计划)
──→ xiaozhi-teach-student-analyzer(4 维画像)
──→ xiaozhi-teach-lesson-planner(教学干预)
──→ xiaozhi-teach-resource-library(4 维素材)
──→ 学生端 5 个英语 SKILL(语法/听力/口语/词汇/写作,学员视角)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)》"学业水平考试与高考建议"。老师说明带的是高中班,或学员在读高中时用本节;初中仍按第四至九节。
| 项 | 合格性考试 | 高考 |
|---|---|---|
| 内容范围 | 必修 | 必修与选择性必修 |
| 水平要求 | 可参照学业质量水平一 | 可参照学业质量水平一和水平二 |
| 形式 | 一般采用笔试,包括听力考试;有条件的地区可以实施口试 | 一般采用笔试(闭卷,包括听力考试);条件允许时可以组织口试(口语考试或听说考试) |
| 考查侧重 | 覆盖听、说、读、看、写,可注重听力、阅读等理解性技能 | 更加全面深入地考查理解性技能,同时注重表达性技能 |
examBlueprints[].items[] 的 itemType、score、expectedP;情境类别、学业质量水平与各部分的作答时间只写在给老师的细目表里。高一单元测评的蓝图示例(学校自编,只示范怎么写课标要求的几个维度,不代表任何一省的试卷结构;分值与时间由 CI 验算)见 references/hs-assessment-blueprint.md。
references/cefr-can-do-statements.md — "能做什么"语句(CSE 为主、CEFR 参照;含定级判定流程)references/four-skill-rubric.md — 4 维(听说读写)评分细则(只出分数 + 微技能,不出等级)references/assessment-template.md — 综合测评设计模板(4 阶段)references/cefr-four-skill-descriptors.md — CEFR 4 维对照速查表(A1-C2 听说读写描述)references/comprehensive-assessment-sample.md — 4 维测评样板(综合测评结构示例)references/student-ability-profile-template.md — 学员能力画像填写模板references/intervention-suggestion-sample.md — 教学干预建议样板references/english-growth-archive-sample.md — 学员英语成长档案样板references/hs-assessment-blueprint.md — 高一单元测评的蓝图示例:课标命题规划的几个维度、各部分分值与作答时间、整卷预期 P 的算法(含 CI 验算断言)💡 小智说: "英语测评不是给学员'打分数', 是给教学'画能力地图'。 学员不是'90 分'或'80 分', 而是'能听懂日常对话、能读短篇故事、 能介绍自己、能写简单邮件'—— 能力量表的意义就在这里:先看他能做什么,再决定教什么。"
© 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 17 other files (references) in teacher/english/xiaozhi-teach-english-assessment of qizhitang/xiaozhi-skills.
Open the folder on GitHubat commit c65f2d4
Xiaozhi Teach English Assessment 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 Assessment this skillqizhitang/xiaozhi-skills | 105 | — | ~4.1k | 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
英语综合测评设计:帮英语老师把"一张卷子"变成听说读写四维的能力测评与画像;高中按合格性考试与高考的课标口径设计. An agent skill from qizhitang/xiaozhi-skills. Xiaozhi Teach English Assessment is an agent skill from qizhitang/xiaozhi-skills.
Xiaozhi Teach English Assessment fits situations like: education work in your project.
Run `npx skills add qizhitang/xiaozhi-skills --skill xiaozhi-teach-english-assessment -a claude-code`. Or copy the skill folder (teacher/english/xiaozhi-teach-english-assessment in qizhitang/xiaozhi-skills) into .claude/skills/xiaozhi-teach-english-assessment in your project. Claude Code loads it when a task matches its description.
Run `npx skills add qizhitang/xiaozhi-skills --skill xiaozhi-teach-english-assessment -a codex`. Or copy the skill folder (teacher/english/xiaozhi-teach-english-assessment in qizhitang/xiaozhi-skills) into .agents/skills/xiaozhi-teach-english-assessment 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-assessment -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-assessment, .gemini/skills/xiaozhi-teach-english-assessment, .github/skills/xiaozhi-teach-english-assessment and .opencode/skills/xiaozhi-teach-english-assessment in your project.
SKILL.md names no scripts, command-line tools or credentials: Xiaozhi Teach English Assessment 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 Assessment is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 4.1k 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 11k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Xiaozhi Teach English Assessment: 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.