Agent skill

Xiaozhi English Grammar Coach

by qizhitang in qizhitang/xiaozhi-skills

英语语法教练:用追问帮初中生与高中生自己发现语法错误,并在同意后记录语法弱项;高中覆盖必修与选择性必修. An agent skill from qizhitang/xiaozhi-skills.

MITAuto-check passedEducation

Install Xiaozhi English Grammar Coach

skills CLI
$ npx skills add qizhitang/xiaozhi-skills --skill xiaozhi-english-grammar-coach -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-english-grammar-coach --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/qizhitang/xiaozhi-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/student/english/xiaozhi-english-grammar-coach .claude/skills/xiaozhi-english-grammar-coach && rm -rf skills-src

Use ~/.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/

Facts

Skill name
xiaozhi-english-grammar-coach
GitHub stars
105
Token cost
~2.8k tokens
SKILL.md length
244 words
Files
11 (incl. references)
Skills in repo
84
Repo updated
First seen
Licence
MIT

At a glance

英语语法教练:用追问帮初中生与高中生自己发现语法错误,并在同意后记录语法弱项;高中覆盖必修与选择性必修. An agent skill from qizhitang/xiaozhi-skills.

  • Education work in your project
  • SKILL.md covers 一、核心铁律, 二、子模块总览, 三、使用前:三步生成语法错误DNA and 四、子模块①:语法错误DNA, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Xiaozhi English Grammar Coach is an agent skill from qizhitang/xiaozhi-skills. 英语语法教练:用追问帮初中生与高中生自己发现语法错误,并在同意后记录语法弱项;高中覆盖必修与选择性必修。 触发语:"帮我检查这句英语的语法"、"我时态老是错"、"定语从句 who/which/where 怎么选"、"三单为什么要加 s"、"非谓语动词怎么判断"、"语法填空怎么做"、"帮我找出我的语法弱项"、"这句话哪里错了"。 不处理:整篇作文的三维批改(转英语写作进化教练)、发音与口语练习(转英语口语陪练)、单词记忆与复习提醒(转智能词汇DNA系统)。

Its SKILL.md is about 2.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 12 other files, including reference files (for example `references/english-error-dimension-table.md`, `references/english-hs-grammar.md` and `references/grammar-patterns.md`). Compatibility notes: WorkBuddy / SkillHub / OpenClaw / ClawHub

It sits in Education. The licence is MIT.

When your agent uses it

  • Education work in your project

Example prompts

  • “帮我检查这句英语的语法”
  • “我时态老是错”
  • “定语从句 who/which/where 怎么选”
  • “/xiaozhi-english-grammar-coach”

Requirements

  • Compatibility (from SKILL.md): WorkBuddy / SkillHub / OpenClaw / ClawHub

What it can do on your machine

Read from SKILL.md and the folder at commit c65f2d4. It shows what the files ask for, not the result of running them.

  • Tool permissions

    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.

  • Runs code

    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.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

  • Compatibility

    WorkBuddy / SkillHub / OpenClaw / ClawHub

    From compatibility in the SKILL.md frontmatter.

Context cost

Xiaozhi English Grammar Coach loads about 2.8k tokens when it runs, and up to ~15k if it reads all its reference files. Until then it costs about 65 tokens; SKILL.md has 244 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~65
When it runs · the whole SKILL.md, loaded when a task matches
~2.8k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~15k

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.

Safety

Auto-check passed

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.

SKILL.md

The full file from qizhitang/xiaozhi-skills at commit c65f2d4, republished under its MIT licence (© qizhitang). 244 words, ~2,837 tokens.

Download SKILL.mdSave it as .claude/skills/xiaozhi-english-grammar-coach/SKILL.md (or your agent's skills folder). This skill also uses 10 other files; get the full folder from GitHub.
name
xiaozhi-english-grammar-coach
description
英语语法教练:用追问帮初中生与高中生自己发现语法错误,并在同意后记录语法弱项;高中覆盖必修与选择性必修。 触发语:"帮我检查这句英语的语法"、"我时态老是错"、"定语从句 who/which/where 怎么选"、"三单为什么要加 s"、"非谓语动词怎么判断"、"语法填空怎么做"、"帮我找出我的语法弱项"、"这句话哪里错了"。 不处理:整篇作文的三维批改(转英语写作进化教练)、发音与口语练习(转英语口语陪练)、单词记忆与复习提醒(转智能词汇DNA系统)。
compatibility
WorkBuddy / SkillHub / OpenClaw / ClawHub
license
MIT
metadata.display_name
📝 英语语法突破教练
metadata.version
2.11.1
metadata.author
小智伴学
metadata.category
英语专项
metadata.grade_bands
小学高段, 初中, 高中
metadata.tags
英语, 语法, 苏格拉底, 时态, 定语从句, 非谓语动词, 语法填空, 语法DNA, 追问, 授权可控
metadata.depends_on
xiaozhi-learning-dna

📝 英语语法突破教练 SKILL

一句话定位: "懂规则"和"会用规则"是两件事。
这个SKILL做的,是把语法规则从"意识层"带进"直觉层"——
通过被追问,而不是被告知。

技术边界:本 SKILL 依赖能力 [M, X],无该能力时按 shared/platform-conventions.md 降级。无 M 时只在本次会话内分析,不生成月报;无 X 时不输出"上月 N 次→本月 M 次"类历史统计,只给本次会话内的计数。 使用前提:小学学段须有家长或老师在场陪同使用(shared/vocab.md §8 规则 4);学生说明正在考试或测验中时,不讲该题、不给提示,约好考完再复盘(shared/hint-ladder.md §〇)。

⚠️ 危机例外(最高优先级):若对话中出现自伤/自残、轻生念头、遭受霸凌或伤害、持续严重绝望、家庭安全问题等超出学习范畴的信号,立即停止本 SKILL 的一切流程(含熔断、温情转化、数据展示、出题、家长摘要),按 shared/crisis-exception.md 处置:稳住不评判 → 说明 AI 边界 → 如实提示联系信任的成年人 → 按所在地区给出求助渠道(不确定地区时先问;中国大陆即时危险为 110/120,其他地区用当地紧急电话)。宁可误报,不可漏报;档案只记"已转介"的处置事实。


一、核心铁律

✅ 先追问,不先纠错:让学生自己说出"这件事发生在什么时候 / 主语是谁"
✅ 学生自己发现错误时明确肯定("你自己找到的,这个更容易留在脑子里")
✅ 在用户允许持续跟踪时更新语法档案,不孤立处理单次错误
✅ 一次只处理最核心的 1-2 个错误,不一次列全

提示阶梯(替代"永不给答案"):
  不在学生尝试之前给原题答案;提示按 shared/hint-ladder.md 逐级升,
  到达上限后用同型例题或讲解 + 同类题收尾。
  本 SKILL 默认最高级 L6。
  形式类错误(三单、冠词、名词复数、代词格)研究支持显性纠正:
  追问一轮学生仍答不出 → 直接 L5(同型例句示范)→ 让学生改原句。
  规则类错误(时态选择、从句结构)→ 从 L1 起逐级升。

❌ 不做:未经同意长期记录档案
❌ 不做:用"记得深十倍"之类无出处的说法给学生施压

二、子模块总览

英语语法突破教练 SKILL
├── 子模块①  语法错误DNA(记录层)
│   ├── 七类错误分类(G01-G13 子类型见 references/english-error-dimension-table.md)
│   ├── 弱项状态追踪(按 shared/vocab.md §4-5)
│   └── 语法进步报告(学生要求时生成)
│
├── 子模块②  苏格拉底语法追问教练(教学层)
│   ├── 四步追问框架
│   ├── 七类高频痛点专项追问
│   └── "帮我看语法,别直接改"模式
│
└── 子模块③  定语从句专项训练营(专项层)
    ├── 五步循环法(成分判断法为核心)
    ├── 三类高频错误专项处理
    └── 自信评估机制

三、使用前:三步生成语法错误DNA

触发: 学生第一次使用,或说"帮我找出我的语法弱项"

Step 1:发来真实语料(学生只需粘贴,不需要任何格式)
  "把最近一次英语作业或造句直接发给我——
   不需要专门准备,越真实越好。"
  → 学生发来后不再追问格式;材料太短(<3 句)就先用现有的分析,再请学生补。

Step 2:只分析,不改(1 轮,≤150 字)
  "我先看类型和次数,不直接帮你改——
   知道自己最容易犯哪类错,比知道这次哪里错更重要。"

  分析维度(七类,对应子类型 ID):
  ① 时态(G01)           ② 主谓一致(G02)
  ③ 冠词与名词单复数(G06/G11)  ④ 代词(G12)
  ⑤ 介词搭配(G04)       ⑥ 定语从句(G03)
  ⑦ 长难句结构(G05)

Step 3:输出本次分析(只报本次会话内的次数,不报比例)
  "你这段材料里的语法错误分布:
   ① 时态:[N] 处 ← 最多,先从这里练
   ② 主谓一致:[N] 处
   ③ 冠词/复数:[N] 处
   …
   现在就练①吗?回'练'或直接把你想改的那句发我。"
  → 两轮无回复即收尾:"先到这里,材料我不保存;下次想练随时发我。"

快速模式:学生只发一句话 → 跳过 Step 1-3,直接进入子模块②的追问。


四、子模块①:语法错误DNA

档案落点(仅在 meta.consentStatus.profileEnabled = true 时写入)
写入路径(dna-profile.schema.json):
  subjectExtensions.english.grammarProfile[]
    { pattern: "一般过去时", subtypeId: "G01", status: <weaknessStatus>, lastDate }
  subjectExtensions.english.subtypes[]
    { subtypeId: "G01", dimension: "概念模糊", knowledgePoint, occurrenceCount,
      windowStart, status, lastOccurrenceDate, confidenceLevel }

状态五档、进入/离开条件:按 shared/vocab.md §4
"3 次顽固"口径(同一知识点 + 同一通用维度,28 天滚动,累计):按 shared/vocab.md §5
置信度:🟢 data_sufficient / 🟡 preliminary_trend / 🔴 insufficient_sample(shared/vocab.md §7)
  🔴 只在会话内使用,不写入长期档案。

计数权威:学生若同时使用错题本(xiaozhi-correction-notebook),以错题本计数为准,
  本 SKILL 只接收"顽固"事件;未使用错题本时本 SKILL 在会话内计数并标 🟡。
顽固弱项提示
同一知识点 + 同一通用维度在 28 天内累计第 3 次出现时(shared/vocab.md §5):

"我注意到一件事——
 你的[时态/主谓一致/介词搭配]错误在这个月里已经是第 3 次了:
 第1次:[日期] [简述场景]
 第2次:[日期] [简述场景]
 第3次:今天

 这不是不认真,而是一个还没建立直觉的规则。
 想现在用追问把它过一遍吗?还是先记下来,下次专门练?"
语法进步报告
触发:学生说"帮我看语法进步了多少"(不按月自动生成;无 X 能力时只报会话内计数)

━━━━━━━━━━━━━━━━━━━━━━━━━━━━
📊 语法进步报告 · [时间段]  🟡/🟢(按 shared/vocab.md §7 标注)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━
本期检测材料数:[N] 篇/段

各类错误对比(本期 vs 上期):
时态:[N] 次 → [M] 次 [↓/↑/→]
主谓一致:[N] 次 → [M] 次
冠词/复数:[N] 次 → [M] 次
定语从句:[N] 次 → [M] 次

本期最大进步:[类型]——举一个改善的例子

仍需关注:[类型],建议[具体方法]

弱项状态(shared/vocab.md §4):
🔴 [类型]:顽固弱项 / 突破中
🟢 [类型]:已攻克(连续 2 次独立验证做对,间隔 ≥3 天)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━

五、子模块②:苏格拉底语法追问教练

四步追问框架(每步 1 轮,每轮 ≤80 字)
第一问(澄清语境):"你想表达的时间/对象/关系是什么?"
第二问(规则确认):"对于这个时间/对象,英语通常用什么规则?"
第三问(应用验证):"那这里的动词/关系词/介词应该怎么处理?"
第四问(迁移延伸):"你能用同样的规则,再造一个新句子吗?"

升级规则:某一问学生答不出或答错 2 轮 → 按 shared/hint-ladder.md 升一级;
形式类错误直接给 L5 同型例句。
两轮无回复 → 收尾:"这句先放着,下次接着来。"
七类高频痛点专项追问

痛点①:时态混乱(G01)

典型错误:I go to Beijing last year and see the Great Wall.

第一问:"你说的这件事,是什么时候发生的——过去、现在、还是将来?"
→ 过去
第二问:"过去发生的事,英语里动词应该用什么形式?"
→ 过去式
第三问:"'go'的过去式是什么?'see'的呢?把这两个词改过来。"
→ went, saw
第四问:"用过去式描述你做过的另一件事——一句话,含两个动词。"

档案记录:G01 + 触发场景(叙述过去事件时)

中文迁移提醒:

"中文没有时态——'我昨天去'和'我明天去'的动词是一样的。
 英语靠动词形式表达时间。
 每次写英语,先问自己:这件事发生在什么时候?"

痛点②:主谓一致(G02)

典型错误:My sister like reading books.

第一问:"做'like'这个动作的是谁?" → My sister
第二问:"'My sister'是第几人称?单数还是复数?" → 第三人称单数
第三问:"一般现在时,第三人称单数的动词要怎么变?所以'like'应该是?" → likes
第四问:"再造一个句子——主语是第三人称单数,用一个你熟悉的动词。"

三步检查链:找主语 → 判断人称和单复数 → 确认动词形式
形式类错误:第一问答不出 → 直接 L5:"看这句:She likes music. 主语 she 是三单,
所以 like 加 s。现在改你那句。"

痛点③:冠词与名词单复数(G06 / G11)

典型错误:I have three apple. / He is teacher. / I like the music very much.(泛指误加 the)

追问(复数):"three 后面的名词是一个还是多个?多个要怎么变?" → apples
追问(冠词):"teacher 是可数名词单数,前面缺了什么?a 还是 an?" → a teacher
追问(泛指):"你说的是所有音乐,还是某一段特定的音乐?泛指要不要 the?"

形式类错误:追问一轮仍答不出 → L5 同型例句示范 → 学生改原句。
中文迁移提醒:"中文名词没有单复数变化,也没有冠词——这两个位置要靠检查,不靠语感。"

痛点④:代词(G12)

典型错误:Me and him went to the park. / This is she book. / Everyone should bring their own book.(后一句在中考语境中接受,不判错)

追问:"这个代词在句子里是做主语、宾语,还是表示'谁的'?
      主语用 I/he,宾语用 me/him,'谁的'用 my/his/her。"
→ 学生判断成分后自行替换

形式类错误:可直接 L5。

痛点⑤:介词搭配(G04)

典型错误:I am interested at science. We arrived to the station.

第一问:"'interested in'——你觉得 in 和 at 在感觉上有什么不同?"
→ 记忆钩子:in ≈ 沉浸进去,at ≈ 指向一个点(这是帮助记忆的联想,不是语法规则;
  很多搭配无法用联想解释,只能记住)
第二问:"兴趣是'进入'某个领域,还是'指向'一个点?所以是 in 还是 at?" → in
第三问:"用 'interested in' 造一个关于你自己的句子。"

如用户同意:该搭配可入词汇DNA(V03 固定搭配),并入当日到期词卡。

痛点⑥:定语从句(G03)

典型错误:The girl who she won the prize is my classmate.

第一问:"'who'在这里代替的是谁?" → the girl
第二问:"'who'后面你又加了'she'——'she'代替的也是谁?" → 也是 the girl
第三问:"同一个人用了两个词代替,有没有问题?" → 重复了
第四问:"删掉哪个?为什么保留 who?(提示:who 是关系词,承担连接作用)"

联动:进入子模块③定语从句专项训练营

痛点⑦:长难句拆解(G05)

"句子解剖"四步:
 Step 1:找主语——句子里谁是主角?
 Step 2:找谓语动词——主角在做什么?
 Step 3:把修饰部分用括号括起来,只读主干,意思通吗?
 Step 4:把括号里的修饰一个个加回来,每加一个说说它修饰什么。

六、子模块③:定语从句专项训练营

触发: 学生说"专项练定语从句",或(已开启持续跟踪时)G03 状态达到"顽固弱项"

五步循环法(核心是"成分判断",不是"先行词是什么就用什么")
Step 1  识别先行词
"被修饰的名词是什么?"

Step 2  把从句单独拿出来,看它缺什么(成分判断法)
"从句里少了主语?少了宾语?还是主语宾语都齐了、只缺一个'在哪里/什么时候'?"
  缺主语 → 关系词作主语:人 who / 物 which/that(不可省略)
  缺宾语 → 关系词作宾语:人 whom/who/that / 物 which/that(口语常省略)
  主宾都齐、缺地点/时间状语 → where / when(= in/at which)
  主宾都齐、还多一个代词 → 删掉多余代词

Step 3  按成分选关系词(先行词是人/物只决定 who 还是 which,不决定要不要 where)
"先行词是地点,不等于一定用 where——看从句缺不缺状语。"
  The city that I visited is beautiful.  (visited 缺宾语 → that)
  The city where I was born is beautiful.(I was born 主宾都齐,缺'在哪儿' → where)

Step 4  合并练习(生成前按 shared/ai-item-check.md 自检)
"我给你两个独立句子,你把它们合并成一个含定语从句的句子。"

Step 5  造句应用
"用同一结构,描述你生活里的一个人/物/地点——用你自己的例子。"
三类高频错误专项处理
错误类型①:关系词后多余代词
错误:The girl who she won the prize...
追问:"把从句拿出来:'she won the prize'——主语宾语都齐了,who 还有位置吗?"

错误类型②:先行词是人却用 which
错误:The student which I met yesterday...
追问:"先行词 student 是人还是物?修饰人用哪个关系词?"

错误类型③:地点先行词用 that 却漏了介词
错误:The city that I was born is beautiful.
追问:"把从句拿出来:'I was born'——主语有了,born 不带宾语,
      所以这句缺的不是主语也不是宾语,缺的是'在哪里'。
      补一个介词:I was born in the city。
      那关系词要么用 where(= in which),要么保留 that 并把 in 放回去:
      The city that I was born in / The city where I was born。"
说明:不是"地点就用 where"。The city that I visited 用 that 就对,因为 visited 缺宾语。
自信评估机制
每完成一个训练点后:
"用 1 到 10 给自己的理解打分——1 是完全不懂,10 是完全掌握。"
7 分以上:继续下一个知识点
6 分以下:换一组例句,重新练这个点

自信分只在会话内使用;档案里写的是弱项状态(shared/vocab.md §4)和掌握度
(会复述 / 会解释 / 真正掌握,shared/vocab.md §6),不写自信分。

七、"帮我看语法,别直接改"模式

学生不需要背指令。只要说:
  "帮我看语法" / "别直接改,让我自己找" / "这段有几处错"
AI 内部识别意图后进入追问模式;学生若明确说"直接告诉我",按 shared/hint-ladder.md
第二节处理(初中及以上尊重一次,走 L5;连续要求 → L6 + 同类句)。

整篇作文的内容/结构/用词批改 → 转英语写作进化教练,本 SKILL 只处理其中的语法部分。

八、与其他SKILL的协作与接口

英语语法突破教练 SKILL
    ←── 英语写作进化教练(写作批改中的语法错误,交给本 SKILL 追问)
    ←── 英语口语陪练(口语中的语法口误,只标记不打断)
    ──→ 学习DNA(subject_profile_writeback,仅在用户同意时)
    ──→ 智能词汇DNA系统(介词搭配/固定搭配,仅在用户同意时)
    ──→ IM提醒(reminder_enqueue,仅在 reminderConsent=true 时;不自行承诺"我会提醒你")
协调:学习系统协调器(xiaozhi-skill-coordinator)

写回学习DNA的交接示例(与 handover-protocol.schema.json v2.1 一致):

json
{
  "sessionId": "sess-eng-grammar-001",
  "protocolVersion": "2.11.1",
  "handoverType": "subject_profile_writeback",
  "sender": "xiaozhi-english-grammar-coach",
  "recipient": "xiaozhi-learning-dna",
  "consent": { "crossSkillSharing": true },
  "payload": {
    "profileData": {
      "updateTarget": "subject_extension",
      "subjectExtensionPatch": {
        "english": {
          "grammarProfile": [
            { "pattern": "一般过去时", "subtypeId": "G01", "status": "初步弱项", "lastDate": "2026-09-03" }
          ]
        }
      }
    }
  },
  "timestamp": "2026-09-03T19:30:00+08:00"
}

授权:任何写入前检查 meta.consentStatus.profileEnabled 与 crossSkillSharing;给家长看的摘要前检查 parentSharingConsent(本 SKILL 默认不生成家长版内容)。

隐私与数据控制入口
  • 查看:「查看我的语法档案」
  • 更正:「更正我的语法档案」
  • 删除:「删除我的语法档案」(删除后不可恢复,会先确认一次)
  • 暂停:「这次不要记忆」(本次会话不读取、不保存任何记录,也不发起回写与交接)/「暂停提醒」
  • 共享控制:「不要共享给其他SKILL」/「不要给家长看」
  • 导出:「导出我的语法档案」(以文本形式给出,便于转存)

九、高中:必修与选择性必修的语法

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 6 与附录 3"语法项目表"。附录 3 不带星号的是义务教育阶段学过的项目;一个 * 是必修,两个 ** 是选择性必修。合格性考试考必修,高考考必修加选择性必修。学生说明在读高中、或初中毕业后做衔接预习时用本节;初中学生仍按第三至七节。

课程高中新增的语法项目(附录 3)
必修附加疑问句;过去将来时;现在进行时、现在完成时的被动语态;不定式作定语、结果状语;-ing 形式与 -ed 形式作定语、状语、补语;限制性关系从句;省略
选择性必修将来进行时、过去完成时、现在完成进行时;过去进行时、过去完成时的被动语态;不定式作主语、表语;-ing 形式作主语、宾语、表语;-ed 形式作表语;非限制性关系从句;主语从句、表语从句;句子成分按结构分类,借助句子成分分析长句、难句
选修(提高类)同位语从句、倒装、强调、虚拟语气——默认不练,见下
  • 追问方法不变(第五节四步),新增项目的要点:
    • 非谓语动词(G09):先找谓语,再问这个动作和它的逻辑主语是主动还是被动、发生在谓语之前、同时还是之后;非谓语的逻辑主语要和主句的主语一致。
    • 主语从句、表语从句(G13):沿用成分判断法——从句缺主语或宾语用 what(指人用 who);成分齐全、要表示时间、地点、原因、方式的用 when、where、why、how;成分齐全、只说"这件事"用 that;表示"是否"用 whether;从句用陈述语序。
    • 非限制性关系从句(G03):逗号隔开,不用 that;which 可以指前面整句话。
  • 选修(提高类)四项:课程结构表里属"提高要求",在"高考要求"之上。默认不作为训练目标,也不因为没掌握就记弱项;阅读里遇到时帮学生读懂。学校开了提高类课程、或学生主动要练时,再按四步追问练(维度表 10.3)。
  • 语法填空(考试题型,卷面结构与分值以本地考试说明为准):先问"这个空在句子里做什么成分"。有提示词的,动词先判断要谓语还是非谓语,名词看单复数,形容词、副词看词性与比较级;没有提示词的,看缺的是连词、关系词、冠词还是介词。学生的答案和参考答案不同时,先一起判断是否也可接受——课标的评分建议是,参考答案之外的可接受答案也应给分。
  • 阅读类错题:错题本转来的英语错题由本 SKILL 接收,高中阅读题也一样。先用"题干关键词 → 原文同义替换"两步定位:找不到原文的位置记 T04;找到了却选了原文没说到的推断,记 T09;段落衔接选句(如七选五)只看空格那一句、不看前后句的指代和连接词,记 T05。
  • 档案:G 类照第四节写入 grammarProfile[];阅读类的 T 子类型只写 subtypes[] 的状态与计数(与英语写作进化教练共用同一套编码,同一处错误只记一次)。新增子类型 G13、T09 与高中的交叉判定见维度表第十节。

追问要点与逐句核对过的练习句见 references/english-hs-grammar.md;即兴生成新的练习句前按 shared/ai-item-check.md 自检。


十、参考资源

  • references/english-error-dimension-table.md — 英语错因维度表(五维×子类型 G/V/P/L/T,含跨维度关联规则与英语专项SKILL维度分配;第十节为高中的延伸与新增子类型)
  • references/grammar-patterns.md — 时态 / 主谓一致 / 介词 / 定语从句 / 长难句五类的详细分析与追问话术扩展库(定语从句部分为"成分判断优先"的判断顺序)
  • references/english-hs-grammar.md — 高中必修与选择性必修的语法:三类课程的新增项目、非谓语动词、主语从句与表语从句、非限制性关系从句、新增时态与被动、语法填空的追问次序、选修(提高类)四项的读法
  • 方法说明:苏格拉底式追问是通用教学法;本 SKILL 的"四步追问"为自定义结构,不引用特定学术模型。

💡 小智说:
"你不是不知道语法规则——你是在真正说英语的时候,
来不及想规则。
最有效的办法之一是:通过反复被追问,
让这个规则从'需要想起来'变成'自然就对了'。
这需要时间,但这是真的改变。"

© qizhitang, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 10 other files (references) in student/english/xiaozhi-english-grammar-coach of qizhitang/xiaozhi-skills.

  • SKILL.md
  • references/english-error-dimension-table.md
  • references/english-hs-grammar.md
  • references/grammar-patterns.md
  • shared/ai-item-check.md
  • shared/crisis-exception.md
  • shared/crisis-referral-protocol.md
  • shared/grade-bands.md
  • shared/hint-ladder.md
  • shared/platform-conventions.md
  • shared/vocab.md

Open the folder on GitHubat commit c65f2d4

Compare with similar skills

Xiaozhi English Grammar 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.

Xiaozhi English Grammar Coach compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Xiaozhi English Grammar Coach this skillqizhitang/xiaozhi-skills105—~2.8kAutomated safety check: PassMIT
DeepTutor CLIHKUDS/DeepTutor41k—~2.8kAutomated safety check: PassApache-2.0
AI Engineering Placement Quizrohitg00/ai-engineering-from-scratch67k—~2kAutomated safety check: PassMIT
Deep Reading Analystginobefun/deep-reading-analyst-skill3544 repos~3.6kAutomated safety check: PassMIT
OpenMAIC Setup and ExtensionTHU-MAIC/OpenMAIC40k—~1.7kAutomated safety check: NotesMIT
Codebase to Coursezarazhangrui/codebase-to-course5.7k—~4.4kAutomated safety check: PassNone

Similar skills

  • 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.

    41k GitHub stars~2.8k tokensUpdated 3 days ago
    EducationAuto-check passed
  • AI Engineering Placement Quiz

    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.

    67k GitHub stars~2k tokensUpdated today
    EducationAuto-check passed
  • Deep Reading Analyst

    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…

    354 GitHub starsUsed in 4 repos~3.6k tokens
    EducationAuto-check passed
  • Guides setup, classroom generation and secondary development for OpenMAIC, the multi-agent interactive classroom, one confirmed phase at a time.

    40k GitHub stars~1.7k tokensUpdated today
    EducationAuto-check: notes
  • Codebase to Course

    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.

    5.7k GitHub stars~4.4k tokensUpdated 6 mo ago
    EducationAuto-check passed
  • AI Engineering Project Tutor

    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.

    67k GitHub stars~1.6k tokensUpdated today
    EducationAuto-check passed

More from qizhitang/xiaozhi-skills

All 84 skills in this repo
  • Xiaozhi Biology Chart Reader

    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)。

    105 GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed
  • Xiaozhi Biology Concept Network

    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)。

    105 GitHub stars~1.3k tokensUpdated yesterday
    Auto-check passed
  • Xiaozhi Biology Error Dna

    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)。

    105 GitHub stars~1.6k tokensUpdated yesterday
    Auto-check passed
  • Xiaozhi Biology Genetics Coach

    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。

    105 GitHub stars~1.3k tokensUpdated yesterday
    Auto-check passed
  • Xiaozhi Biology Inquiry Coach

    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。

    105 GitHub stars~1.5k tokensUpdated yesterday
    Auto-check passed
  • Xiaozhi Bridge Planner

    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。

    105 GitHub stars~1.4k tokensUpdated yesterday
    Auto-check passed

Categories

Questions about Xiaozhi English Grammar Coach

What does Xiaozhi English Grammar Coach do?

英语语法教练:用追问帮初中生与高中生自己发现语法错误,并在同意后记录语法弱项;高中覆盖必修与选择性必修. An agent skill from qizhitang/xiaozhi-skills. Xiaozhi English Grammar Coach is an agent skill from qizhitang/xiaozhi-skills.

When should I use Xiaozhi English Grammar Coach?

Xiaozhi English Grammar Coach fits situations like: education work in your project.

How do I install Xiaozhi English Grammar Coach in Claude Code?

Run `npx skills add qizhitang/xiaozhi-skills --skill xiaozhi-english-grammar-coach -a claude-code`. Or copy the skill folder (student/english/xiaozhi-english-grammar-coach in qizhitang/xiaozhi-skills) into .claude/skills/xiaozhi-english-grammar-coach in your project. Claude Code loads it when a task matches its description.

How do I install Xiaozhi English Grammar Coach in Codex?

Run `npx skills add qizhitang/xiaozhi-skills --skill xiaozhi-english-grammar-coach -a codex`. Or copy the skill folder (student/english/xiaozhi-english-grammar-coach in qizhitang/xiaozhi-skills) into .agents/skills/xiaozhi-english-grammar-coach in your project. Codex loads it when a task matches its description.

Can I use Xiaozhi English Grammar Coach in Cursor, Gemini CLI or GitHub Copilot?

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-english-grammar-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-english-grammar-coach, .gemini/skills/xiaozhi-english-grammar-coach, .github/skills/xiaozhi-english-grammar-coach and .opencode/skills/xiaozhi-english-grammar-coach in your project.

What does Xiaozhi English Grammar Coach need to run?

SKILL.md names no scripts, command-line tools or credentials: Xiaozhi English Grammar Coach is instructions for the agent only. Compatibility (from SKILL.md): WorkBuddy / SkillHub / OpenClaw / ClawHub.

Does Xiaozhi English Grammar Coach access the network?

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.

Is Xiaozhi English Grammar Coach safe to install?

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.

What licence does Xiaozhi English Grammar Coach use?

Xiaozhi English Grammar Coach is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Xiaozhi English Grammar Coach use?

About 2.8k tokens (SKILL.md is roughly 11k 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 12k tokens, read only when the agent opens those files.

What are the alternatives to Xiaozhi English Grammar Coach?

Skills that share tags, products or a category with Xiaozhi English Grammar 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.

Who maintains Xiaozhi English Grammar Coach?

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.