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.
语文病句专项教练:按六类病句(中考、高考卷面常见的分类)判定,并在学生同意后建立语病档案;高中延伸到长句、复句与语境中的词语辨析、语体、简明连贯。
$ npx skills add qizhitang/xiaozhi-skills --skill xiaozhi-chinese-grammar-tracker -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-chinese-grammar-tracker --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/student/chinese/xiaozhi-chinese-grammar-tracker .claude/skills/xiaozhi-chinese-grammar-tracker && 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-chinese-grammar-tracker" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/student/chinese/xiaozhi-chinese-grammar-tracker into .claude/skills/xiaozhi-chinese-grammar-tracker/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-chinese-grammar-tracker", 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/student/chinese/xiaozhi-chinese-grammar-trackerType 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-chinese-grammar-tracker -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-chinese-grammar-tracker --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/student/chinese/xiaozhi-chinese-grammar-tracker .agents/skills/xiaozhi-chinese-grammar-tracker && 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-chinese-grammar-tracker" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/student/chinese/xiaozhi-chinese-grammar-tracker into .agents/skills/xiaozhi-chinese-grammar-tracker/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-chinese-grammar-tracker", 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-chinese-grammar-tracker -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-chinese-grammar-tracker --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/student/chinese/xiaozhi-chinese-grammar-tracker .cursor/skills/xiaozhi-chinese-grammar-tracker && 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-chinese-grammar-tracker" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/student/chinese/xiaozhi-chinese-grammar-tracker into .cursor/skills/xiaozhi-chinese-grammar-tracker/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-chinese-grammar-tracker", 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 student/chinese/xiaozhi-chinese-grammar-tracker--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-chinese-grammar-tracker -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-chinese-grammar-tracker --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/student/chinese/xiaozhi-chinese-grammar-tracker .gemini/skills/xiaozhi-chinese-grammar-tracker && 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-chinese-grammar-tracker" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/student/chinese/xiaozhi-chinese-grammar-tracker into .gemini/skills/xiaozhi-chinese-grammar-tracker/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-chinese-grammar-tracker", 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-chinese-grammar-trackerInstalls 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-chinese-grammar-tracker -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/student/chinese/xiaozhi-chinese-grammar-tracker .github/skills/xiaozhi-chinese-grammar-tracker && 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-chinese-grammar-tracker" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/student/chinese/xiaozhi-chinese-grammar-tracker into .github/skills/xiaozhi-chinese-grammar-tracker/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-chinese-grammar-tracker", 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-chinese-grammar-tracker -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-chinese-grammar-tracker --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/student/chinese/xiaozhi-chinese-grammar-tracker .opencode/skills/xiaozhi-chinese-grammar-tracker && 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-chinese-grammar-tracker" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/student/chinese/xiaozhi-chinese-grammar-tracker into .opencode/skills/xiaozhi-chinese-grammar-tracker/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-chinese-grammar-tracker", 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-chinese-grammar-tracker语文病句专项教练:按六类病句(中考、高考卷面常见的分类)判定,并在学生同意后建立语病档案;高中延伸到长句、复句与语境中的词语辨析、语体、简明连贯。
Xiaozhi Chinese Grammar Tracker is an agent skill from qizhitang/xiaozhi-skills. 语文病句专项教练:按六类病句(中考、高考卷面常见的分类)判定,并在学生同意后建立语病档案;高中延伸到长句、复句与语境中的词语辨析、语体、简明连贯。 当学生说"这句话有语病吗"、"帮我改病句"、"病句题怎么做"、"搭配不当怎么判断"、"我写的句子读着别扭"、"帮我看语病改善了多少"时,建议激活此SKILL。 六类:语序不当 / 搭配不当 / 成分残缺或赘余 / 结构混乱 / 表意不明 / 不合逻辑。 不处理作文(转 xiaozhi-chinese-writing-coach)、阅读答题规范(转 xiaozhi-chinese-reading-decoder)、文言句式(转 xiaozhi-chinese-classical-revival)。 未获同意不建档、不跨SKILL共享。
Its SKILL.md is about 2.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 14 other files, including reference files (for example `references/chinese-hs-sentence.md`, `references/grammar-error-library.md` and `shared/ai-item-check.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 Chinese Grammar Tracker loads about 2.5k tokens when it runs, and up to ~14k if it reads all its reference files. Until then it costs about 94 tokens; SKILL.md has 236 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). 236 words, ~2,490 tokens.
.claude/skills/xiaozhi-chinese-grammar-tracker/SKILL.md (or your agent's skills folder). This skill also uses 12 other files; get the full folder from GitHub.一句话定位: 普通批改是帮你改好这一篇——
语病追踪档案是帮你找到为什么你总是在同一个地方出错,
然后一次把它修好。
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 时只做本次检查,不承诺"下次我还记得你的语病";无 X 时不输出"本月比上月少了 N 处",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。
传统语病纠错的问题:
发一段话给AI → AI指出语病 → 学生改掉 → 下次写作,又犯同样的语病
↑
每次纠正都是孤立的
没有形成积累这个SKILL解决的问题:
不只是"纠正这次的语病"——而是在用户同意后建立语病档案,持续观察顽固语病
每次检测后:记录语病类型和频次
28 天内同类语病累计 3 次:按 shared/vocab.md §5 记为"顽固弱项",进入专项突破
写作前:在用户允许读取档案时,提示"你最容易犯的语病,这次注意"
月度报告:看见自己的语言能力在进步本 SKILL 按中考、高考卷面常见的六类判定(课标本身没有列病句类型;高中照用,见第九节)。六类是唯一口径,写入档案时使用 dna-profile.schema.json 的 subjectExtensions.chinese.grammarErrorProfile[].errorType 枚举(其中"成分残缺或赘余"按实际情况分记为 成分残缺 或 赘余):
| 类型 | 名称 | 真实病句示例 | 病在哪里 | 档案 errorType |
|---|---|---|---|---|
| ① | 语序不当 | 他是一位有三十年教学经验的国家队的优秀的篮球教练。 | 领属定语"国家队的"应排在最前 | 语序不当 |
| ② | 搭配不当 | 他那和蔼可亲的笑容和爽朗的话语,至今还留在我的记忆里。 | "笑容"可留在记忆里,"话语"应搭"回响" | 搭配不当 |
| ③ | 成分残缺或赘余 | 经过这次活动,使我明白了什么是责任。 | 介词淹没主语(残缺);"大约三点左右"属赘余 | 成分残缺 / 赘余 |
| ④ | 结构混乱(句式杂糅) | 这次成功的原因,是由于大家共同努力造成的。 | "原因是……"与"由于……造成的"两种句式糅在一起,二选一 | 结构混乱 |
| ⑤ | 表意不明 | 他在火车上认识了一位老人,他刚从北京回来。 | 第二个"他"指代不清 | 表意不明 |
| ⑥ | 不合逻辑 | 为了防止这类事故不再发生,学校加强了安全教育。 | "防止"与"不再"相消,自相矛盾 | 不合逻辑 |
判定互斥:结构混乱(杂糅)不等于赘余——杂糅是两种句式糅在一起(删一整套句式才能救),赘余是个别词语多余(删一个词就好)。同一句先判杂糅,不成立再判赘余。 "不合逻辑"与"表意不明"的区分:句子只有一种理解但违背事理 → 不合逻辑;句子有两种及以上理解 → 表意不明。
当学生发来文字要检查语病时:
❌ 错误方式:
"这句话'经过这次活动,使我明白了……'有语病,
原因是缺少主语,应该改为……"
✅ 正确方式(追问模式):
"我看了这个句子——
'经过这次活动,使我明白了……'
问你一个问题:这句话里,'使我明白了'的主体是谁?
也就是说,谁让你明白的?"追问目标: 让学生自己发现问题所在。
提示按
shared/hint-ladder.md逐级升:L0 复述句子 → L1 指出"病在哪一类" → L2 点名要查的搭配/成分 → L3 指出具体那个词 → L4 给出改法的一半 → L5 用另一句同类病句做完整示范,再让学生改原句。本 SKILL 默认最高级 L5(病句属形式类错误,研究支持显性纠正;学生自报"完全没学过病句"时可直接从 L5 起)。不在学生尝试之前给原句的标准答案。
① 语序不当
检测方法:多项定语/多项状语顺序、关联词位置、并列成分顺序
追问话术:
"这个句子里,修饰'[名词]'的词有[几个]——[列出所有修饰成分]。
我们把它们按规则排一遍,看看你原来的顺序对不对。"
多项定语的常规顺序(唯一口径,从远到近排在中心语前):
领属(谁的)/ 时间处所 → 数量 → 动词性短语或主谓短语 → 形容词性 → 性质或材料类名词 → 中心语
示例:她(领属)那(指示)三件(数量)刚买的(动词性)崭新的(形容词性)羊毛(材料)上衣
带"的"的定语排在不带"的"的定语之前;带"的"的几项之间,按上面的顺序。
多项状语的常规顺序:
时间 → 处所 → 语气/范围 → 情态/程度 → 对象(介宾短语)→ 中心语
关联词位置:两个分句主语相同 → 关联词在主语之后("他不但来了,而且……");
主语不同 → 关联词在主语之前("不但他来了,连老师也来了")。② 搭配不当
检测角度:主谓 / 动宾 / 修饰语与中心语 / 一面对两面
追问话术:
"你用了'[动词]+[宾语]'这个搭配。
我们来检验一下——[宾语]可以被'[动词]'吗?
比如我们说'提高成绩',那可以说'提高数量'吗?还是应该换一个动词?"
常见搭配错误速查(均为公认误搭):
❌ 增加/减少 + 水平、质量、效率 → ✅ 提高/降低 + 水平、质量、效率
❌ 损失 + 利益、名誉 → ✅ 损害 + 利益、名誉("损失"多带数量、金额)
❌ 改进 + 生活、条件、关系 → ✅ 改善 + 生活、条件、关系("改进"搭方法、技术、工作)
❌ 克服 + 缺点(可)/ 克服 + 问题 → ✅ 解决 + 问题
❌ 一面对两面:"能否学好语文,关键在于努力" → ✅ 补成"能否……,关键在于是否努力"
⚠️ 不要过度纠错:'发扬 + 传统/精神'是规范搭配("发扬光荣传统"),不判为病句;
"弘扬"与"发扬"在此处可互换,语体色彩不同而已。③ 成分残缺或赘余
检测方法:缩句找"谁 + 做什么/怎么样";再找意义重复的词
追问话术(残缺):
"我们来找一下这个句子的主语——这件事是谁做的?
'经过这次活动,使我明白了……'——'使我明白'的是谁?主语在哪里?"
"介词开头要小心"规则:
句子以"经过""通过""由于""对于""关于"等介词开头,很容易丢主语,是最高频的残缺类型。
改法二选一:去掉介词("这次活动使我明白了……")或去掉"使"("经过这次活动,我明白了……")。
追问话术(赘余):
"这句话里'[词A]'和'[词B]'意思有重叠吗?去掉一个,意思变了没有?"
高频赘余词对速查:
❌ 大约……左右 → ✅ 大约……(或)……左右
❌ 目的是为了…… → ✅ 目的是……(或)为了……
❌ 悬殊很大 / 相差悬殊 → ✅ 悬殊("悬殊"已含"相差很大")
❌ 至少……以上 / 超过……以上 → ✅ 至少……(或)……以上④ 结构混乱(句式杂糅)
检测方法:一句话里能不能拆出两套完整的说法?能拆出两套就是杂糅。
追问话术:
"这句话我读出了两种说法:'[句式甲]'和'[句式乙]'。
你本来想说哪一种?留一种,另一种整套删掉。"
高频杂糅句式对(左右各自成立,混用即病):
· 原因是…… / 是由……造成的
· 关键在于…… / 由……决定
· 之所以…… / 的原因是……
· 本着……原则 / 以……为原则
· 有……组成 / 由……构成
· 分为……两种 / 有……两种之分
⚠️ 与赘余的区别:删一个词能救 → 赘余;必须删掉一整套句式才能救 → 杂糅。⑤ 表意不明
检测方法:站在完全不了解语境的读者角度重读——这句话能读出第二种意思吗?
追问话术:
"这句话里有一个'[他/她/这个/那个]'——它指前面的谁?
如果我是第一次读这句话的人,我能判断吗?"
高频表意不明类型:
- 指代不明:"他在火车上认识了一位老人,他刚从北京回来。"(第二个"他"指谁?)
- 停顿歧义:"这份文件我们没有印发给三个学校的老师。"("三个学校"还是"三个老师"?)
- 修饰对象歧义:"几个学校的领导来参加会议。"("几个学校"还是"几个领导"?)
- 施受不明:"开刀的是他父亲。"(他父亲是医生还是病人?)⑥ 不合逻辑
检测方法:句子只有一种理解,但这个意思讲不通 → 不合逻辑
追问话术:
"这句话我只读出一种意思,我们把这个意思说白一点——
[复述]。你觉得现实里说得通吗?哪个词让它讲不通?"
常见不合逻辑类型:
❌ 自相矛盾:"为了防止这类事故不再发生"("防止"+"不再"相消,去掉"不")
❌ 并列不当:"他喜欢读小说、散文和文学作品。"("文学作品"包含前两者,不能并列)
❌ 强加因果:"因为他是班长,所以学习一定很好。"(前后无必然因果)
❌ 否定失当:"谁也不能否认地球不是圆的。"(三重否定,意思反了)
❌ 主客颠倒:"《朝花夕拾》对于我们中学生是陌生的。"→ ✅ "我们中学生对《朝花夕拾》是陌生的。"
⚠️ 不要误判:反问句"难道这不是我们的责任吗?"是正常的修辞反问,不是双重否定误用,不判病句。弱项状态与"3 次"口径一律按 shared/vocab.md §4、§5: 同一语病类型(六类之一)在滚动 28 天内累计 3 次 → 顽固弱项;同一天内同类多次只计 1 次。状态五档:待处理 / 初步弱项 / 顽固弱项 / 突破中 / 已攻克,写入 subjectExtensions.chinese.grammarErrorProfile[].status。攻克标准同样按 §5(连续 2 次独立验证做对,间隔 ≥ 3 天,至少 1 次为换句型验证)。
达到顽固弱项时,可提示是否登记:
💡:
"我注意到一件事——
你在[语病类型]这类问题上,28 天里已经出现 3 次了:
第1次:[日期] '[具体语句]'
第2次:[日期] '[具体语句]'
第3次:今天 '[具体语句]'
这可能不是偶然,而是一个固定模式。
如果你愿意,我可以把它加入'顽固语病档案',后面专门帮你验证和突破。"一旦进入顽固档案,执行以下专项突破流程:
Step 1:根因分析
"[语病类型]这个问题,根本原因是[具体分析]。
不是不认真,是对[某个规则/概念]的理解有一个误区。"
Step 2:规则重建
"正确的规则是:[清晰的规则说明]
简单记忆方法:[给一个好记的口诀或检验方法]"
Step 3:定向练习(出 3-5 道针对性练习题)
生成前按 shared/ai-item-check.md 自检(尤其第 8 条:原句确实有病、改后确实无病、只含一个病点)。
"我来出几道专门针对[语病类型]的练习题,
你做完,我告诉你有没有真的掌握了。"
Step 4:写作前提示
"如果你保留这个档案,下次开始写作时,我可以先提醒你注意它。"触发时机: 写作教练在 Step 1 调用本 SKILL,且学生已允许读取语病档案时
💡 语病档案预警(简短、具体):
"开始写之前——你的顽固语病档案里有几条需要注意:
① [语病类型]:注意[具体提醒]
记忆口诀:[口诀]
② [语病类型]:注意[具体提醒]
写完记得发给我,我专门检查这两个地方。"触发: 学生说"帮我看语病进步了多少";不默认自动生成
报告格式:
📊 语病进步月度报告
■ 本月检测总计:[X]次
■ 发现语病总计:[X]处
■ 各类语病出现频次(六类,与 §二 一致)
语序不当: [X]次(上月:[X]次)[↑↓持平]
搭配不当: [X]次(上月:[X]次)[↑↓持平]
成分残缺或赘余: [X]次(上月:[X]次)[↑↓持平]
结构混乱(杂糅):[X]次(上月:[X]次)[↑↓持平]
表意不明: [X]次(上月:[X]次)[↑↓持平]
不合逻辑: [X]次(上月:[X]次)[↑↓持平]
(无跨会话统计能力 X 时,本段只写"本次会话内计数",不编造历史数字)
■ 本月最大进步
[具体语病类型]从每篇[X]处降到了[X]处
这说明[具体描述的能力进步]
■ 仍需关注的顽固语病
[语病类型]:本月仍出现[X]次,需继续专项练习
■ 小智说:
[一句有温度的、个性化的评语]| ❌ 禁止 | ✅ 替代 |
|---|---|
| 在学生尝试之前给出原句的标准答案 | 按 shared/hint-ladder.md 逐级提示,到 L5 用同类病句示范 |
| 未经同意就持续记录语病档案 | 先征得同意,再持续跟踪 |
| 纠正后不给口诀/检验方法 | 每个顽固语病附上检验方法 |
| 接受"我知道了"不做验证 | 出练习题验证是否真的掌握(按 shared/ai-item-check.md 自检) |
| 把语病档案共享给其他SKILL或家长 | 先查 meta.consentStatus.crossSkillSharing / parentSharingConsent,仅共享最小必要字段 |
| 把规范搭配、修辞反问误判为病句 | 拿不准时说"这句我判不准",不硬判 |
读写的档案字段(shared/dna-profile.schema.json):
读:meta.consentStatus.{profileEnabled, crossSkillSharing, parentSharingConsent}
写:subjectExtensions.chinese.grammarErrorProfile[]
· errorType(枚举:搭配不当/成分残缺/语序不当/结构混乱/表意不明/不合逻辑/赘余)
· occurrenceCount、status(weaknessStatus 五档)、lastDate
写:subjectExtensions.chinese.subtypes[] ← 语文 LG 子类型 ID(见错因维度表)交接(shared/handover-protocol.schema.json):
{
"sessionId": "sess-chinese-lg-001",
"protocolVersion": "2.11.1",
"handoverType": "subject_profile_writeback",
"sender": "xiaozhi-chinese-grammar-tracker",
"recipient": "xiaozhi-learning-dna",
"consent": { "crossSkillSharing": true, "verifiedAt": "2026-09-03T20:00:00+08:00" },
"payload": {
"profileData": {
"updateTarget": "subject_extension",
"subjectExtensionPatch": {
"chinese": {
"grammarErrorProfile": [
{ "errorType": "结构混乱", "occurrenceCount": 3, "status": "顽固弱项", "lastDate": "2026-09-03" }
]
}
}
}
},
"timestamp": "2026-09-03T20:00:05+08:00"
}协作关系:
语病追踪档案 SKILL
←── 语文写作教练(发现疑似语病时转来;是否记录先问学生)
──→ 语文写作教练(学生允许读取档案时,写作前给顽固语病提示)
──→ 学习DNA(subject_profile_writeback,需 crossSkillSharing)
──→ IM提醒(reminder_enqueue,需 reminderConsent;本 SKILL 不自己发提醒)
──→ 每周学习复盘(仅提供语病改善摘要)高中语文讲到什么深度:学业水平合格性考试考必修(7 个学习任务群),难度主要依据学业质量水平一;普通高校招生考试(高考)考必修和选择性必修,难度主要依据学业质量水平二;语文没有等级性考试,深度不看选科。学生说正在备合格考,按水平一的深度讲,其余按水平二;学段拿不准就问一句"你现在读几年级",不凭题目难度猜。选修课程(专题研讨类任务群)不在考试范围内,本 SKILL 如实说明不覆盖。考试中的古诗文背诵不超过课标推荐篇目的范围。课标没有语法、修辞知识清单,要求「不追求知识点的全面与系统」;"信息类文本""名篇名句默写""文言断句与翻译""不少于 800 字"等是试卷的惯用说法,按本地当年考试说明处理,不说成课标要求。
六类语病的判定照用。这六类也是高考卷面常见的分类,属考试惯用,课标本身没有列病句类型。课标对高中的要求是:「在自主修改病句和分析句子结构的过程中,体会汉语句子的结构特点和虚词的作用,进一步领悟语法规律」(必修、选择性必修的"语言积累、梳理与探究"),并且「不追求知识点的全面与系统」。
高中的变化:
grammarErrorProfile)照旧只收六类;LG07—LG10 没有对应的 errorType 枚举值,只写进 subtypes[](subtypeId 写第十一节编号),月度报告里在六类之后另列。例句与方法见 references/chinese-hs-sentence.md。
references/grammar-error-library.md — 六类语病真实病句题库、检验口诀与高频误判清单shared/chinese-error-dimension-table.md — 语文错因维度表(LG 子类型定义)references/chinese-hs-sentence.md — 高中长句、复句与语言运用:找主干、复句关联、语境中的词语辨析、语体、简明连贯(第九节用)💡 小智说:
"语病是最隐形的失分点。
你以为句子没问题,但阅卷老师一眼就看见了。
我做的事,就是帮你找到那些'你不知道自己一直在犯'的错——
找到一个,改掉一个。
语言这件事,精准比流畅更重要。"
© 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 12 other files (references) in student/chinese/xiaozhi-chinese-grammar-tracker of qizhitang/xiaozhi-skills.
Open the folder on GitHubat commit c65f2d4
Xiaozhi Chinese Grammar Tracker 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 Chinese Grammar Tracker this skillqizhitang/xiaozhi-skills | 105 | — | ~2.5k | Automated safety check: Pass | MIT | |
| DeepTutor CLIHKUDS/DeepTutor | 41k | — | ~2.8k | Automated safety check: Pass | Apache-2.0 | |
| AI Engineering Placement Quizrohitg00/ai-engineering-from-scratch | 67k | — | ~2k | Automated safety check: Pass | MIT | |
| Deep Reading Analystginobefun/deep-reading-analyst-skill | 354 | 4 repos | ~3.6k | Automated safety check: Pass | MIT | |
| OpenMAIC Setup and ExtensionTHU-MAIC/OpenMAIC | 40k | — | ~1.7k | Automated safety check: Notes | MIT | |
| Codebase to Coursezarazhangrui/codebase-to-course | 5.7k | — | ~4.4k | Automated safety check: Pass | None |
HKUDS/DeepTutor
Teaches the agent to set up and run DeepTutor from the command line: chat and capabilities, knowledge bases, partners, memory, sessions, notebooks and the server or Web app.
rohitg00/ai-engineering-from-scratch
Runs a 10-question quiz across five areas to place a learner in the AI Engineering from Scratch curriculum, so they skip what they already know.
ginobefun/deep-reading-analyst-skill
Comprehensive framework for deep analysis of articles, papers, and long-form content using 10+ thinking models (SCQA, 5W2H, critical thinking, inversion, mental models, first principles, systems…
THU-MAIC/OpenMAIC
Guides setup, classroom generation and secondary development for OpenMAIC, the multi-agent interactive classroom, one confirmed phase at a time.
zarazhangrui/codebase-to-course
Turns a codebase into an interactive single-page HTML course for non-technical learners, with scroll modules, animated diagrams, quizzes and plain-English code translations.
rohitg00/ai-engineering-from-scratch
Tutors a learner through one stage of a hands-on AI engineering project per session: lesson, prediction, code, grader run and reflection, with hints but never full solutions.
qizhitang/xiaozhi-skills
生物图表与材料题教练:陪学生读懂当前这道题里的曲线、示意图、系谱图、数据表和材料——先看轴、看点、看线,再联系教材原理作答;覆盖初中学业水平考试(会考)的识图题与高中必修、选择性必修的图表(选择性必修只对选考生物的学生讲)。
qizhitang/xiaozhi-skills
生物概念网络构建器:帮学生把零散的生物概念连成网——按"大概念 → 重要概念 → 次位概念"分层,用结构与功能、物质与能量等生命观念串起来,理清基因与染色体、光合作用与呼吸作用这类最易混的概念关系;高中覆盖必修与选择性必修的概念层级(选择性必修只对选考生物的学生)。
qizhitang/xiaozhi-skills
初中到高中的生物错题根因分析与档案:按生物六维(概念网络、结构与功能、图表识读、变量与实验设计、表述与术语、遗传与数据计算)定位子类型,给出弱项报告;高中覆盖必修与选择性必修(维度表第八、十一、十二节)。
qizhitang/xiaozhi-skills
遗传推理教练:陪学生做当前这道遗传题——定性状、定基因组成、画遗传图解、算概率;初中讲显性与隐性、基因组成和性别决定,高中必修讲分离定律、自由组合定律、伴性遗传与系谱图判断,以及 DNA 复制与基因表达的计算、可遗传变异、基因频率。
qizhitang/xiaozhi-skills
生物实验探究教练:讲清探究的步骤、对照实验怎么设计、每一步为什么这样做、结论怎么写,覆盖初中常见实验与实验操作考试备考,以及高中必修与选择性必修的学生活动与实验设计题。
qizhitang/xiaozhi-skills
初高衔接规划:中考结束到高一上学期,诊断语文、数学、物理、化学、英语、生物、地理、历史各自的衔接缺口,排出暑假与高一开学头几周的衔接计划,再把具体内容交给对应的学科技能。
Categories
语文病句专项教练:按六类病句(中考、高考卷面常见的分类)判定,并在学生同意后建立语病档案;高中延伸到长句、复句与语境中的词语辨析、语体、简明连贯。. Xiaozhi Chinese Grammar Tracker is an agent skill from qizhitang/xiaozhi-skills.
Xiaozhi Chinese Grammar Tracker fits situations like: education work in your project.
Run `npx skills add qizhitang/xiaozhi-skills --skill xiaozhi-chinese-grammar-tracker -a claude-code`. Or copy the skill folder (student/chinese/xiaozhi-chinese-grammar-tracker in qizhitang/xiaozhi-skills) into .claude/skills/xiaozhi-chinese-grammar-tracker in your project. Claude Code loads it when a task matches its description.
Run `npx skills add qizhitang/xiaozhi-skills --skill xiaozhi-chinese-grammar-tracker -a codex`. Or copy the skill folder (student/chinese/xiaozhi-chinese-grammar-tracker in qizhitang/xiaozhi-skills) into .agents/skills/xiaozhi-chinese-grammar-tracker 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-chinese-grammar-tracker -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-chinese-grammar-tracker, .gemini/skills/xiaozhi-chinese-grammar-tracker, .github/skills/xiaozhi-chinese-grammar-tracker and .opencode/skills/xiaozhi-chinese-grammar-tracker in your project.
SKILL.md names no scripts, command-line tools or credentials: Xiaozhi Chinese Grammar Tracker 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 Chinese Grammar Tracker is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.5k tokens (SKILL.md is roughly 10k 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.
Skills that share tags, products or a category with Xiaozhi Chinese Grammar Tracker: 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.