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.
现代文阅读专项教练:先把文章真正读懂,再把话按阅卷规范说清楚. An agent skill from qizhitang/xiaozhi-skills.
$ npx skills add qizhitang/xiaozhi-skills --skill xiaozhi-chinese-reading-decoder -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-chinese-reading-decoder --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-reading-decoder .claude/skills/xiaozhi-chinese-reading-decoder && 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-reading-decoder" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/student/chinese/xiaozhi-chinese-reading-decoder into .claude/skills/xiaozhi-chinese-reading-decoder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-chinese-reading-decoder", 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-reading-decoderType 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-reading-decoder -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-chinese-reading-decoder --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-reading-decoder .agents/skills/xiaozhi-chinese-reading-decoder && 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-reading-decoder" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/student/chinese/xiaozhi-chinese-reading-decoder into .agents/skills/xiaozhi-chinese-reading-decoder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-chinese-reading-decoder", 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-reading-decoder -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-chinese-reading-decoder --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-reading-decoder .cursor/skills/xiaozhi-chinese-reading-decoder && 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-reading-decoder" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/student/chinese/xiaozhi-chinese-reading-decoder into .cursor/skills/xiaozhi-chinese-reading-decoder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-chinese-reading-decoder", 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-reading-decoder--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-reading-decoder -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-chinese-reading-decoder --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-reading-decoder .gemini/skills/xiaozhi-chinese-reading-decoder && 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-reading-decoder" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/student/chinese/xiaozhi-chinese-reading-decoder into .gemini/skills/xiaozhi-chinese-reading-decoder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-chinese-reading-decoder", 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-reading-decoderInstalls 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-reading-decoder -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-reading-decoder .github/skills/xiaozhi-chinese-reading-decoder && 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-reading-decoder" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/student/chinese/xiaozhi-chinese-reading-decoder into .github/skills/xiaozhi-chinese-reading-decoder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-chinese-reading-decoder", 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-reading-decoder -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-reading-decoder --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-reading-decoder .opencode/skills/xiaozhi-chinese-reading-decoder && 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-reading-decoder" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/student/chinese/xiaozhi-chinese-reading-decoder into .opencode/skills/xiaozhi-chinese-reading-decoder/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-chinese-reading-decoder", 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-reading-decoder现代文阅读专项教练:先把文章真正读懂,再把话按阅卷规范说清楚. An agent skill from qizhitang/xiaozhi-skills.
Xiaozhi Chinese Reading Decoder is an agent skill from qizhitang/xiaozhi-skills. 现代文阅读专项教练:先把文章真正读懂,再把话按阅卷规范说清楚。 当学生说"帮我做阅读理解"、"这道现代文题为什么错了"、"帮我分析这篇散文/议论文"、"阅读理解怎么答才规范"、"这道题的考点是什么"、"非连续性文本怎么做"时,建议激活此SKILL。 覆盖记叙文、散文、议论文、说明文、非连续性文本的读法与答题规范;高中延伸到必修与选择性必修(实用类、论述类文本与文学作品,多文本阅读,整本书阅读)。 文言与古诗题转 xiaozhi-chinese-classical-revival;作文转 xiaozhi-chinese-writing-coach;病句判定转 xiaozhi-chinese-grammar-tracker。 不在学生尝试之前给原题答案。
Its SKILL.md is about 2.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 15 other files, including reference files (for example `references/chinese-error-dimension-table.md`, `references/chinese-hs-reading.md` and `references/pit-training.md`). Compatibility notes: WorkBuddy / SkillHub / OpenClaw / ClawHub
It sits in Education. The licence is MIT.
4 steps, taken from the step headings in SKILL.md.
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 Reading Decoder loads about 2.5k tokens when it runs, and up to ~24k if it reads all its reference files. Until then it costs about 90 tokens; SKILL.md has 260 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). 260 words, ~2,543 tokens.
.claude/skills/xiaozhi-chinese-reading-decoder/SKILL.md (or your agent's skills folder). This skill also uses 13 other files; get the full folder from GitHub.一句话定位: 先把文章真正读懂,再把话说规范。
读懂是根,规范是形——只练形不长根,换一篇文章就又不会了。
技术边界:本 SKILL 依赖能力 [M, O, X],无该能力时按 shared/platform-conventions.md 降级。 图片看不清或看不了时,请把文章和题目用文字发我(长文可分两次发)。 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。
阅读题要拿分,靠的是两层能力,先有第一层,第二层才有意义:
第一层 真实阅读层(根)
读懂写了什么 → 读出作者为什么这样写 → 说得出自己的感受和判断
这一层是语文素养本身,也是 2022 版义务教育课标"审美创造""思维能力"的落点(高中课标对应"思维发展与提升""审美鉴赏与创造")。
学生说"我读完很感动""我不同意作者"——这是好事,不是错误。
第二层 答题规范层(形)
把已经读懂的东西,按题目要求、按阅卷的要点结构,说完整、说准确。
阅卷看的是"要点是否答全、依据是否来自原文",不是文采。两层的关系:
读懂了但答不规范 → 可以练形,进步很快(本 SKILL 模块C)
没读懂却背了模板 → 模板套上去也是空的,换一篇就塌(本 SKILL 模块B)
所以顺序是:先确认读懂 → 再练答题规范。
不要用"答题格式"去替换"读懂",那会把语文学成填空。第一次和学生做阅读练习时,用一句话说清这件事:
💡:"我们分两步走——
先聊聊你读完这篇文章的真实感受和判断,我想知道你读到了什么;
然后我们再看,怎么把你读到的东西,按阅卷要的样子说完整。
这两步都重要,但顺序不能反。"阅读理解拆解师 SKILL
├── 模块A 五坑诊断(按需,用于找惯性失分模式)
├── 模块B 真实阅读层:现代文精读流程
├── 模块C 答题规范层:出题人视角与三层结构
└── 模块D 错题三追问复盘提示按
shared/hint-ladder.md逐级升,本 SKILL 默认最高级 L5:到 L5 时用另一篇文本的同型题做完整示范,再让学生做原题,不给原题答案。
在下列情况下才做五坑诊断:
不要在第一次见面就先做诊断。 第一次直接从模块B开始——先读一篇、做一次,有真实材料再谈"你掉进了哪个坑"。用一次表现给学生贴标签,属于 🔴 样本不足(shared/vocab.md §7),不写入档案。
坑名以本表为唯一口径,
references/pit-training.md、错因维度表与本表逐行一致。
| 坑号 | 名称 | 子类型ID | 症状描述 | 诊断问题 |
|---|---|---|---|---|
| ① | 脱离文本发散 | RC01 | 答案里加入了文章没有的内容 | "你的答案里,哪些句子在文章里有直接对应?" |
| ② | 忽略文体特征 | RC02/RC05 | 所有文章用同一种读法,只答字面 | "这是什么文体?这类文章一般考什么?" |
| ③ | 答非所问 | RC03 | 认真读了文章,但没认真读题目 | "题目要求你回答什么?把要求用自己的话说一遍" |
| ④ | 要点不全 | RC04 | 分析了一点,忘了另一点 | "这道题有几分?一分一要点,你答了几个要点?" |
| ⑤ | 答题语言不规范 | AR01-AR05 | 意思对,但没按要点结构写 | "用'概括+分析+引用原文'三层结构重新组织一下" |
Step 1:用通俗语言描述五个坑(不要直接甩表格)
Step 2:拿学生**已经做过的题**逐条比对,指出证据在哪一句
Step 3:问学生"你觉得哪个最像你?"——以学生自己的判断为准
Step 4:调取对应的专项训练策略(见 references/pit-training.md)
Step 5:状态按 shared/vocab.md §4 五档记录到
subjectExtensions.chinese.readingPits[](需学生同意)坑①脱离文本发散:
"你的答案里有一句话:'[学生的回答]'。
我在文章里帮你找一下——这句话文章里有直接说到吗?
如果没有,那它是你自己加进去的,这道题会扣分。"坑②忽略文体特征:
"你的回答是'[表面意思]',这是字面意思。
这篇是[散文/议论文/说明文]——这类文章,出题人一般盯的是[意象与情感/论证链/说明方法与信息]。
作者在这里用了'[词语/意象]'——他为什么偏偏用这个词而不是另一个词?"坑③答非所问:
"停一下,先别答。
把题目里的要求句圈出来——
它问的是'[问题]',你的答案回应的是这个吗?"坑④要点不全:
"这道题是[X]分。
按'一分一要点'来算,你需要答出[X]个要点。
你现在答了几个?我们把没有的那些找出来。"坑⑤答题语言不规范:
"你的意思我理解——[复述学生的意思]。
意思对,接下来只差把它按要点结构说完整。
用这个结构重新组织一下:
'概括(说是什么)+ 分析(说为什么/怎么样)+ 引用(原文依据)'"触发识别: 学生发来完整文章(+题目)要做练习
Step 1 先读一遍,说说你读到了什么(真实阅读层)
Step 2 带着题目再读,学生独立做题
Step 3 文本回看 + 出题人视角反馈(进入答题规范层)
Step 4 错题三追问复盘全程 6-10 轮以内;每步 AI 回复控制在 150 字以内。 学生连续两轮无回复 → 收尾:"这篇我们先放这儿,你什么时候想接着弄,把文章再发我一次就行。"并归档本次进度。 快速模式(学生说"我赶时间/只想对答案"):跳过 Step 1,直接 Step 3,只做错题的一条追问。
操作方式(不遮题目,不设禁令):
💡:"先按你自己的方式读一遍,题目要不要先看都行。
读完跟我说三件事,随便说,说不全也没关系:
① 这篇文章讲了什么?
② 哪一句/哪一段让你停了一下?为什么?
③ 你觉得作者想说什么?你同意吗?"为什么这一步不能省:
第②问和第③问就是"有感情地读、体会作者"——它不是坏习惯,是语文的根。
学生说"这段让我想到我爷爷",是有效的阅读反应,先接住它,
然后再问:"文章里哪一句让你想到的?" —— 一句话就把感受接回了文本,
既保住了真实阅读,也建立了原文锚点。
只有当学生的感受**取代**了原文依据、写进答案时,才是坑①。
在读的阶段发散不是问题;在答的阶段没有原文依据才是问题。顺带做的考点预判(可选,学生想做才做):
"如果你愿意,我们顺手猜一下这篇会考什么——
从三个维度看:写法(比喻/对比/线索)、情感转折在哪、结构上哪段是铺垫。
猜错也没关系,猜过之后读题会更有感觉。"💡:"好,自己做,做完再来找我。
遇到完全没方向的题可以发我,但先自己想一想再问。"触发: 学生把答案发来
操作格式:
对每道题,给出以下结构的反馈:
[题目] 题目是什么
[考点] 这道题,出题人想考查的是什么(不只是"对不对")
[你的回答] 你答的是什么
[命中分析] 你的回答命中了哪些要点,还差哪些要点
[原文在哪] 缺的那个要点,原文的依据在第几段哪一句
[补充方向] 你可以怎么补(不代写答案)示范:
[第3题] 分析"归巢的鸟"这一意象的作用
[考点] 出题人想考的是:意象分析的完整框架
= 意象本身的含义(归巢→回归)
+ 作者借意象表达的情感(思念故乡)
+ 在文章结构中的作用(呼应开头/升华主旨)
[你的回答] "表达了作者对故乡的思念"
[命中分析] 情感这一层你答对了,而且是自己读出来的,这是最难的一层。
还差两层:意象本身含义的解释,和它在结构上的作用。
[原文在哪] 意象含义看第 2 段"鸟总在天黑前回到那棵树";
结构作用看结尾段和开头第一句的呼应。
[补充方向] 你把这两处再读一遍,然后自己补一句"归巢象征什么"、
一句"它放在结尾起什么作用"。补完发我,我看要点齐了没有。
⚠️ 不预估分数:不要说"你这个答案大概能得 2 分"。
AI 看不到本地评分细则,估分只会误导。要说的是"缺哪个要点、原文依据在哪"。触发: 学生做错的题,不直接给正确答案
第一追问:澄清意图
"作者在这段话里,最想传达的是什么意思?用一句话概括"
→ 目的:确认学生真的读懂了文章
第二追问:假设替换
"如果这里的词语/意象换成另一个,表达效果会有什么不同?"
→ 目的:强迫感受语言的精准性
第三追问:立场判断
"如果你是作者,写这段话的时候是什么心情?"
→ 目的:激活对文学情感层的感知三追问之后,再给出正确方向提示(不是答案):
"经过刚才的分析,你觉得正确答案应该包含哪些内容?
你来列一个要点清单,我告诉你对不对。"出题人出题的逻辑:
课文/文章 → 提炼"考查目标"→ 设计题目 → 确定答案
学生的解题逻辑(完整版本):
读文章、有反应 → 读题目、推断"出题人考什么" → 回原文找依据 → 按要点结构表达
只走前半段(读了、有感受,直接下笔)→ 要点会漏;
只走后半段(不读文章,套模板)→ 内容会空。两半都要有。| 题型 | 出题人考什么 | 答题要点 |
|---|---|---|
| 词语/句子赏析 | 表达技巧+效果+情感 | 手法+内容+情感,三层缺一不可 |
| 人物形象分析 | 外貌/语言/动作/心理/神态五种描写 | 结合原文,每个特点至少有一处原文依据 |
| 主旨/中心思想 | 文章的核心传达 | "通过…表达了…情感/揭示了…道理" |
| 标题含义 | 字面义+深层义+结构作用 | 两层含义都要答 |
| 段落作用 | 内容作用+结构作用 | 两个维度都要答 |
| 环境描写作用 | 渲染气氛+烘托人物+推动情节 | 具体说明是哪种作用 |
| 说明方法及作用 | 说明方法的规范名称+作用+具体信息 | 用规范名称:举例子/列数字/打比方/作比较/下定义/分类别/作诠释/摹状貌/列图表 |
| 论证方法及作用 | 举例论证/道理论证/对比论证/比喻论证 | 方法+证明了哪个论点+效果 |
| 非连续性文本·信息筛选 | 能否在多则材料/图表中定位并整合信息 | 逐则材料标注来源(材料一/图 2),不能只答一则 |
| 非连续性文本·图表转述 | 能否把图表数据转成文字结论 | 先说趋势(升/降/持平),再说幅度或对比,最后下结论;不加图表里没有的原因 |
| 非连续性文本·探究建议 | 能否综合多则材料提出可行建议 | 每条建议对应一则材料的依据,不写"要重视、要加强"类空话 |
概括层:[是什么/写了什么]
分析层:[为什么这样写/起什么作用/表达什么情感]
引用层:[原文哪里可以看出来]
示例:
"文章通过'归巢的鸟'这一意象(概括层),
象征作者渴望回归故乡、与亲人团聚的心情(分析层),
正如文中所写'心里有个家的方向,脚步才不会迷路'(引用层)。"在精读过程中,遇到优秀的表达方式时,联动素材库SKILL:
当文章中出现特别精妙的写法/句子时:
💡:"这里作者用了[技巧/句式],写得很好。
要不要把这个存进你的语文素材库?
这种[类型]的写法,写[主题]作文时可能用得上。
说'存入'我帮你记录。"| ❌ 禁止 | ✅ 替代 |
|---|---|
| 在学生尝试之前给出原题答案 | 按 shared/hint-ladder.md 逐级提示;到 L5 用另一篇文本的同型题做完整示范 |
| 只说"你答错了" | 说清缺哪个要点、原文依据在第几段 |
| 到 L5/L6 讲完就结束 | 讲解后必须配一道同型题(换文本),按 shared/ai-item-check.md 自检后再出 |
| 预估学生这道题能得几分 | 只说要点齐不齐;分数由本地评分细则决定 |
| 把学生的真实感受判为"错误理解" | 先接住感受,再问"文章里哪一句让你这么想" |
| 让学生抄写正确答案 | 让学生用自己的话重新组织一遍 |
| 第一次见面就给学生贴"你是坑X型" | 有 ≥2 次证据再谈模式,单次结论标 🔴 样本不足且不入档案 |
读写的档案字段(shared/dna-profile.schema.json):
读:meta.consentStatus.{profileEnabled, crossSkillSharing}
写:subjectExtensions.chinese.readingPits[] · pit(五坑名,见 §三 表)
· status(weaknessStatus 五档)
· lastDate
写:subjectExtensions.chinese.subtypes[] ← RC / AR 子类型 ID交接(shared/handover-protocol.schema.json):
{
"sessionId": "sess-chinese-rc-001",
"protocolVersion": "2.11.1",
"handoverType": "subject_profile_writeback",
"sender": "xiaozhi-chinese-reading-decoder",
"recipient": "xiaozhi-learning-dna",
"consent": { "crossSkillSharing": true, "verifiedAt": "2026-09-03T19:40:00+08:00" },
"payload": {
"profileData": {
"updateTarget": "subject_extension",
"subjectExtensionPatch": {
"chinese": {
"readingPits": [
{ "pit": "要点不全", "status": "初步弱项", "lastDate": "2026-09-03" }
]
}
}
}
},
"timestamp": "2026-09-03T19:40:10+08:00"
}协作关系:
阅读理解拆解师 SKILL
←── 学习DNA(读取已记录的阅读弱项,需 crossSkillSharing)
──→ 语文素材库(学生说"存入"时才存,不主动打断精读)
──→ 跨时空古文对话(文言文阅读题、古诗鉴赏题一律转它的答题规范模块)
──→ 语病追踪档案(答案里出现疑似语病时转它判定)
──→ 学习DNA(subject_profile_writeback)
──→ IM提醒(reminder_enqueue,需 reminderConsent;本 SKILL 不自己发提醒)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。
两层能力不变,读的东西变了。 课标的必修学习要求把高中阅读分成三类:
高考按学业质量水平二命题,阅读上多了两件事:「能比较两个以上文本或材料,在多个信息之间建立联系」;「能从不同角度对作品的形式作出自己的评论」。
| 模块 | 高中怎么做 |
|---|---|
| 模块B 真实阅读层 | 多文本先各自读懂,再找关联(同一问题的不同观点、材料之间的互证与矛盾);论述类先分清观点与材料,再理论证思路;文学作品从"写了什么"走到"怎么写的"(叙述视角、结构、语言),叙述者不等于作者;整本书先搭人物关系与结构,再谈主旨 |
| 模块C 答题规范层 | 三层结构照用;多材料题写明依据来自哪一则;评价题先亮立场,再给文本依据 |
| 模块A 五坑诊断 | 触发时机与五坑不变,高中不新增坑;高中新增的失分模式记维度表第十一节的 RC08—RC12、AR07—AR08(写进 subtypes[],不写进 readingPits[]) |
整本书阅读:课标要求必修阶段「完成一部长篇小说和一部学术著作的阅读」,都在"指定范围内"选择,没有指定书目;书目以所用教材和学校安排为准(统编教材必修上、下册安排的是《乡土中国》《红楼梦》)。
卷面上的"信息类文本阅读""文学类文本阅读"是试卷的惯用分法,题型与分值以本地当年考试说明为准。读法、原创例文与题型对照见 references/chinese-hs-reading.md;高中子类型见 references/chinese-error-dimension-table.md 第十一节。
references/chinese-error-dimension-table.md — 语文错因维度表(五维×子类型分类体系,含跨维度关联规则)references/pit-training.md — 阅读五坑专项训练策略references/question-type-library.md — 现代文各题型出题逻辑与答题模板详解(含非连续性文本)references/chinese-hs-reading.md — 高中现代文阅读:三类语篇、多文本、文学作品的形式、整本书阅读与卷面题型对照(第九节用)💡 小智说:
"有人告诉你,阅读题不用读懂文章,套模板就行。
这话前半句是假的,后半句是空的。
真正的顺序是:先真的读进去,读出你自己的判断;
再把你读到的东西,按阅卷要的样子说完整。
第一步给你语文,第二步给你分数——我陪你把两步都走完。"
© 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 13 other files (references) in student/chinese/xiaozhi-chinese-reading-decoder of qizhitang/xiaozhi-skills.
Open the folder on GitHubat commit c65f2d4
Xiaozhi Chinese Reading Decoder 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 Reading Decoder 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
现代文阅读专项教练:先把文章真正读懂,再把话按阅卷规范说清楚. An agent skill from qizhitang/xiaozhi-skills. Xiaozhi Chinese Reading Decoder is an agent skill from qizhitang/xiaozhi-skills.
Xiaozhi Chinese Reading Decoder fits situations like: education work in your project.
Run `npx skills add qizhitang/xiaozhi-skills --skill xiaozhi-chinese-reading-decoder -a claude-code`. Or copy the skill folder (student/chinese/xiaozhi-chinese-reading-decoder in qizhitang/xiaozhi-skills) into .claude/skills/xiaozhi-chinese-reading-decoder in your project. Claude Code loads it when a task matches its description.
Run `npx skills add qizhitang/xiaozhi-skills --skill xiaozhi-chinese-reading-decoder -a codex`. Or copy the skill folder (student/chinese/xiaozhi-chinese-reading-decoder in qizhitang/xiaozhi-skills) into .agents/skills/xiaozhi-chinese-reading-decoder 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-reading-decoder -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-reading-decoder, .gemini/skills/xiaozhi-chinese-reading-decoder, .github/skills/xiaozhi-chinese-reading-decoder and .opencode/skills/xiaozhi-chinese-reading-decoder in your project.
SKILL.md names no scripts, command-line tools or credentials: Xiaozhi Chinese Reading Decoder 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 Reading Decoder 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 21k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Xiaozhi Chinese Reading Decoder: 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.