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.
初中到高中的数学错题根因深度分析(高中覆盖必修与选择性必修):把错题本判定的通用四维,细化为数学子类型(B/C/R/M + 两位编码)并做跨维度关联。
$ npx skills add qizhitang/xiaozhi-skills --skill xiaozhi-math-error-dna -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-math-error-dna --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/math/xiaozhi-math-error-dna .claude/skills/xiaozhi-math-error-dna && 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-math-error-dna" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/student/math/xiaozhi-math-error-dna into .claude/skills/xiaozhi-math-error-dna/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-math-error-dna", 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/math/xiaozhi-math-error-dnaType 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-math-error-dna -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-math-error-dna --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/math/xiaozhi-math-error-dna .agents/skills/xiaozhi-math-error-dna && 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-math-error-dna" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/student/math/xiaozhi-math-error-dna into .agents/skills/xiaozhi-math-error-dna/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-math-error-dna", 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-math-error-dna -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-math-error-dna --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/math/xiaozhi-math-error-dna .cursor/skills/xiaozhi-math-error-dna && 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-math-error-dna" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/student/math/xiaozhi-math-error-dna into .cursor/skills/xiaozhi-math-error-dna/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-math-error-dna", 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/math/xiaozhi-math-error-dna--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-math-error-dna -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-math-error-dna --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/math/xiaozhi-math-error-dna .gemini/skills/xiaozhi-math-error-dna && 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-math-error-dna" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/student/math/xiaozhi-math-error-dna into .gemini/skills/xiaozhi-math-error-dna/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-math-error-dna", 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-math-error-dnaInstalls 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-math-error-dna -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/math/xiaozhi-math-error-dna .github/skills/xiaozhi-math-error-dna && 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-math-error-dna" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/student/math/xiaozhi-math-error-dna into .github/skills/xiaozhi-math-error-dna/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-math-error-dna", 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-math-error-dna -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-math-error-dna --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/math/xiaozhi-math-error-dna .opencode/skills/xiaozhi-math-error-dna && 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-math-error-dna" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/student/math/xiaozhi-math-error-dna into .opencode/skills/xiaozhi-math-error-dna/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-math-error-dna", 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-math-error-dna初中到高中的数学错题根因深度分析(高中覆盖必修与选择性必修):把错题本判定的通用四维,细化为数学子类型(B/C/R/M + 两位编码)并做跨维度关联。
Xiaozhi Math Error Dna is an agent skill from qizhitang/xiaozhi-skills. 初中到高中的数学错题根因深度分析(高中覆盖必修与选择性必修):把错题本判定的通用四维,细化为数学子类型(B/C/R/M + 两位编码)并做跨维度关联。 典型触发:"为什么我数学总在同一个地方错""帮我分析我的数学错误规律""帮我生成数学弱项月报""我数学太差了"。 不处理:错题的收录与次数统计(由 xiaozhi-correction-notebook 唯一负责,本 SKILL 只接收它推送的交接)、单题当场讲解(转 xiaozhi-math-problem-solving-coach)、概念重建(转 xiaozhi-math-concept-explainer)、分层练习(转 xiaozhi-math-gradient-trainer)。 未获同意时,不建立长期档案、不跨SKILL共享。
Its SKILL.md is about 3.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 12 other files, including reference files (for example `references/concept-confusion-map.md`, `references/math-error-dimension-table.md` and `references/reading-habits.md`). Compatibility notes: WorkBuddy / SkillHub / OpenClaw / ClawHub
It sits in Education, covering Tutoring and explanations. 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 Math Error Dna loads about 3.7k tokens when it runs, and up to ~21k if it reads all its reference files. Until then it costs about 93 tokens; SKILL.md has 307 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). 307 words, ~3,695 tokens.
.claude/skills/xiaozhi-math-error-dna/SKILL.md (or your agent's skills folder). This skill also uses 10 other files; get the full folder from GitHub.一句话定位: 普通错题本告诉你"哪道题错了"——
数学错误DNA告诉你"你为什么总在同一个地方出错",
然后把模糊的"我数学不行"换成一个具体、能处理的点。
技术边界:本 SKILL 依赖能力 [M, X],无该能力时按 shared/platform-conventions.md 降级。 无跨会话统计(X)时:不输出"上周做了 N 道错了 M 道"类历史精确数字,只输出本次会话内的计数,或"从档案看大致…"并标 🟡 初步趋势。 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)。
- 查看:「查看我的数学错误档案」
- 更正:「更正我的档案」
- 删除:「删除我的档案」(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:「导出我的档案」(以文本形式给出,便于转存)传统错题处理的问题:
出错 → 看答案 → 抄步骤 → 下次同类题,还是出错
↑
处理的是"这道题的表面"
没有处理"出错的根因"这个SKILL解决的问题:
出错 → 分析根因 → 分类存档 → 发现规律 → 顽固弱项专项突破
↑
从"这道题"上升到"这类错误"
从孤立事件变成可分析的数据⚠️ 【架构定位声明——数学错题双SKILL协作协议】 本SKILL是通用核心包中"❌ 智能错题本 SKILL"在数学领域的专属扩展实现,并非独立的第二套错题本。两者按以下协议分工协作:
| 职责 | 归属 | 说明 |
|---|---|---|
| 接收数学错题(初始触发) | 通用错题本 | 统一入口,所有科目错题先经过通用错题本 |
| 拍题三信息法(信息收集) | 通用错题本 | 通用错题本的标准流程 |
| 通用四维判定(概念模糊/计算失误/读题失误/方法用错) | 通用错题本 | 词表见 shared/vocab.md §1,完成后交接至本SKILL |
| 表面信息存档 | 通用错题本 | 记录题目、答案、日期、来源、状态等表面字段 |
| 次数统计与弱项状态判定 | 通用错题本(唯一权威) | 按 shared/vocab.md §5 计数;本 SKILL 不自行计数,只接收错题本推送的"顽固"事件 |
| 子类型精确定位(B01/C01/R01/M01 等) | 本SKILL | 接收通用错题本的四维判定后,进行深度子类型定位 |
| 跨维度关联分析 | 本SKILL | 通用错题本不做跨维度分析 |
| 顽固弱项的专项突破流程 | 本SKILL | 判定归错题本、突破流程归本SKILL |
| 数学焦虑处理 | 本SKILL | 通用错题本检测到焦虑信号词后转交本SKILL;危机信号按 shared/crisis-exception.md,不进本流程 |
| 数学弱项月报 | 本SKILL | 学生要求时生成,通用错题本不重复生成数学月报 |
| 学期全景报告·数学章节 | 通用错题本(汇总层) | 本SKILL提供数据,通用错题本做跨科目汇总呈现 |
| IM提醒·数学部分 | xiaozhi-im-reminder(唯一发送方) | 本SKILL只生成 reminder_enqueue 入队,不自行承诺提醒时间 |
核心原则:通用层记表面并唯一计数,数学层记根因;不产生重复记录,不重复触发预警。 本 SKILL 不独立接收学生直接触发的数学错题——学生说"帮我记这道数学错题"时,由通用错题本收题,再交接给本 SKILL 做深度分析。
通用四维由通用错题本判定,本 SKILL 只在其基础上做子类型细化。每一道错题只记一个主维度:
| 通用维度 | 定义 | 一句话判定 | 数学层根治方法 |
|---|---|---|---|
| 计算失误(数学子类型前缀 C) | 解题思路正确,在运算过程中出现错误 | 思路对、列式对,算错/抄错/漏单位 | 专项计算步骤训练;找到"哪一步操作"最容易出错 |
| 概念模糊(前缀 B) | 对某个定义、定理、公式的理解有偏差 | 换成"纯净版"最简题也做不对 | 概念追问;用类比重建理解;见 references/concept-confusion-map.md |
| 方法用错(前缀 M) | 知道相关知识点,但选错了解题策略 | 概念清楚、读题无误,但选错工具/路径 | 题型识别训练;梳理"哪类题用哪类方法"的对应关系 |
| 读题失误(前缀 R) | 题意理解偏差,漏读或误读条件 | 把条件读对后立刻会做 | 读题习惯训练;高亮关键词练习;见 references/reading-habits.md |
判定顺序:先 R(复述条件)→ 再 B(纯净版)→ 再 M(换题型)→ 剩下的归 C。
子类型编码(如 B02、C01、R05、M03)定义在 references/math-error-dimension-table.md,与通用维度的对应关系见 shared/vocab.md §2。
错题记录条目(本 SKILL 的深度分析层,写入 dna-profile 的
`subjectExtensions.math.subtypes[]`;表面字段由通用错题本持有):
errorId:沿用通用错题本的记录 ID(不另起一套编号)
知识点标签:(如:二元一次方程/相似三角形/勾股定理)
通用维度(basicDimension):[概念模糊 / 计算失误 / 读题失误 / 方法用错]
子类型ID(subtypeId):[如 B02/C01/M02/R05,见 references/math-error-dimension-table.md]
跨维度关联:[主维度+次要维度,如 "B03+C02",无则填"无"]
深度根因(rootCause,一句话):(如:“符号规则理解偏差导致移项变号遗漏,纯净版测试确认不是执行层失误”)
弱项状态(status):[待处理 / 初步弱项 / 顽固弱项 / 突破中 / 已攻克](五档,见 shared/vocab.md §4)
置信度:🟢 数据充分 / 🟡 初步趋势 / 🔴 样本不足(schema: data_sufficient / preliminary_trend / insufficient_sample)
攻克验证方式(crackedVerification):(如:“间隔 4 天两次独立验证,其中一次为换题型”)
⚠️ 次数(occurrenceCountInWindow)由通用错题本统计并随交接带过来,
本 SKILL 只读不写、不自行累加。只在收到通用错题本的交接后触发(本 SKILL 不独立收题):
├── 交接类型「新错题」 → 做子类型定位与跨维度分析
├── 交接类型「顽固弱项确认」(由错题本按 shared/vocab.md §5 判定)→ 启动四步突破
├── 交接类型「深度分析请求」 → 生成错误类型图谱
└── 交接类型「焦虑信号」 → 先做危机信号检查,再走 §七
学生说"帮我记录这道数学错题" / 发来错题图片说"存入档案":
→ 回一句"我把它交给错题本收录,收好之后我来分析你错在哪一类",
由通用错题本收题后交接给本 SKILL。
状态变更(待处理→初步弱项→顽固弱项→突破中→已攻克)一律按
shared/vocab.md §4/§5 的条件,由错题本裁定,本 SKILL 回写建议值。判定权威在通用错题本:口径按 shared/vocab.md §5(同一知识点 + 同一通用维度,滚动 28 天累计 3 次,同一天多次只计 1 次)。
本 SKILL 收到错题本推送的"顽固弱项确认"后启动下面的突破流程,不自行数次数、不自行宣布"第3次了"。
🧬 档案提醒(收到错题本的顽固事件后):
"错题本那边确认了一件事——
你在[知识点X]上的[通用维度]在 28 天里累计到了 3 次:
第1次:[日期] [题目概述]
第2次:[日期] [题目概述]
第3次:今天 [题目概述]
这可能是一个'顽固弱项'。
如果你愿意,我可以把它加入持续跟踪档案,后面专门帮你验证和突破。
现在有10分钟吗?我们来处理它。"Step 1:根因确认
不复述之前的分析——直接出一道"纯净版"题
(只包含这一个知识点,排除其他干扰;
生成前按 shared/ai-item-check.md 自检):
"先做这道题,只需要30秒:[纯净版题目]"
Step 2:规则重建
如果纯净版做错:说明是概念层(B 类)问题
→ 转 xiaozhi-math-concept-explainer 重建这个知识点
如果纯净版做对:说明是干扰条件下的识别/执行问题
→ 出 2-3 道"加入干扰条件"的递进题(同样先自检)
Step 3:验证锁定(口径按 shared/vocab.md §5)
"你刚才做对了——按规矩还要再确认一次。
隔至少 3 天我再出一道同类型的题,
两次独立验证都做对(其中一次是换题型或纯净版),才算攻克。"
Step 4:写入档案
在学生同意持续跟踪时,把建议状态"突破中"回写给通用错题本
(deep_analysis_writeback,见 §8.2),由错题本落定状态。
学生同意提醒时,生成一条 reminder_enqueue 交给 xiaozhi-im-reminder,
按 shared/vocab.md §9 合并发送;本 SKILL 不承诺"我明天提醒你"。触发: 学生说"帮我分析我的数学错误规律"时生成;不默认按月生成
从档案中统计所有错题记录,生成以下结构的分析报告:
📊 数学错误类型图谱
统计时间范围:[本学期 / 本月 / 自定义]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
错误类型分布:
计算失误 ████████████ 38% (N次)
概念模糊 ████████ 24% (N次)
读题失误 ███████ 22% (N次)
方法用错 █████ 16% (N次)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
AI诊断:
[计算失误占比>30%]
→ 计算失误比例偏高。
深挖:这[N]次计算失误集中在[具体步骤]——
其中[X]次发生在符号处理,[Y]次发生在分数运算。
建议:专项针对[符号处理/分数运算]的流程训练,
不是多做题,而是放慢速度做对每一步。
[概念模糊最集中的知识点]
→ 概念模糊主要集中在[知识点A]和[知识点B]。
这两个知识点有一个共同点:[分析]。
建议:先用概念解释器重建[知识点A]的理解,
再做3道纯概念应用题确认。
[读题失误高频触发词]
→ 读题失误中,有[X]次都涉及"[关键词]"这类条件——
这说明你对含有[关键词]的题型需要特别注意审题习惯。
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
弱项清单(状态用 shared/vocab.md §4 五档;次数取自错题本):
[弱项1](28天内累计N次,状态:顽固弱项)🟢 数据充分
[弱项2](28天内累计N次,状态:突破中)🟡 初步趋势
[弱项3](状态:已攻克,上次错误:[日期])🟢 数据充分
近期进步:
✅ [弱项X] 两次独立验证做对(间隔≥3天,含1次换题型),状态改为已攻克
✅ [具体子类型]的错题条数比上一统计周期减少(数字取自错题本,
无跨会话统计能力时不写具体数字,改写"最近没有新增记录"并标 🟡)置信度标签只用 🟢 数据充分 / 🟡 初步趋势 / 🔴 样本不足(对应 schema 的
data_sufficient/preliminary_trend/insufficient_sample);⚠️不再用于置信度。 🔴 样本不足的结论只在当前会话使用,不写入长期档案。
触发: 学生说"帮我生成数学月报"时生成;不默认自动提示
📋 数学弱项月报
学生:[姓名/昵称]
报告周期:[月份]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
一、本月学习概况
拍照训练次数:[N]次
涉及知识模块:[列举]
最活跃的学习日:[日期](做了N道)
二、错误类型变化(对比上月)
计算失误:[本月N次] vs [上月N次] [↑升/↓降/→持平]
概念模糊:[本月N次] vs [上月N次] [↑升/↓降/→持平]
读题失误:[本月N次] vs [上月N次] [↑升/↓降/→持平]
方法用错:[本月N次] vs [上月N次] [↑升/↓降/→持平]
三、本月最大进步
[具体进步,必须有数据支撑]
示例:"二次函数相关题型的错误率从每5道错2道降到5道错0-1道"
四、本月最需关注
[最顽固的弱项,说明根因和突破建议]
五、下月重点攻克目标
目标1:[具体知识点+具体训练方法]
目标2:[具体知识点+具体训练方法]
六、给家长看的数据摘要(**默认不生成**)
生成前先检查 `meta.consentStatus.parentSharingConsent`;
摘要里含情绪/焦虑相关内容时,再检查 `emotionSharingWithParent`。
任一为 false → 只把摘要给学生本人,并告诉他"你可以自己决定要不要转给家长"。
两项都为 true 时才输出:
这个月[孩子昵称]在数学上:
✅ 完成了[N]次系统练习
✅ 攻克了[N]个弱项:[列举]
📌 仍在处理的地方:[简短事实描述]
📈 变化最明显的一项:[一句话]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━月报不默认推送给家长,也不默认按月自动生成——学生说"帮我生成数学月报"时才生成。
⚠️ 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。
① 危机信号(自伤/轻生/霸凌/家庭安全/持续严重绝望)
→ 不进本节流程,按上面的危机例外处置,档案只记"已触发危机转介"
② 学习压力信号(本节处理):
- "我数学太差了"
- "一考数学就脑子空白"
- "感觉怎么学都学不会"
- "明天考试,我完全没把握"
- "我就是学不好数学"
→ 走下面的四步流程
判不准时按①处理——宁可误报,不可漏报。Step 1:确认感受(1-2句,不展开)
"你现在很担心,我听到了。
先别急,我来看一下你的档案说了什么。"
Step 2:调取档案里的具体条目(关键步骤)
不说"你肯定行",而是说:
"你的档案里记着:
[具体知识点]的错题集中在[精确子类型],
当前状态是[五档之一]。
[另一个知识点]之前也在这个清单上,
后来两次独立验证都做对了,已经标成攻克。"
⚠️ 数字只能来自错题本的统计;无跨会话统计能力(X)时不报具体次数,
改说"从档案看大致集中在[X]"并标 🟡 初步趋势,不编造历史数字。
Step 3:把模糊焦虑变成具体任务
"所以'数学不行'这个说法太宽了——
你现在真正需要的是:
搞定[精确子类型]这一个点。
我们现在做3道,针对这个点。
做完了,你去考试心里有底了。"
Step 4:执行(出3道递进题,生成前按 shared/ai-item-check.md 自检)
第1道:档案里做对过的同类型(先站稳)
第2道:精确的弱项点(直面问题)
第3道:弱项点的变形(确认迁移)不承诺"做完就不焦虑了""这个感觉就会消失"——只说下一步做什么、做完能确认什么。
数学错误DNA SKILL
<-- xiaozhi-correction-notebook(wrong_answer_handover:通用四维 + 表面信息 + 28天累计次数)
--> xiaozhi-correction-notebook(deep_analysis_writeback:subtypeId + 深度根因 + 建议状态)
<-- xiaozhi-math-problem-solving-coach(间接:教练的错题先进错题本,再由错题本交接过来)
--> xiaozhi-math-problem-solving-coach(考前梳理时提供弱项清单与子类型ID)
--> xiaozhi-math-concept-explainer(B 类概念错误转交重建)
--> xiaozhi-math-gradient-trainer(弱项攻克后可转进阶;训练层级由它写
dna-profile 的 subjectExtensions.math.gradientLevel)
--> xiaozhi-im-reminder(仅 reminder_enqueue 入队,按 shared/vocab.md §9 合并)
--> xiaozhi-learning-dna(subject_profile_writeback:写
subjectExtensions.math.subtypes[];须 meta.consentStatus.crossSkillSharing=true)
--> xiaozhi-weekly-review(仅提供本周数学错误摘要)本SKILL与通用错题本构成专属层→通用层的纵向协作关系,是§一架构定位声明的操作细则。
本SKILL从通用错题本接收以下类型的交接记录:
交接一律用 handoverType: "wrong_answer_handover",由 payload.wrongAnswerData.handoverTrigger 区分场景:
handoverTrigger = "new_error"(新错题)
触发:通用错题本完成数学科目通用四维判定后
接收字段:concept + basicDimension + surfaceInfo{questionAbstract, studentAnswer,
correctAnswer, surfaceRootCause} + occurrenceCountInWindow
本SKILL动作:子类型精确定位(subtypeId,如 B02)+ 跨维度关联 + 深度根因
handoverTrigger = "stubborn_weakness"(顽固弱项确认)
触发:错题本按 shared/vocab.md §5 判定累计 3 次(本SKILL不重复计数)
接收字段:historyRefs[] + occurrenceCountInWindow
本SKILL动作:四步突破流程(纯净版测试-规则重建-验证锁定-回写建议状态)
handoverTrigger = "anxiety_trigger"(焦虑信号转交)
触发:通用错题本检测到数学焦虑信号词
接收字段:anxietySignals[]
本SKILL动作:先做危机信号分级(§七),学习压力类才走四步流程
深度分析请求(学生说"为什么我总在这种题上出错"):
仍由错题本转交,trigger 记 "new_error" 并带 historyRefs[];
本SKILL动作:生成错误类型图谱(§五)或针对性分析收到的交接示例(字段与 handover-protocol.schema.json 一致):
{
"sessionId": "sess-20260903-002",
"protocolVersion": "2.11.1",
"handoverType": "wrong_answer_handover",
"sender": "xiaozhi-correction-notebook",
"recipient": "xiaozhi-math-error-dna",
"consent": { "crossSkillSharing": true, "verifiedAt": "2026-09-03T20:10:00+08:00" },
"payload": {
"wrongAnswerData": {
"errorId": "math-20260903-007",
"subject": "math",
"concept": "整式运算·去括号",
"handoverTrigger": "stubborn_weakness",
"basicDimension": "概念模糊",
"subtypeId": "B02",
"occurrenceCountInWindow": 3,
"surfaceInfo": {
"questionAbstract": "化简 3-(2x-1)",
"studentAnswer": "3-2x-1",
"correctAnswer": "4-2x",
"surfaceRootCause": "括号前是负号时只变了第一项"
},
"historyRefs": ["math-20260815-003", "math-20260828-011"]
}
},
"timestamp": "2026-09-03T20:10:05+08:00"
}回写一律用 handoverType: "deep_analysis_writeback",payload 为 deepAnalysisData:
{
"sessionId": "sess-20260903-002",
"protocolVersion": "2.11.1",
"handoverType": "deep_analysis_writeback",
"sender": "xiaozhi-math-error-dna",
"recipient": "xiaozhi-correction-notebook",
"consent": { "crossSkillSharing": true, "verifiedAt": "2026-09-03T20:25:00+08:00" },
"payload": {
"deepAnalysisData": {
"errorId": "math-20260903-007",
"subject": "math",
"subtypeId": "B02",
"basicDimension": "概念模糊",
"rootCause": "把“括号前的负号”当成只作用于第一项,纯净版测试确认是规则理解偏差而非执行失误",
"status": "突破中",
"crackedVerification": "间隔4天两次独立验证,其中一次为换题型",
"recommendedAction": "先用概念解释器重建“负号分配”,再做3道加干扰条件的递进题"
}
},
"timestamp": "2026-09-03T20:25:03+08:00"
}字段口径:
subtypeId → 数学子类型(B/C/R/M + 两位数字),本SKILL产出
basicDimension → 通用四维,沿用错题本判定,不擅自改判
status → 五档(待处理/初步弱项/顽固弱项/突破中/已攻克),本SKILL给**建议值**,
最终由错题本按 shared/vocab.md §4/§5 落定
crackedVerification → 攻克时写明"两次独立验证、间隔≥3天、含1次换题型/纯净版"
月度摘要:不走回写通道,学生要求生成月报时在会话内输出(§六)。为防止数学错题的双重触发,本SKILL遵守以下规则:
规则一:不独立接收数学错题、不独立计数
所有数学错题的初始接收与 28 天窗口计数由通用错题本统一处理(shared/vocab.md §5)
本SKILL只接收通用错题本推送的交接记录
学生直接说"帮我记录这道数学错题"时,由通用错题本收题,再交接至本SKILL
规则二:不重复生成递进练习
通用错题本在数学科目不独立生成顽固弱项的递进练习
本SKILL统一执行四步突破流程
规则三:提醒只入队,不自行发送
本SKILL生成 reminder_enqueue 交给 xiaozhi-im-reminder(唯一发送方),
由它按 shared/vocab.md §9 的每日预算合并;本SKILL正文不出现"我会在X时提醒你"
规则四:学期报告数据由本SKILL提供
本SKILL不生成学期报告,数学数据交给通用错题本汇总
数学弱项月报(§六)在学生要求时由本SKILL生成协作边界:
meta.consentStatus.profileEnabled)parentSharingConsent;含情绪内容再检查 emotionSharingWithParentcrossSkillSharing 为 false 时只用本次会话)依据《普通高中数学课程标准日常修订版(2017 年版 2025 年修订)》。学生说明在读高中,或初中毕业后做衔接预习时用本节;初中学生仍用维度表第二至五节的子类型。
| 学段 | 范围 | 子类型 |
|---|---|---|
| 初中 | 本 SKILL 的主体 | 维度表第二至五节 |
| 高中·高一衔接段 | 必修主题一"预备知识"、主题二"函数":集合、常用逻辑用语、不等式、从函数观点看一元二次方程与不等式;函数概念与性质、幂函数、指数函数、对数函数、三角函数、函数应用 | 维度表第九节:B10—B18、C09—C11、M07—M09、R07—R08 |
| 高中·必修后半 | 必修主题三"几何与代数"(平面向量及其应用、复数、立体几何初步)、主题四"概率与统计"(概率、统计) | 维度表第十节:B19—B26、C12—C14、M10、R09 |
| 高中·选择性必修 | 数列、一元函数导数及其应用;空间向量与立体几何、平面解析几何;计数原理、概率、统计 | 维度表第十一节:B27—B38、C15—C16、M11—M16、R10 |
学业水平考试的范围是必修课程,高考的范围是必修与选择性必修课程(课标:高考命题不超过学业质量水平二)。选修课程(A~E 类)和必修、选择性必修以外的内容,如实说明不覆盖,只做通用四维分类。课标标*的选学内容(如数学归纳法、贝叶斯公式)不作为考试要求。
高一最常见的六处断层(子类型定义与验算断言见维度表第九节):
高一下到高三最常见的断层(子类型定义与验算断言见维度表第十、十一节):
突破流程与初中相同(第四节):先用纯净版题定位;B 类转数学概念解释器,M07、M08、M10—M16 转数学解题教练,M06(测量题画不出图)与 M09(函数、数列与回归模型选错)转应用题数学建模教练;间隔 3 天以上两次独立做对才算攻克。纯净版题与变式题生成前按 shared/ai-item-check.md 自检。
references/math-error-dimension-table.md — 数学错因维度表(四维×子类型分类体系,含跨维度关联规则与追踪标准;第九至十一节为高中的子类型:高一衔接段、必修后半、选择性必修,含 CI 验算断言)references/concept-confusion-map.md — 初中数学高频概念混淆对照表references/reading-habits.md — 数学读题失误训练方法手册💡 小智说:
"你说'数学不行',我不同意。
我看到的是:
你在[具体地方]反复错在同一个点上,
根因是[精确原因]。
这不是'数学不行',这是一个可以被处理的具体问题。
把话说具体,事情就有了下一步。"
© 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 10 other files (references) in student/math/xiaozhi-math-error-dna of qizhitang/xiaozhi-skills.
Open the folder on GitHubat commit c65f2d4
Xiaozhi Math Error Dna 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 Math Error Dna this skillqizhitang/xiaozhi-skills | 105 | — | ~3.7k | Automated safety check: Pass | MIT | |
| DeepTutor CLIHKUDS/DeepTutor | 41k | — | ~2.8k | Automated safety check: Pass | Apache-2.0 | |
| AI Engineering Project Tutorrohitg00/ai-engineering-from-scratch | 66k | — | ~1.6k | Automated safety check: Pass | MIT | |
| Hung-Yi Lee Teaching Stylevoidful/hung-yi-lee-skill | 1.3k | — | ~13k | Automated safety check: Pass | None | |
| Claude Certification Tutorrohitg00/ai-engineering-from-scratch | 66k | — | ~3k | Automated safety check: Pass | MIT | |
| StudyVault Quiz Tutorbevibing/tutor-skills | 1.3k | — | ~1.4k | Automated safety check: Pass | MIT |
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
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.
voidful/hung-yi-lee-skill
Explains machine learning, LLMs, AI agents and speech modeling in a Hung-Yi Lee-inspired teaching style, drawing on a knowledge base built from his lectures and research references.
rohitg00/ai-engineering-from-scratch
Guides a learner through one of four independent Claude certification tracks with onboarding, lessons, practice labs, mock exams and remediation.
bevibing/tutor-skills
Quizzes you on the notes in an Obsidian StudyVault, tracks proficiency per concept and drills weak areas in four-question rounds.
THU-MAIC/OpenMAIC
Designs a review-and-practice lesson around an independent first attempt, targeted feedback, supported practice, a fresh independent check and a next step.
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
初中到高中的数学错题根因深度分析(高中覆盖必修与选择性必修):把错题本判定的通用四维,细化为数学子类型(B/C/R/M + 两位编码)并做跨维度关联。. Xiaozhi Math Error Dna is an agent skill from qizhitang/xiaozhi-skills.
Xiaozhi Math Error Dna fits situations like: tasks that involve Tutoring and explanations.
Run `npx skills add qizhitang/xiaozhi-skills --skill xiaozhi-math-error-dna -a claude-code`. Or copy the skill folder (student/math/xiaozhi-math-error-dna in qizhitang/xiaozhi-skills) into .claude/skills/xiaozhi-math-error-dna in your project. Claude Code loads it when a task matches its description.
Run `npx skills add qizhitang/xiaozhi-skills --skill xiaozhi-math-error-dna -a codex`. Or copy the skill folder (student/math/xiaozhi-math-error-dna in qizhitang/xiaozhi-skills) into .agents/skills/xiaozhi-math-error-dna 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-math-error-dna -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-math-error-dna, .gemini/skills/xiaozhi-math-error-dna, .github/skills/xiaozhi-math-error-dna and .opencode/skills/xiaozhi-math-error-dna in your project.
SKILL.md names no scripts, command-line tools or credentials: Xiaozhi Math Error Dna 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 Math Error Dna is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.7k tokens (SKILL.md is roughly 15k 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 17k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Xiaozhi Math Error Dna: DeepTutor CLI (HKUDS/DeepTutor, 41k stars), AI Engineering Project Tutor (rohitg00/ai-engineering-from-scratch, 66k stars), Hung-Yi Lee Teaching Style (voidful/hung-yi-lee-skill, 1.3k stars) and Claude Certification Tutor (rohitg00/ai-engineering-from-scratch, 66k 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.