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.
把独立教师散在文件夹、微信收藏和笔记本里的讲义、题目、讲评话术、错因案例收进一个可检索的库. An agent skill from qizhitang/xiaozhi-skills.
$ npx skills add qizhitang/xiaozhi-skills --skill xiaozhi-teach-resource-library -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-teach-resource-library --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/qizhitang/xiaozhi-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/teacher/independent/xiaozhi-teach-resource-library .claude/skills/xiaozhi-teach-resource-library && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "xiaozhi-teach-resource-library" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/teacher/independent/xiaozhi-teach-resource-library into .claude/skills/xiaozhi-teach-resource-library/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-teach-resource-library", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/qizhitang/xiaozhi-skills/tree/main/teacher/independent/xiaozhi-teach-resource-libraryType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add qizhitang/xiaozhi-skills --skill xiaozhi-teach-resource-library -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-teach-resource-library --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/qizhitang/xiaozhi-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/teacher/independent/xiaozhi-teach-resource-library .agents/skills/xiaozhi-teach-resource-library && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "xiaozhi-teach-resource-library" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/teacher/independent/xiaozhi-teach-resource-library into .agents/skills/xiaozhi-teach-resource-library/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-teach-resource-library", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add qizhitang/xiaozhi-skills --skill xiaozhi-teach-resource-library -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-teach-resource-library --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/qizhitang/xiaozhi-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/teacher/independent/xiaozhi-teach-resource-library .cursor/skills/xiaozhi-teach-resource-library && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "xiaozhi-teach-resource-library" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/teacher/independent/xiaozhi-teach-resource-library into .cursor/skills/xiaozhi-teach-resource-library/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-teach-resource-library", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/qizhitang/xiaozhi-skills.git --path teacher/independent/xiaozhi-teach-resource-library--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add qizhitang/xiaozhi-skills --skill xiaozhi-teach-resource-library -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-teach-resource-library --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/qizhitang/xiaozhi-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/teacher/independent/xiaozhi-teach-resource-library .gemini/skills/xiaozhi-teach-resource-library && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "xiaozhi-teach-resource-library" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/teacher/independent/xiaozhi-teach-resource-library into .gemini/skills/xiaozhi-teach-resource-library/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-teach-resource-library", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-teach-resource-libraryInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add qizhitang/xiaozhi-skills --skill xiaozhi-teach-resource-library -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/qizhitang/xiaozhi-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/teacher/independent/xiaozhi-teach-resource-library .github/skills/xiaozhi-teach-resource-library && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "xiaozhi-teach-resource-library" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/teacher/independent/xiaozhi-teach-resource-library into .github/skills/xiaozhi-teach-resource-library/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-teach-resource-library", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add qizhitang/xiaozhi-skills --skill xiaozhi-teach-resource-library -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-teach-resource-library --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/qizhitang/xiaozhi-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/teacher/independent/xiaozhi-teach-resource-library .opencode/skills/xiaozhi-teach-resource-library && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "xiaozhi-teach-resource-library" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/teacher/independent/xiaozhi-teach-resource-library into .opencode/skills/xiaozhi-teach-resource-library/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-teach-resource-library", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
xiaozhi-teach-resource-library把独立教师散在文件夹、微信收藏和笔记本里的讲义、题目、讲评话术、错因案例收进一个可检索的库. An agent skill from qizhitang/xiaozhi-skills.
Xiaozhi Teach Resource Library is an agent skill from qizhitang/xiaozhi-skills. 把独立教师散在文件夹、微信收藏和笔记本里的讲义、题目、讲评话术、错因案例收进一个可检索的库。 适用于老师说"帮我找一下 [X] 的讲义""有没有 [X 题型] 的题""这类错题怎么讲评""这个讲义存一下""教过的类似案例""这个教案能给别的学员用吗""资源怎么分类"。 流程:入库时打标签与版权状态 → 按知识点/难度检索 → 改编适配后复用 → 记录用过几次、效果如何。 本 SKILL 不出题、不备课、不批改、不联系家长——只管资源的存、找、改;AI 生成的题必须老师验算后才算入库。
Its SKILL.md is about 3.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 14 other files, including reference files (for example `references/copyright-annotation-template.md`, `references/resource-categorization.md` and `references/resource-entry-examples.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.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
WorkBuddy / SkillHub / OpenClaw / ClawHub
From compatibility in the SKILL.md frontmatter.
Xiaozhi Teach Resource Library loads about 3.1k tokens when it runs, and up to ~7.1k if it reads all its reference files. Until then it costs about 69 tokens; SKILL.md has 264 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). 264 words, ~3,126 tokens.
.claude/skills/xiaozhi-teach-resource-library/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: 独立教师最贵的资产不是学员名单,而是你积累的教学经验——把它从"脑子里"搬到"库里",才算真的拥有。
技术边界:本 SKILL 依赖能力 [M, F],无该能力时按 shared/platform-conventions.md 降级。
教学主体边界:本 SKILL 只给老师出草稿、做分析,不替老师上课,不代老师回答学生的问题,也不代老师评价学生;面向学生或家长的内容,一律由老师审定后再用(教育部《中小学生成式人工智能使用指南(2025 年版)》)。
适用范围:用于校外培训(一对一、小班)时,只在合法范围内用,口径见
shared/off-campus-training.md——学科类须经审批,各地已不再审批新的学科类培训机构;不占学校上课时间,线下 20:30、线上 21:00 前结束,不给学员留作业,一次收费不超过 3 个月或 60 课时,高中学员同样适用;面向义务教育阶段学生的另外不占用休息日、节假日与寒暑假,线上每课时不超过 30 分钟,面向高中学生的这两条参照执行。本技能不预设违规的排课、作业与收费。
资源库不向学员推送任何东西,只在老师检索时给出候选。学员案例入库必须完全脱敏(化名、模糊学段、去掉可识别细节),不允许反查到具体学员。
版权:每条资源必须有 copyrightStatus,取值只有 shared/vocab.md §11 的四档——自有 / 改编 / 公开可引用 / 仅存索引。教辅原题与历年真题一律 仅存索引,只记书名、页码、题号,不录入题干。禁止存储盗版扫描件与未授权转载的网络资源。
AI 生成的题:本 SKILL 自己不出题,但会接收其他环节生成的题。凡是 AI 生成的,aiGenerated 置为 true,入库时必须带上【AI 生成,入库前请人工验算】标注;老师逐题验算并把 verifiedByTeacher 置为 true 之前,这条资源不得用于学员。生成规则见 shared/ai-item-check.md。
试题保密:启用前的统考试题不得录入资源库,也不得输入本 SKILL——国家、省、地(市)级教育统一考试启用前的试题、参考答案、评分标准属国家秘密(《教育工作中国家秘密及其密级具体范围的规定》),区县级、校级统考按当地保密要求同样处理。统考结束后的试卷可按上面的版权规则入库,历年真题仍一律 仅存索引。跨校联考要等参加的学校全部考完,分几天、分批进行的考试要等全部批次、全部场次考完,同一份卷子还有学生补考的要等补考考完,这之后才能入库;考后不公开试卷的考试(如用题库命题、机考的),不据学生回忆还原原题入库。依据《中小学生成式人工智能使用指南(2025年版)》教师一节:“严禁将个人信息、考试试题等敏感数据输入AI工具”。
独立教师资源管理常见的三个误区:
误区① 资源散落:讲义在电脑文件夹、题库在微信收藏、
讲评话术在脑子里、错题案例在笔记本上,
需要时找不到,找到时已过时。
误区② 从零开始:每个新学员/新学期都从零备课,
之前教过的优秀案例、题库、讲评话术
都没有积累,白白浪费。
误区③ 资源孤岛:优秀讲义、题库、讲评话术
只在某个学员/某次课用一次,
之后被遗忘。本 SKILL 要解决的是:
| 触发场景 | 示例语句 |
|---|---|
| 资源检索 | "帮我找一下 [X 讲义]" / "有没有 [X 题型]" |
| 讲评话术 | "这类错题怎么讲评" / "讲评怎么说" |
| 学员匹配 | "[化名] 适合什么资源" |
| 案例查找 | "教过的案例" / "类似情况怎么处理" |
| 资源入库 | "这个讲义/题库/案例存一下" |
| 资源管理 | "资源怎么分类" / "教学资源库" |
| 错因案例 | "学员犯过这种错吗" / "类似错因" |
| 教案复用 | "这个教案可以给另一个学员用吗" |
┌──────────────────────────┐
│ ① 入库 │
│ 分类 + 版权状态 │
└────────────┬─────────────┘
↓
┌──────────────────────────┐
│ ② AI 生成的先验算 │
│ aiGenerated=true │
│ 老师验算 → verifiedByTeacher│
└────────────┬─────────────┘
↓
┌──────────────────────────┐
│ ③ 打标签 │
│ 学科/知识点/难度/学段 │
└────────────┬─────────────┘
↓
┌──────────────────────────┐
│ ④ 检索 │
│ 关键词/知识点/难度 │
└────────────┬─────────────┘
↓
┌──────────────────────────┐
│ ⑤ 改编适配后复用 │
│ 记来源 + 记效果 │
└──────────────────────────┘生成时(在别的环节):
按 shared/ai-item-check.md 自检——自解一遍、有解且唯一、
条件充分不多余、数值友好、学段内、与原题同维度
到本 SKILL 入库时:
aiGenerated = true
verifiedByTeacher = false(默认)
标题或 usageNotes 带【AI 生成,入库前请人工验算】
老师逐题验算后说"验过了":
verifiedByTeacher = true,标注可去掉
在 verifiedByTeacher 为 false 期间:
· 检索时这条资源标灰,附一句「待验算,先别直接给学员」
· 不进入"推荐给学员"的候选为什么卡这一道:AI 生成的题看起来总是对的——格式规整、说法专业。真正的问题(条件矛盾、答案不唯一、超纲、数值算出无理数)要动笔算一遍才看得出来。这一道验算挡在库门口,比挡在学员面前便宜得多。
📎 五大类(讲义库/题库/讲评话术库/错因案例库/教案库)的用途、入库要求与入库示例,完整模板见
references/resource-entry-examples.md
对应 workspace.resourceLibraryIndex[] 的字段:
┌──────────────────┬──────────────────────────────┬──────────────┐
│ 字段 │ 取值 │ 用途 │
├──────────────────┼──────────────────────────────┼──────────────┤
│ subject │ 数学/语文/英语/物理/… │ 主分类 │
│ knowledgePoint │ 一次函数图象/定语从句/… │ 精确定位 │
│ gradeLevel │ 年级或学段 │ 适用筛选 │
│ difficulty │ 基础/中等/提升/挑战(四档枚举)│ 难度匹配 │
│ resourceType │ 题目/讲义/课件/板书/讲评话术/ │ 类型筛选 │
│ │ 错因案例/家长话术(七档枚举) │ │
│ copyrightStatus │ 自有/改编/公开可引用/仅存索引 │ 版权(必填) │
│ aiGenerated │ true / false │ 是否 AI 生成 │
│ verifiedByTeacher│ true / false │ 老师是否验算过│
│ usageNotes │ 自由文本(≤500 字) │ 用过几次、效果│
└──────────────────┴──────────────────────────────┴──────────────┘没有"学员类型"这个字段。按"基础学员/拔尖学员"给资源贴适用人群,等于把学员分了层再把资源分了层,用起来看着方便,实际会让老师照着标签发题而不是照着这个孩子当前卡在哪里发题。要匹配就按 knowledgePoint + difficulty 匹配。
■ 必填
· resourceId / title / resourceType / copyrightStatus(schema required)
· knowledgePoint + difficulty(不填就检索不到,等于没存)
■ 推荐
· subject / gradeLevel
· aiGenerated(AI 生成的必须为 true)
■ usageNotes 里写什么
· 用过几次、给什么情况的学员用过、效果如何
· 改编来源("改自 R-001,把出租车换成快递")
· AI 生成未验算时的【AI 生成,入库前请人工验算】标注输入:关键词(如"一次函数复习")
匹配:所有包含"一次函数"+"复习"的资源
排序:按相关度 / 使用频率 / 学员匹配度输入:学员化名 + 当前卡住的知识点
读:workspace.studentCards[].gradeBand / .primaryWeaknesses
workspace.homeworkFollowups[].mainErrors[].knowledgePoint / .dimension
匹配:knowledgePoint 相同 + difficulty 与当前掌握度相称 +
gradeLevel 在该学员学段内
输出(每条标明为什么推荐它):
· [资源标题]([类型],[难度])
推荐理由:针对 [知识点] 的 [dimension],上次给 [场景] 用过
⚠️ 待验算:aiGenerated=true 且 verifiedByTeacher=false 的标出来
不做的事:
❌ 按"这是基础学员"整批推荐一组资源
❌ 推荐超出该学员 gradeBand 的内容(要用就标 ⚠高中 并说明是拓展)输入:通用四维之一(概念模糊 / 计算失误 / 读题失误 / 方法用错,
见 shared/vocab.md §1)
匹配:resourceType=错因案例 且 knowledgePoint 或维度相符的条目
输出:
· 案例描述(已脱敏,不含任何可识别到具体学员的细节)
· 当时的应对动作
· 效果记录(写事实,不写"效果很好")第 1 步:检索资源
· 基于当前需求(学员画像/学情)检索
· 找到 1-3 个候选资源
第 2 步:评估匹配度
· 难度匹配?
· 知识点匹配?
· 学员类型匹配?
第 3 步:调整适配
· 修改参数(数字/情境)
· 调整难度
· 添加学员特定元素
第 4 步:使用并记录
· 标记"复用自 [资源 ID]"
· 记录使用效果
· 反馈到资源库■ 改数(参数)
原题 y=2x+1 → 改编 y=3x-2
适合:同一知识点不同参数
⚠️ 改完必须重算一遍:换个系数就可能算出无理数或负人数
■ 改问(设问角度)
原题"求 X" → 改编"判断 X 是否正确"
适合:换角度测同一概念
■ 改情境(背景)
原题"出租车" → 改编"网约车"
适合:让题目更贴近学生生活
⚠️ 换情境要检查量纲还合不合理(速度、单价、人数)
■ 改综合度
单知识点 → 多知识点综合
适合:检验综合应用
⚠️ 改成综合题后不再与原题同型,不能再当"同类题"用于弱项验证
改编后一律按 shared/ai-item-check.md 复核:自解一遍、有解且唯一、
条件充分不多余、数值友好、学段内。改编件的 copyrightStatus 记 `改编`,
usageNotes 里写清原出处与改动点。复用记录不单独建表,直接写进 workspace.resourceLibraryIndex[].usageNotes(≤500 字符)。一行一次,累积成这条资源的使用史:
usageNotes 写法(**只记资源本身的使用情况,不记学员**):
用过 2 次 | 效果:1 次需提示、1 次直接做对 | 下次配纯净版再试
→ 不写学员化名、日期、分数、个体弱项。个体层面的记录在 lessonLogs / homeworkFollowups 里已经有,
靠 resourceId 关联即可;把它们再抄一遍进 usageNotes,会在一条自由文本里累积成准可识别的学员画像
改自 R-001(把出租车情境换成快递),已重算
【AI 生成,入库前请人工验算】← 验算后删掉这一行
写事实,不写"效果很好""这题很经典"——
后者三个月后回头看,等于什么都没说。
超过 500 字符时保留最近几条,旧的合并成一句"此前用过 N 次"。四档取值来自 shared/vocab.md §11,本 SKILL 不另设分类。
✅ 自有
老师自己写的
完整存储
✅ 改编
基于某资源改编
必须在 usageNotes 标注"原出处 + 改了什么"
✅ 公开可引用
教材例题、明确开放授权(如 CC 协议)的资源
完整存储,标注来源
⚠️ 仅存索引
**教辅原题与历年真题一律归这一档**,没有例外
只记书名/卷名、页码、题号,不录入题干、不存扫描件
检索时给出"在哪本书第几页",老师自己去翻
❌ 禁止入库
未授权的教辅原题题干
盗版扫描件、拍照件
未授权转载的网络资源为什么真题也只存索引:历年真题的汇编本同样有版权,"大家都在用"不构成授权。存索引不影响使用——老师手上有那本书,需要时按页码翻到即可;存题干则是在自己的库里做了一份未授权复制件。
📎 完整模板见
references/copyright-annotation-template.md(四档 copyrightStatus 的版权信息填写模板)
■ 必脱敏
· 真实姓名 → 化名
· 学校名称 → "某公立/民办学校"
· 年级 → 模糊("初中学员")
· 家长身份 → 移除
· 家庭住址 → 移除
· 联系方式 → 移除
■ 可保留(用于案例分析)
· 学科
· 知识点
· 错因
· 应对动作
· 效果数据□ 学员姓名已替换为化名
□ 学校名称已模糊化
□ 年级已模糊化("初中学员"等)
□ 家长身份信息已移除
□ 家庭住址已移除
□ 联系方式已移除
□ 案例描述不含可识别细节
□ 案例分析基于错因/方法/效果而非具体人■ 必入库时机
· 学员试讲课讲义通过后
· 优秀作业讲评案例
· 重要错因突破案例
· 阶段性测评优秀试卷
· 复习规划方案
■ 选入库时机
· 课堂过渡话术
· 家长沟通案例
· 学员进步转折点每次使用资源后:
· 标记使用次数
· 记录使用效果
· 标记"使用频率高"或"待改进"
→ 资源库排序基于实际使用效果
→ 高频高质量资源进入"我的最爱"
→ 低频低质资源进入"待优化"或"归档"新入库 → 试用 → 优化 → 成熟 → 经典
↓
归档(如过时/淘汰) 老师说"这个存一下" ──→ ┌────────────────────┐ ──→ 检索结果(带推荐理由)
老师说"帮我找…" ──→ │ resource-library │ ──→ 改编后的资源
│ (本 SKILL) │
└─────────┬──────────┘
│ 只写这一处
resourceLibraryIndex[]本 SKILL 不需要任何 SKILL 先跑,也不向任何 SKILL 推送。老师需要资源时来找,找到了自己拿走用。
读:
workspace.studentCards[].alias / .gradeLevel / .gradeBand /
.subjects / .goals / .primaryWeaknesses
→ 匹配资源用(按知识点与难度,不按"学员类型")
workspace.homeworkFollowups[].mainErrors[].knowledgePoint / .dimension
→ 按当前错因找对应的题与讲评话术
workspace.lessonLogs[].completedContent / .nextLessonFocus
→ 找下节课要用的材料
写(唯一写入处):
workspace.resourceLibraryIndex[].resourceId
workspace.resourceLibraryIndex[].title
workspace.resourceLibraryIndex[].resourceType (七档枚举)
workspace.resourceLibraryIndex[].subject
workspace.resourceLibraryIndex[].gradeLevel
workspace.resourceLibraryIndex[].knowledgePoint
workspace.resourceLibraryIndex[].difficulty (四档枚举)
workspace.resourceLibraryIndex[].copyrightStatus(四档枚举,必填)
workspace.resourceLibraryIndex[].aiGenerated (AI 生成的必须 true)
workspace.resourceLibraryIndex[].verifiedByTeacher(老师验算后才 true)
workspace.resourceLibraryIndex[].usageNotes (用过几次、效果、改编来源)
派生视图(不落库):
· 匹配结果 ← resourceLibraryIndex[] 与 studentCards[] / mainErrors[] 实时比对
· 使用统计 ← 运行时聚合;要留痕就写进 usageNotes,不新增字段
不写:
· 题干原文(copyrightStatus=仅存索引 的资源只记出处)
· 任何学员可识别信息(案例一律脱敏)xiaozhi-teach-solo-dashboard 只读 resourceLibraryIndex[] 做展示。若装有教师通用包,备课、作业设计、命题类 SKILL 可以来检索本库;未安装时本库对独立教师日常照常可用。任何一方取走 verifiedByTeacher=false 的资源,都要带上【AI 生成,入库前请人工验算】的标注。
✅ 可存储:化名案例、自有内容、改编件、公开可引用资源
❌ 禁止:未授权教辅原题的题干、盗版扫描件、未授权转载
✅ 案例可保留:学科/知识点/错因维度/应对方法/效果事实
❌ 不保留:真实姓名/学校/家长信息/家庭住址/联系方式
✅ 检索基于:知识点、难度、类型、关键词
❌ 检索不支持:反查具体学员("这条案例是谁")| ✅ 应该做 | ❌ 不能做 |
|---|---|
| 入库即填 knowledgePoint + difficulty | 存了不打标签,等于没存 |
| 案例入库前逐条脱敏 | 真实学员案例直接入库 |
| 教辅/真题一律仅存索引 | 把题干抄进库里 |
| AI 生成的标 aiGenerated | 混进库里看不出是 AI 写的 |
| 老师验算后才 verifiedByTeacher | 未验算就发给学员 |
| 改编后重新验算一遍 | 改完数字直接用 |
| 用过之后写进 usageNotes | 用了不留痕,下次重新判断 |
| 按知识点 + 难度匹配 | 按"基础学员/拔尖学员"整批推 |
教学资源复用库(自成闭环,不需要前置 SKILL)
读 workspace.studentCards[] ← student-intake 写
读 workspace.homeworkFollowups[] ← homework-tracker 写
读 workspace.lessonLogs[] ← lesson-log 写
写 workspace.resourceLibraryIndex[] ← 本 SKILL 唯一写入方
其他 SKILL 需要资源时直接读 resourceLibraryIndex[],本 SKILL 不推送。
若装有教师通用包,备课/作业/命题类 SKILL 可来检索;未安装不影响使用。禁止行为:
copyrightStatusverifiedByTeacher=false 的 AI 生成题用于学员学员/家长要求删除该学员相关数据时,一并检查资源库里的错因案例,把涉及该学员的条目删除或进一步脱敏。
校验要求:案例类资源入库前须完成脱敏检查(§9.2);跨 SKILL 共享前须确认 consent.crossSkillSharing 为 true。真实姓名、联系方式、学校信息一律不写入(详见 SECURITY_BASELINE.md)。
references/resource-categorization.md — 资源分类、标签与检索references/resource-entry-examples.md — 五大类资源的用途、入库要求与示例references/copyright-annotation-template.md — 版权标注模板shared/vocab.md — 版权四档、错因四维(唯一来源)shared/ai-item-check.md — AI 出题自检协议💡 小智说: "独立教师的核心壁垒不是'我能教', 是'我教过 1000 个学员,每个都不一样,但我都记得'。 当你把这些经验和素材沉淀到资源库, 你的第 1001 个学员不用再走弯路。 教学资源库是独立教师的'第二大脑'—— 你不会累,不会忘,不会因为今天状态不好就教错。"
© 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 teacher/independent/xiaozhi-teach-resource-library of qizhitang/xiaozhi-skills.
Open the folder on GitHubat commit c65f2d4
Xiaozhi Teach Resource Library next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Xiaozhi Teach Resource Library this skillqizhitang/xiaozhi-skills | 105 | — | ~3.1k | Automated safety check: Pass | MIT | |
| DeepTutor CLIHKUDS/DeepTutor | 41k | — | ~2.8k | Automated safety check: Pass | Apache-2.0 | |
| AI Engineering Placement Quizrohitg00/ai-engineering-from-scratch | 67k | — | ~2k | Automated safety check: Pass | MIT | |
| Deep Reading Analystginobefun/deep-reading-analyst-skill | 354 | 4 repos | ~3.6k | Automated safety check: Pass | MIT | |
| OpenMAIC Setup and ExtensionTHU-MAIC/OpenMAIC | 40k | — | ~1.7k | Automated safety check: Notes | MIT | |
| Codebase to Coursezarazhangrui/codebase-to-course | 5.7k | — | ~4.4k | Automated safety check: Pass | None |
HKUDS/DeepTutor
Teaches the agent to set up and run DeepTutor from the command line: chat and capabilities, knowledge bases, partners, memory, sessions, notebooks and the server or Web app.
rohitg00/ai-engineering-from-scratch
Runs a 10-question quiz across five areas to place a learner in the AI Engineering from Scratch curriculum, so they skip what they already know.
ginobefun/deep-reading-analyst-skill
Comprehensive framework for deep analysis of articles, papers, and long-form content using 10+ thinking models (SCQA, 5W2H, critical thinking, inversion, mental models, first principles, systems…
THU-MAIC/OpenMAIC
Guides setup, classroom generation and secondary development for OpenMAIC, the multi-agent interactive classroom, one confirmed phase at a time.
zarazhangrui/codebase-to-course
Turns a codebase into an interactive single-page HTML course for non-technical learners, with scroll modules, animated diagrams, quizzes and plain-English code translations.
rohitg00/ai-engineering-from-scratch
Tutors a learner through one stage of a hands-on AI engineering project per session: lesson, prediction, code, grader run and reflection, with hints but never full solutions.
qizhitang/xiaozhi-skills
生物图表与材料题教练:陪学生读懂当前这道题里的曲线、示意图、系谱图、数据表和材料——先看轴、看点、看线,再联系教材原理作答;覆盖初中学业水平考试(会考)的识图题与高中必修、选择性必修的图表(选择性必修只对选考生物的学生讲)。
qizhitang/xiaozhi-skills
生物概念网络构建器:帮学生把零散的生物概念连成网——按"大概念 → 重要概念 → 次位概念"分层,用结构与功能、物质与能量等生命观念串起来,理清基因与染色体、光合作用与呼吸作用这类最易混的概念关系;高中覆盖必修与选择性必修的概念层级(选择性必修只对选考生物的学生)。
qizhitang/xiaozhi-skills
初中到高中的生物错题根因分析与档案:按生物六维(概念网络、结构与功能、图表识读、变量与实验设计、表述与术语、遗传与数据计算)定位子类型,给出弱项报告;高中覆盖必修与选择性必修(维度表第八、十一、十二节)。
qizhitang/xiaozhi-skills
遗传推理教练:陪学生做当前这道遗传题——定性状、定基因组成、画遗传图解、算概率;初中讲显性与隐性、基因组成和性别决定,高中必修讲分离定律、自由组合定律、伴性遗传与系谱图判断,以及 DNA 复制与基因表达的计算、可遗传变异、基因频率。
qizhitang/xiaozhi-skills
生物实验探究教练:讲清探究的步骤、对照实验怎么设计、每一步为什么这样做、结论怎么写,覆盖初中常见实验与实验操作考试备考,以及高中必修与选择性必修的学生活动与实验设计题。
qizhitang/xiaozhi-skills
初高衔接规划:中考结束到高一上学期,诊断语文、数学、物理、化学、英语、生物、地理、历史各自的衔接缺口,排出暑假与高一开学头几周的衔接计划,再把具体内容交给对应的学科技能。
Categories
把独立教师散在文件夹、微信收藏和笔记本里的讲义、题目、讲评话术、错因案例收进一个可检索的库. An agent skill from qizhitang/xiaozhi-skills. Xiaozhi Teach Resource Library is an agent skill from qizhitang/xiaozhi-skills.
Xiaozhi Teach Resource Library fits situations like: education work in your project.
Run `npx skills add qizhitang/xiaozhi-skills --skill xiaozhi-teach-resource-library -a claude-code`. Or copy the skill folder (teacher/independent/xiaozhi-teach-resource-library in qizhitang/xiaozhi-skills) into .claude/skills/xiaozhi-teach-resource-library in your project. Claude Code loads it when a task matches its description.
Run `npx skills add qizhitang/xiaozhi-skills --skill xiaozhi-teach-resource-library -a codex`. Or copy the skill folder (teacher/independent/xiaozhi-teach-resource-library in qizhitang/xiaozhi-skills) into .agents/skills/xiaozhi-teach-resource-library in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add qizhitang/xiaozhi-skills --skill xiaozhi-teach-resource-library -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/xiaozhi-teach-resource-library, .gemini/skills/xiaozhi-teach-resource-library, .github/skills/xiaozhi-teach-resource-library and .opencode/skills/xiaozhi-teach-resource-library in your project.
SKILL.md names no scripts, command-line tools or credentials: Xiaozhi Teach Resource Library is instructions for the agent only. Compatibility (from SKILL.md): WorkBuddy / SkillHub / OpenClaw / ClawHub.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Xiaozhi Teach Resource Library is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.1k tokens (SKILL.md is roughly 13k 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 3.9k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Xiaozhi Teach Resource Library: 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.