Semantic Line-Art SVG Diagrams
simbajigege/book2skills
Turns text, screenshots, or existing diagrams into minimal, accessible line-art SVGs for teaching material, with an optional Mermaid relationship spec.
把"全班同一份作业"变成分层、可批改、时长可控的任务卡. An agent skill from qizhitang/xiaozhi-skills.
$ npx skills add qizhitang/xiaozhi-skills --skill xiaozhi-teach-assignment-designer -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-teach-assignment-designer --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/general/xiaozhi-teach-assignment-designer .claude/skills/xiaozhi-teach-assignment-designer && 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-assignment-designer" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/teacher/general/xiaozhi-teach-assignment-designer into .claude/skills/xiaozhi-teach-assignment-designer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-teach-assignment-designer", 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/general/xiaozhi-teach-assignment-designerType 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-assignment-designer -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-teach-assignment-designer --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/general/xiaozhi-teach-assignment-designer .agents/skills/xiaozhi-teach-assignment-designer && 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-assignment-designer" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/teacher/general/xiaozhi-teach-assignment-designer into .agents/skills/xiaozhi-teach-assignment-designer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-teach-assignment-designer", 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-assignment-designer -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-teach-assignment-designer --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/general/xiaozhi-teach-assignment-designer .cursor/skills/xiaozhi-teach-assignment-designer && 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-assignment-designer" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/teacher/general/xiaozhi-teach-assignment-designer into .cursor/skills/xiaozhi-teach-assignment-designer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-teach-assignment-designer", 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/general/xiaozhi-teach-assignment-designer--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-assignment-designer -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-teach-assignment-designer --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/general/xiaozhi-teach-assignment-designer .gemini/skills/xiaozhi-teach-assignment-designer && 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-assignment-designer" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/teacher/general/xiaozhi-teach-assignment-designer into .gemini/skills/xiaozhi-teach-assignment-designer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-teach-assignment-designer", 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-assignment-designerInstalls 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-assignment-designer -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/general/xiaozhi-teach-assignment-designer .github/skills/xiaozhi-teach-assignment-designer && 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-assignment-designer" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/teacher/general/xiaozhi-teach-assignment-designer into .github/skills/xiaozhi-teach-assignment-designer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-teach-assignment-designer", 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-assignment-designer -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-assignment-designer --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/general/xiaozhi-teach-assignment-designer .opencode/skills/xiaozhi-teach-assignment-designer && 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-assignment-designer" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/teacher/general/xiaozhi-teach-assignment-designer into .opencode/skills/xiaozhi-teach-assignment-designer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-teach-assignment-designer", 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-assignment-designer把"全班同一份作业"变成分层、可批改、时长可控的任务卡. An agent skill from qizhitang/xiaozhi-skills.
Xiaozhi Teach Assignment Designer is an agent skill from qizhitang/xiaozhi-skills. 把"全班同一份作业"变成分层、可批改、时长可控的任务卡。 当老师说"帮我设计一份一次函数的作业"、"出一份分层练习"、"这份作业怎么批改、给什么反馈"、"出一份带评分细则的作业"、"本章学完了帮我设计复习作业"、"高二物理合格考班的分层作业怎么出"时,建议激活此 SKILL。 工作流:知识点拆解 → 难度梯度 → A/B/C 任务卡(每题标预计用时)→ 评分标准 → 反馈模板 → 完成情况回写。 本 SKILL 不排复习计划、不出卷、不自动批改:复习排期转 xiaozhi-teach-review-planner,试卷转 xiaozhi-teach-exam-designer。高中有学科技能的作业(如化学用语过关卡、作文批改标准)先转学科技能,见正文 5.3。
Its SKILL.md is about 5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 12 other files, including reference files (for example `references/assignment-rubric.md`, `shared/ai-item-check.md` and `shared/class-teaching-workspace.schema.json`). 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 Assignment Designer loads about 5k tokens when it runs, and up to ~8.1k if it reads all its reference files. Until then it costs about 92 tokens; SKILL.md has 458 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). 458 words, ~4,962 tokens.
.claude/skills/xiaozhi-teach-assignment-designer/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: 作业不是量的堆叠,而是精准诊断每个学生思维位置的探针。
技术边界:本 SKILL 依赖能力 [M, F],无该能力时按
shared/platform-conventions.md降级。 特有降级:无F(表格导出)时,任务卡以文本给出,老师自行排版打印。
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)》)。
内容边界:道德与法治、思想政治只排任务卡与评分标准的格式,不出题目与参考答案,题目与评分要点由老师按统编教材自拟(老师给出教材原文时,可以把原文改排成填空题,挖空处就是原文的词句,不改原文表述,不生成选项、干扰项与观点性内容);涉及方针政策、政治制度、意识形态、国家主权与领土、民族与宗教的表述,照录老师提供的课标与统编教材;时政材料由老师从权威来源选取并注明来源与日期;学生作业里的政治表述不写进完成情况汇总,也不点评。历史题涉及版图领土、民族、宗教、中国共产党历史与新中国史的评价性表述,以及战争性质、人物评价,照录课标原句,课标没有原句的以统编教材为准(原句由老师提供;材料题与开放性试题的评分标准转历史命题与答题规范指导),材料只用课标、教材与注明出处的经典文献,不编造史料与人物言论,不引入课标与教材以外的评价、有争议的说法与当代政治、国际时事;地理作业的地图用教材地图或标准地图,不绘制、不改动国界与行政区划,涉及国家版图、领土与海洋权益的表述照录课标原句与教材(由老师提供),不另加评论(SECURITY_BASELINE.md 4.4)。
⚠️ 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。
分层从哪来:A/B/C 读 classWorkspace.studentTiers(xiaozhi-teach-student-analyzer 依据近 3 次测评平均得分率写入)。
拿不到时输出"基础版作业"(单一梯度),标题注明"无学情",不硬编分层。
不自动批改:本 SKILL 输出评分标准,不判分。判分需要专用判题引擎,不在本 SKILL 能力范围, 也不要把学生端的解题教练当判题引擎——它的设计目标是陪一个学生想明白一道题,不是给一叠作业打分。
生成题目时:AI 生成的题(含变式题、同类题)在给老师之前按 shared/ai-item-check.md 自检,
输出时标注【AI 生成,入库前请人工验算】;未经老师验算不得进入正式作业。
作业量:默认"少而精",每题都填 estimatedMinutes,整份作业给出 estimatedTotalMinutes。
如老师要求加量,先确认是否挤占睡眠、运动与其他科目作业时间。高中的作业量另见 5.3(不套用初中的分钟数)。
启用前的统考试题不得输入本 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。 高中的学业水平合格性考试、等级性考试与高考,地(市)统一组织的模拟考试(如一模、二模),以及实验操作考试、外语听说考试的试题,全部批次、全部场次考完之前都按启用前处理(这两类考试常分几天、分批进行,本班考完不等于考完),不改编成作业;跨校联考要等参加的学校全部考完。已经启用过的历年真题只记出处(版权状态"仅存索引"),不把整卷原题写进作业记录。 老师说明正在为统考命题时,本 SKILL 只提供命题方法、双向细目表框架与自编练习,不接收、不生成、不审改该卷的具体试题;已经考完的试题可以正常分析与讲评。同一份卷子还有学生补考的,补考考完才算考完;考后不公开试卷的考试(如用题库命题、机考的),考完也不据学生回忆还原原题、改编成作业,同类练习按本地公布的样题自编。 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”。
面向家长的作业反馈(§8.2)在生成前先检查学生端
parentSharingConsent;含情绪内容再检查emotionSharingWithParent。
老师布置作业时常见的三个误区:
误区① 一刀切:全班做同一份作业,
基础学生"完不成/抄作业",拔尖学生"早做完没事干"。
误区② 数量代替质量:以为"多刷几道就能提分",
实际重复练习的低效知识点已经掌握。
误区③ 缺反馈标准:作业收上来不知道"对到哪一步算对",
批改时只画对错,学生不知道自己错在哪一步。本 SKILL 要解决的是:
| 触发场景 | 示例语句 |
|---|---|
| 设计新作业 | "帮我设计一份 X 知识点的作业" |
| 分层布置 | "同一个班的作业怎么分层,让学生自己选" |
| 改写现有作业 | "这是原作业,帮我重做成 A/B/C 分层" |
| 复习作业 | "本章学完了,帮我设计复习作业" |
| 作业批改 | "这份作业怎么批改、给什么反馈" |
| 评分标准 | "出一份带评分细则的作业" |
| 阶段性作业包 | "帮我整理本月作业包" |
| 反馈模板 | "作业反馈怎么写" |
| 高中作业 | "高二物理合格考班的分层作业怎么出" / "高三每天加一套卷行不行"(作业量与考查范围见 5.3) |
触发语分工(与 xiaozhi-teach-review-planner 的边界):
| 老师说 | 归谁 |
|---|---|
| "本章学完了,帮我设计复习作业""出一份复习练习""考前冲刺练什么题" | 本 SKILL(具体题目、分层任务卡、评分标准、预计时长) |
| "帮我排期末复习计划""考前两周怎么安排""这几个知识点老混怎么排练习" | xiaozhi-teach-review-planner(时间排期、间隔回看、交叉组合) |
| "帮我出一份卷子" | xiaozhi-teach-exam-designer |
| "出一份课堂上做的单元练习卷""出期中卷" | xiaozhi-teach-exam-designer(课堂上做的单元练习与试卷;课后的作业归本 SKILL) |
| "这节课怎么上" | xiaozhi-teach-lesson-planner |
| 高中有学科技能的作业(化学用语过关卡、作文任务与批改标准、文言文背诵任务等) | 该学科的老师端技能,转交表见 5.3 |
一句话:"作业"归本 SKILL,"计划"归 review-planner。 老师说"复习作业"时,先看
classWorkspace.reviewPlans有没有排期;有就按排期配题,没有就直接按弱项配题。
┌──────────────────────────┐
│ ① 输入确认 │
│ 知识点 / 课时 / 学情摘要 │
└────────────┬─────────────┘
↓
┌──────────────────────────┐
│ ② 知识点拆解 │
│ 概念/规则/应用/迁移四层 │
└────────────┬─────────────┘
↓
┌──────────────────────────┐
│ ③ 难度梯度设计 │
│ 基础/中等/较难 三档 │
└────────────┬─────────────┘
↓
┌──────────────────────────┐
│ ④ A/B/C 分层任务卡 │
│ 基础/提升/拓展 三层 │
└────────────┬─────────────┘
↓
┌──────────────────────────┐
│ ⑤ 评分标准与批改指南 │
│ 过程分 + 结果分 │
└────────────┬─────────────┘
↓
┌──────────────────────────┐
│ ⑥ 反馈模板与提交标准 │
│ 简明反馈 / 满分模板 │
└────────────┬─────────────┘
↓
┌──────────────────────────┐
│ ⑦ 写回 student-analyzer │
│ 作为下次诊断的数据源 │
└──────────────────────────┘每道作业题必须对应一个明确的知识点层级,避免"模糊综合题"。
┌─────────────────────────────────────────────────────┐
│ 知识点四层结构(针对单一知识点) │
├─────────────────────────────────────────────────────┤
│ ① 概念层 │
│ · 学生能否准确复述定义/定理/规则 │
│ · 对应题型:填空、判断、简答 │
│ · 验证:能用一句话准确说出 │
├─────────────────────────────────────────────────────┤
│ ② 规则层 │
│ · 学生能否在标准情境下正确使用规则 │
│ · 对应题型:直接套用型计算、规则应用 │
│ · 验证:看到题目能说出"用 X 规则" │
├─────────────────────────────────────────────────────┤
│ ③ 应用层 │
│ · 学生能否在新情境中选择合适方法 │
│ · 对应题型:综合应用、变式题 │
│ · 验证:能说出"为什么用这个方法" │
├─────────────────────────────────────────────────────┤
│ ④ 迁移层 │
│ · 学生能否把方法迁移到跨章节/跨学科情境 │
│ · 对应题型:跨章综合、开放探究 │
│ · 验证:能解释"这个方法和 XX 是一回事" │
└─────────────────────────────────────────────────────┘每份作业至少覆盖①②③三层,④层仅在有学情支持时加入。
difficultyBand 一致)难度档全库统一为三档:基础 / 中等 / 较难(对应 homeworkAssignments[].tasks[].difficultyBand,
与 xiaozhi-teach-exam-designer 的试卷难度档同一套口径)。
"跨章迁移/开放探究"是知识点层级④(§四的另一根轴),落到难度档上仍归"较难"。
┌──────┬──────────────────────────────┬──────────────┬──────────────┐
│ 档位 │ 描述 │ 预计用时 │ 知识点层级 │
├──────┼──────────────────────────────┼──────────────┼──────────────┤
│ 基础 │ 直接套用概念或规则 │ 3-5 分钟/题 │ ①② │
│ 中等 │ 一步变形,或两个知识点组合 │ 5-8 分钟/题 │ ②③ │
│ 较难 │ 多步推理、综合、跨章迁移、开放探究│ 8-15 分钟/题 │ ③④ │
└──────┴──────────────────────────────┴──────────────┴──────────────┘
预计用时就是每题的 estimatedMinutes;一份作业的 estimatedTotalMinutes = 各题之和。
上表的每题用时是经验值(约数);高中按学科与题型另估,见 5.3。本科这份作业放进全科总量里定(shared/grade-bands.md 第五节:小学一、二年级不布置家庭书面作业;
小学三至六年级每天书面作业全科平均不超过 60 分钟;初中平均不超过 90 分钟;高中见 5.3)。
先问年级给本科的份额;问不到时按"全科总量 ÷ 当天有书面作业的科数"估,并在输出里写明是估的。
单课时作业(45 分钟课时):
基础 3-4 道 + 中等 2 道 + 较难 1 道 = 6-7 道(按本科份额删减)
预计总耗时:不超过本科当天的份额
单元复习作业(5-8 课时单元):
基础 6-8 道 + 中等 4-5 道 + 较难 3-4 道 = 13-17 道,分几天做
每天不超过本科当天的份额
考前冲刺作业(考前 3-7 天):
全部为已做过的错题 + 1-2 道变式,不引入新题型
不加量:把新题换成错题重做,每天不超过本科当天的份额若老师要求"加量",必须先确认:
1. 学生的可用复习时间是否充足
2. 是否会挤占睡眠/运动/休息
3. 是否会与错题复习时间冲突
4. 是否能保证每题都被批改反馈
不主动推荐"刷题"型作业;优先推荐"少而精+分层+错题"组合。高中的作业先问清四件事,再进第三节的流程:
① 为哪场考试服务
· 学业水平合格性考试(合格考)、学业水平等级性考试(等级考,各地也叫选考),
还是高考的语文、数学、外语;也可能只是校内的单元、期中、期末
② 本地当年的考试说明
· 本 SKILL 不内置任何省份的考试政策;老师没提供的地方,
作业说明上标"待老师按本地考试说明确认",不猜
③ 这个教学班考哪一种
· 合格考班、等级考班,还是两类学生在同一个班——班级工作区没有选科这一项,
由老师说明,要人数不要名单,不从成绩或其他字段推断
④ 新课教到哪
· 读 lessonPlans 看教到哪一章;作业不超出已教的进度作业量:双减对书面作业时长的规定只管义务教育;高中没有全国统一的书面作业分钟数,本 SKILL 不内置,也不写死本科的分钟数。
shared/grade-bands.md 第一节:高中建议就寝不晚于 23:00,免打扰 22:30-6:30;提交截止不设在免打扰窗口里。考查范围:
shared/ai-item-check.md 的"学段内",高中细化为"不超出本班的考试范围与已学进度";知识点④迁移层,合格考班只在必修内迁移。shared/hs-subject-standards.md 第十一节),可以作拓展,不计分。学业质量与难度是两根轴:难度档仍是基础、中等、较难(difficultyBand);学业质量水平用该科课标的原名写在作业说明里,各学科分级不同,见 shared/hs-subject-standards.md 第一节,不跨学科换算,也不写进班级工作区。"较难"不等于某一级水平。
高中课标对作业的要求:化学课标要求先做单元作业的整体规划、再做课时作业,单元规划里有贯穿单元的实践类作业;生物学课标要求既有纸笔作业,也有实践性作业;数学课标也写到作业;物理课标的作业要求写在教材编写建议里;英语课标把作业写在评价里(作业评价)。原话见 shared/hs-subject-standards.md 各学科一节的第五条(化学第六节、生物学第七节)。老师要单元作业规划时,先列出各课时作业与贯穿单元的实践类作业,再逐课时出任务卡;§5.1 的单元复习作业与 references/assignment-rubric.md 第四节的复习作业包都不等于单元作业规划。
实践性作业(调查、观察、制作、实验报告、小课题):
选科与走班:classId 用教学班;分层读这个教学班自己的 studentTiers,开学初没有本班测评时只出基础版。学校"分层走班"的层名与本 SKILL 的 A/B/C 不是一回事,任务卡照旧印"任务卡一/二/三"。不以选科公开分组,不出名单;本 SKILL 的输出不作学分认定或综合素质评价的依据。
家长版反馈(§8.2):高中另外不写赋分与等级预测、年级或联考的位次与百分位、选科或换科建议、"合格考会不会过"的预测;授权位照旧逐次查,高中由学生本人决定,高三有已成年的学生,以学生本人的同意为准。
高三:
高中转学科技能(表外的学科与题型本库暂无专门技能,本 SKILL 出通用的任务卡与评分标准):
| 老师要的 | 转给 |
|---|---|
| 化学用语的分级过关卡 | 化学用语过关训练设计(xiaozhi-teach-chemistry-notation-drill) |
| 作文任务、二稿修改与作文批改标准 | 写作教学指导(xiaozhi-teach-chinese-writing-guide) |
| 文言文背诵与翻译任务 | 文言文教学指导(xiaozhi-teach-chinese-classical-guide) |
| 预习与拓展阅读任务 | 阅读教学指导(xiaozhi-teach-chinese-reading-guide) |
| 历史材料题、开放性试题的评分标准 | 历史命题与答题规范指导(xiaozhi-teach-history-assessment-guide) |
| 物理、化学实验后的数据处理与实验报告 | 物理实验教学指导(xiaozhi-teach-physics-experiment-coach);化学实验教学指导(xiaozhi-teach-chemistry-lab-guide) |
| 生物学的实验与户外取样,地理的野外考察与社会调查 | 生物教案设计(xiaozhi-teach-biology-lesson-planner);地理教案设计(xiaozhi-teach-geography-lesson-planner) |
| 某类物理题的讲法与变式梯度 | 物理解题教学指导(xiaozhi-teach-physics-problem-guide);成套的分层作业仍归本 SKILL |
| 英语听力、口语的练习材料与任务;听说读写的测评卷 | 英语听力材料设计(xiaozhi-teach-english-listening-designer);英语口语活动设计(xiaozhi-teach-english-speaking-designer);英语综合测评(xiaozhi-teach-english-assessment) |
| 数学的单元测评与整卷;作业与试卷的错因统计 | 数学测评设计(xiaozhi-teach-math-exam-designer);班级错因分析(xiaozhi-teach-math-error-analyzer) |
| 复习排期 | 复习规划师(xiaozhi-teach-review-planner);生物、地理的合格考复习转生地学业水平考试复习规划(xiaozhi-teach-bio-geo-review-planner)。两者只排期,具体题目回到本 SKILL |
没有学科技能的五科:思想政治、信息技术、通用技术、艺术、体育与健康本库没有学科技能,本 SKILL 照接,只出分层任务卡、评分标准与反馈的框架,课标原文与教材内容由老师提供;各科的边界见 shared/hs-subject-standards.md 第十节。本 SKILL 另守一条:思想政治(小学、初中的道德与法治同此)不出题目与参考答案(教材原文改排成填空题的例外见本 SKILL 开头的内容边界),题目与评分要点由老师按统编教材自拟,本 SKILL 只排任务卡与评分标准的格式;学生作业里的政治表述不写进 completionSummary。
当 classWorkspace.studentTiers 有数据时输出三套任务卡;没有时只出基础版并注明"无学情"。
A 层 · 需补基础(近 3 次平均得分率 < 0.60):以"搭梯子"为主
· 基础 + 少量中等题
· 留 30% 弹性时间
· 教师批改时重点关注过程
B 层 · 达标(0.60-0.85):以"拉满目标"为主
· 基础 + 中等 + 1 道较难
· 标准时间
· 教师批改时关注错误类型
C 层 · 可拓展(≥ 0.85):以"跨章迁移"为主
· 中等 + 较难(含 1 道跨章或开放题)
· 标准时间,明确截止
· 教师批改时关注思维深度
⚠️ 三层的 estimatedTotalMinutes 应大致相当:分层是换难度,不是给某一层加量。
⚠️ 任务卡上印"任务卡一/二/三",不印层名——层是给老师排任务用的,不是给学生贴的标签。【任务卡一】《一次函数的图象与性质》 (发给 A 层)
1. 课本例题 1(基础,直接套用规则) 预计 4 分钟
2. 课本练习 1(基础,套用规则) 预计 5 分钟
3. 课本练习 2(中等,一步变形) 预计 7 分钟
4. 看图填空:k>0 / k<0 时图象走向(基础) 预计 6 分钟
⏱ estimatedTotalMinutes 22,弹性 +8 分钟
📌 重点:把每一步"为什么"写清楚
【任务卡二】《一次函数的图象与性质》 (发给 B 层)
1. 课本例题 1(基础) 预计 4 分钟
2. 变式题:把 k 改为负数(中等) 预计 6 分钟
3. 课本练习 4:用图象解应用题(中等) 预计 8 分钟
4. 综合题:一次函数与正比例函数对比(较难)预计 10 分钟
⏱ estimatedTotalMinutes 28
📌 重点:写出思路,不只写答案
【任务卡三】《一次函数的图象与性质》 (发给 C 层)
1. 变式题:把 k 改为负数(中等) 预计 6 分钟
2. 课本练习 4:用图象解应用题(中等) 预计 8 分钟
3. 跨章综合:用一次函数描述匀速直线运动 s=vt(较难)预计 8 分钟
4. 开放题:设计一个能列出一次函数的生活情境(较难)预计 8 分钟
⏱ estimatedTotalMinutes 30,明确截止
📌 重点:跨章联结的论证
(三张卡的总时长 22 / 28 / 30 分钟,差距控制在 10 分钟以内)每道题必须配可操作的评分标准;批改时按"过程分 + 结果分"双轨打分。
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
📋 评分标准 · [题目]
满分:[ ] 分
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
■ 过程分([N] 分)
· 步骤 1([M] 分):[具体内容]
· 步骤 2([M] 分):[具体内容]
· 步骤 3([M] 分):[具体内容]
· 关键概念/规则([M] 分):[具体内容]
■ 结果分([N] 分)
· 答案正确([M] 分)
· 单位/格式([M] 分)
■ 常见错误与扣分
· 错误 ①:[描述] → 扣 [M] 分
· 错误 ②:[描述] → 扣 [M] 分
■ 满分模板(参考作答)
[步骤化满分作答]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━✓ 完全正确
▲ 思路对但计算/书写错
? 思路不清/不完整
✗ 思路错误
?✓ 部分对,看具体情况
# 超纲或解法独特(需教师判断)shared/vocab.md §1 / §3)批改时先判通用四维(shared/vocab.md §1,写入数据用这一层),
需要跟老师、跟学生说得更细时再用老师端七类(§3),两者的映射是固定的:
| 老师端七类(§3) | 通用四维(§1) | 简明反馈(≤ 30 字/题) |
|---|---|---|
| 知识漏洞 | 概念模糊 | "概念 X 的定义是 Y,请重读课本第 N 页" |
| 规则错误 | 概念模糊 | "Y 规则的关键步骤是 Z,你跳过了哪一步" |
| 审题错误 | 读题失误 | "看清题目问的是 A 不是 B" |
| 策略错误 | 方法用错 | "这类题用 X 方法更快,先看条件里有没有 [标志]" |
| 表达/书写不规范 | 方法用错 | "结论对,但第 2 步没写出来,过程分拿不到" |
| 计算错误 | 计算失误 | "思路对,第 3 步的运算再算一遍" |
| 习惯性失误 | 计算失误 | "抄错了原题的数字,做之前先把条件圈一遍" |
判定顺序(shared/vocab.md §1):
先 R(让学生复述条件)→ 再 C(给纯净版最简题)→ 再 M(换题型)→ 剩下的归 K
三条规则:
· 一道错题只记一个主维度,不要同时记两类
· 不写"粗心"作为原因——粗心是结果,要落到"抄错数字(读题失误)"
或"运算出错(计算失误)"这样能采取行动的描述
· "移项不变号"归规则错误(概念模糊),不归计算;"看错数字"归审题(读题失误)
写入:homeworkAssignments[].completionSummary.commonErrors[]
每条含 knowledgePoint、dimension(四维)、teacherCategory(七类,可选)、count✅ 你做对了:
· [题号/知识点]
⚠️ 你卡在了:
· [题号] → 错因:[一句话] → 建议:[一句话]
🎯 下次重点:
· [1-2 个具体改进点]生成前先检查 parentSharingConsent;含情绪内容再检查 emotionSharingWithParent。任一为 false 时只给老师与学生本人。
[学生化名/座号] 本次作业完成情况:[N] 道完成 [N] 道待订正
主要错因:[按通用四维聚合,如"计算失误 2 道 / 概念模糊 1 道"]
建议家长配合:
· 关注孩子 [具体行为] 时段
· 与孩子约定 [1 个具体动作]
· 不必:[焦虑式话术]
❌ 不写班级排名、名次段、与其他同学的对比作业收上来批完后,把聚合结果写进本次作业条目自己的 completionSummary,
xiaozhi-teach-student-analyzer 读它作为辅助证据:
homeworkAssignments[].completionSummary
· submitted 已提交份数
· total 应交份数
· commonErrors[] 共性错因(knowledgePoint + dimension + teacherCategory + count)
⚠️ 不写"学生分层变化"和"顽固弱项状态":
分层写在 studentTiers、顽固计数写在 weaknessRank,都由 student-analyzer 唯一维护。
作业数据是这两者的**输入证据**之一,不是它们的第二个来源。
上一版这里写的 assignmentResults[] 在 schema 中不存在,已删除。 ┌────────────────────────┐
│ xiaozhi-teach- │
│ lesson-planner │
│ (教案侧重点) │
└───────────┬────────────┘
│
↓
┌────────────────────────┐
│ xiaozhi-teach- │
│ assignment-designer │
│ (本 SKILL) │
└───────────┬────────────┘
│
↓ 作业数据回写
┌────────────────────────┐
│ xiaozhi-teach- │
│ student-analyzer │
│ (学情反哺) │
└───────────┬────────────┘
│
┌───────────┴───────────┐
↓ ↓
classroom-coach exam-designer
(课堂讲评) (测评检验)shared/class-teaching-workspace.schema.json)| classWorkspace 字段 | 谁写 | 本 SKILL |
|---|---|---|
classProfile | 老师首次建档 | 读(gradeBand 定作息约束,按 shared/grade-bands.md 第一节;全科作业总量由老师按学校统筹与规定协调;classProfile.subject、classProfile.gradeLevel 定学科与年级,高中据此按 5.3 判断转不转学科技能) |
lessonPlans | xiaozhi-teach-lesson-planner 或学科老师端技能 | 读 topic、objectives、sourceWeaknessIds(作业侧重点)、segments 的 tierVariants(课堂分层,作业与之衔接) |
weaknessRank | xiaozhi-teach-student-analyzer 或学科老师端技能 | 读(作业针对哪些弱项、什么错因维度) |
studentTiers | xiaozhi-teach-student-analyzer | 读(A/B/C 各多少人 → 印几份任务卡) |
examBlueprints | xiaozhi-teach-exam-designer 或学科老师端技能 | 读(认知层级与难度档口径对齐,避免作业和测评两套标准) |
reviewPlans | xiaozhi-teach-review-planner 主写 + 学科技能(english-assessment、english-listening-designer、bio-geo-review-planner)只补本学科条目 | 读 spacingSchedule(哪天该回看哪个知识点)、interleavingSets(哪几个混着练) |
homeworkAssignments | 本 SKILL 主写;学科老师端技能也写本学科的条目,读时不覆盖别人的条目 | 写 assignmentId、planId、date、purpose(诊断/巩固/补救/拓展)、tasks[](taskNo、knowledgePoint、cognitiveLevel、difficultyBand、tier、estimatedMinutes)、estimatedTotalMinutes、completionSummary |
两条硬规则:
· 每道题必须填 estimatedMinutes,整份必须填 estimatedTotalMinutes。
没有时长的作业设计是不可控的——老师看不出这份作业到底要多久,
也就无法与其他科目协调总量。
· 分层(studentTiers)与顽固计数(weaknessRank)都不由本 SKILL 写;
作业数据通过 completionSummary 作为证据流向 student-analyzer。- 拿不到 studentTiers 时输出"基础版",标题注明"无学情",不硬编 A/B/C
- 不主动推高题量:默认"少而精",每题标时长
- 不替老师承诺提分:作业只服务"诊断 + 补救"
- 不自动批改:仅输出评分标准
- 不替老师给学生写评语:只生成反馈模板
- 不排复习计划:间隔与交叉的日期归 review-planner,本 SKILL 按它的排期配题✅ 允许:化名、学号、座位号
❌ 禁止:真实姓名、家庭住址、家长身份
✅ 允许:聚合错因("全班 35% 学生 X 知识错")
❌ 禁止:单独学生分数对比✅ 写:X 知识点 11 人失分,错因集中在"方法用错"
❌ 不写:小明 X 知识点 35 分
✅ 写:submitted 39 / total 42
❌ 不写:未交名单| ✅ 应该做 | ❌ 不能做 |
|---|---|
| 每题都配可观测的评分标准 | 只画对错不给分 |
| 分层作业基于学情而非猜测 | 全班同一份作业 |
| 优先"少而精"再考虑"多练" | 堆题量 |
| 反馈用具体行为描述 | 用"你真棒""继续努力"等空话 |
| 写回学生数据前做脱敏 | 在反馈中暴露真实姓名 |
| 错题归档进入错题本机制 | 批改完就归档不回顾 |
作业设计师
<── xiaozhi-teach-lesson-planner(lessonPlans:教案侧重点与课堂分层)
<── xiaozhi-teach-student-analyzer(weaknessRank / studentTiers)
<── xiaozhi-teach-review-planner(reviewPlans:回看日与交叉组合 → 按排期配题)
<── xiaozhi-teach-exam-designer(examBlueprints:认知层级与难度档口径对齐)
──→ xiaozhi-teach-student-analyzer(homeworkAssignments 的 completionSummary 作辅助证据)
──→ xiaozhi-teach-math-error-analyzer(数学:homeworkAssignments 的 completionSummary 里的共性错因 → 七类错因分析)
──→ xiaozhi-teach-classroom-coach(高频错题 → 讲评素材)
──→ 学生端错题本 SKILL(学生个人错题归档)
·· 独立教师场景不布置家庭作业(校外培训不留作业):作业跟进管家(xiaozhi-teach-homework-tracker)
只跟进独立教师的课上练习与学员带来的学校作业、考试错题,不接本 SKILL 的作业数据禁止行为:
references/assignment-rubric.md — 作业评分标准模板💡 小智说: "作业不是惩罚,是探测器。 每一道题都在告诉你: 这个学生,在哪一步是真的会了, 在哪一步只是假装会了。 好的作业设计,是让探测器带回来的信号清晰, 而不是把探测器堆满他的书包。"
© 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 teacher/general/xiaozhi-teach-assignment-designer of qizhitang/xiaozhi-skills.
Open the folder on GitHubat commit c65f2d4
Xiaozhi Teach Assignment Designer 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 Assignment Designer this skillqizhitang/xiaozhi-skills | 105 | — | ~5k | Automated safety check: Pass | MIT | |
| Semantic Line-Art SVG Diagramssimbajigege/book2skills | 183 | — | ~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 |
simbajigege/book2skills
Turns text, screenshots, or existing diagrams into minimal, accessible line-art SVGs for teaching material, with an optional Mermaid relationship spec.
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.
adithya-s-k/manim_skill
Plans educational Manim videos before any code: researches the topic, asks about audience and scope, and writes a scene-by-scene scenes.md in 3Blue1Brown style.
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"全班同一份作业"变成分层、可批改、时长可控的任务卡. An agent skill from qizhitang/xiaozhi-skills. Xiaozhi Teach Assignment Designer is an agent skill from qizhitang/xiaozhi-skills.
Xiaozhi Teach Assignment Designer fits situations like: education work in your project.
Run `npx skills add qizhitang/xiaozhi-skills --skill xiaozhi-teach-assignment-designer -a claude-code`. Or copy the skill folder (teacher/general/xiaozhi-teach-assignment-designer in qizhitang/xiaozhi-skills) into .claude/skills/xiaozhi-teach-assignment-designer in your project. Claude Code loads it when a task matches its description.
Run `npx skills add qizhitang/xiaozhi-skills --skill xiaozhi-teach-assignment-designer -a codex`. Or copy the skill folder (teacher/general/xiaozhi-teach-assignment-designer in qizhitang/xiaozhi-skills) into .agents/skills/xiaozhi-teach-assignment-designer 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-assignment-designer -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-assignment-designer, .gemini/skills/xiaozhi-teach-assignment-designer, .github/skills/xiaozhi-teach-assignment-designer and .opencode/skills/xiaozhi-teach-assignment-designer in your project.
SKILL.md names no scripts, command-line tools or credentials: Xiaozhi Teach Assignment Designer 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 Assignment Designer is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 5k tokens (SKILL.md is roughly 20k 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 3.1k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Xiaozhi Teach Assignment Designer: Semantic Line-Art SVG Diagrams (simbajigege/book2skills, 183 stars), DeepTutor CLI (HKUDS/DeepTutor, 41k stars), AI Engineering Placement Quiz (rohitg00/ai-engineering-from-scratch, 67k stars) and Deep Reading Analyst (ginobefun/deep-reading-analyst-skill, 354 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.