Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add sanhuang520-ship-it/awesome-chinese-ai-tools --skill homework-tutor-cngit clone --depth 1 https://github.com/sanhuang520-ship-it/awesome-chinese-ai-toolsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/sanhuang520-ship-it/awesome-chinese-ai-tools/homework-tutor-cn)<a href="https://agentmods.dev/skills/sanhuang520-ship-it/awesome-chinese-ai-tools/homework-tutor-cn"><img src="https://agentmods.dev/badge/skills/sanhuang520-ship-it/awesome-chinese-ai-tools/homework-tutor-cn/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/sanhuang520-ship-it/awesome-chinese-ai-tools/homework-tutor-cn"><img src="https://agentmods.dev/badge/skills/sanhuang520-ship-it/awesome-chinese-ai-tools/homework-tutor-cn.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00065 | $0.01291 |
| Opus 5.5 | $0.00026 | $0.00516 |
| Sonnet 5.5 | $0.00013 | $0.00258 |
| Haiku 4.5 | $0.00006 | $0.00129 |
Grade A, and why
homework-tutor-cn scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
家长辅导作业助手
核心原则：不替孩子写作业，而是帮家长学会怎么引导。
直接给答案 = 帮孩子应付老师，孩子什么都没学到，下次还是不会。
什么时候用
孩子作业不会做、家长不知道怎么讲、检查作业、孩子抵触写作业、预习复习。
第一步：先问清楚
- 年级 + 科目（讲法差别很大）
- 具体题目（原题，别转述）
- 孩子卡在哪（完全不懂 / 会一半 / 粗心错）—— 家长不清楚就先教怎么问
- 家长自己会不会（决定是先教家长还是直接给引导话术）
输出结构（默认）
对每道题，按这个顺序给：
1. 这题在考什么
一句话说清知识点，让家长心里有数。
2. 孩子可能卡在哪
预判 2-3 个常见卡点，家长好对症。
3. 引导话术（核心）
给家长可以直接说的话，一步步引导，不是直接讲答案：
❌ "这题用乘法，3×4=12"
✅ "咱们先读一遍题，说说题里告诉了我们什么？"
→ "每盘有 3 个苹果，一共 4 盘，那要求什么？"
→ "如果一盘一盘数，要怎么算？有没有更快的办法？"
4. 完整解法
给家长看的（家长得先自己懂），标注每步为什么。
5. 举一反三
一道变式题，检验是真会了还是蒙对了。
分学科要点
数学
- 先让孩子讲题，讲不清就是没懂
- 用实物、画图帮理解（低年级尤其）
- 应用题：先圈条件、再圈问题、再想关系
- 错了先问"你是怎么想的"，找到错误的思维起点
语文
- 阅读理解：先在原文找依据，别凭感觉答
- 作文：从"你想说什么"开始，不要一上来给范文
- 生字词：结合语境记，不要死抄
- 背诵：理解后再背，分段背
英语
- 优先读出来，不要默看
- 单词结合句子记，不要孤立背
- 语法题：先看句子想表达什么，再套规则
科学
- 鼓励先猜想、再验证
- 能动手做的就做（安全前提下）
- "为什么"比"是什么"重要
特殊情况处理
孩子不想写作业
先别急着讲题，可能是：
| 表现 | 可能原因 | 建议 |
|---|---|---|
| 一坐下就走神 | 任务太大，没有掌控感 | 拆小：先做 5 道，做完休息 |
| 一看就说不会 | 畏难，怕出错被批评 | 降低难度起点，先做会的建立信心 |
| 拖到很晚 | 时间管理没建立 | 一起定计划，用计时器 |
| 情绪对抗 | 亲子关系紧张 | 今天先不辅导，关系比作业重要 |
家长自己情绪要炸了
明确提醒：辅导作业最常见的失败不是题不会，是家长发火。
建议话术：
"我现在有点着急，咱们各自安静五分钟再说。"
长期关系 > 这一道题。 必要时建议交给老师。
家长自己也不会
- 先给家长讲明白（用成人能懂的方式）
- 再给引导孩子的话术
- 家长不必装懂，可以说"这题我也得想想，咱们一起研究"——这是很好的示范
注意事项
- 不生成给孩子直接抄写的成品答案。家长需要核对时，可以在引导话术之后单列“家长核对”，写清思路、结果与单位，并明确不要直接转发；如果用户坚持只要答案，也要把最小必要思路放在答案前。Skill 无法控制家长最终是否转发，因此不要声称能阻止抄写。
- 不做超前教学。低年级用高年级方法（如用方程解应用题）会让孩子在学校跟不上。
- 不评价孩子。只说题目和方法，不说"你怎么这么笨"这类话，也提醒家长别说。
- 不确定的知识点要说明。教材版本、解法要求各地不同，涉及"老师要求的格式"时建议问老师。
- 发现可能的学习困难（如持续的读写困难）时，建议家长咨询老师或专业人士，不做诊断。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 112 lines · 65 tokens per session scan A 742a36729552
homework-tutor-cn is a skill published in the GitHub repository sanhuang520-ship-it/awesome-chinese-ai-tools (11 stars, last pushed yesterday), licensed MIT. It adds 65 tokens to every session and 1,291 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
note-organizer
Use this skill whenever the user wants to organize course materials, lecture notes, PPT/PDF/DOCX files, textbooks, personal notes, senior-student notes, historical exams, review questions, standards, manuals, or scattered study resources into a structured Markdown note library. Use it even when the user only says…
wps-courseware
A teaching-material generator that turns learning goals and subject information into a structured presentation. The structure includes an introduction, new material, exercises, review and homework.
wps-exam-paper
An exam-paper formatter for creating standard test sheets with features such as a tear-off sealing line, score table, question numbering, and answer space.
摆脱自我意识三步法
A three-step reflection method for handling defensiveness, envy, or excuses when facing unfamiliar information or someone else's success.
身份认同塑造法
A three-part method for changing limiting beliefs about who you are by redesigning your environment, social group, and learning habits.
22战略执行指南
A long-term routine built around two hours of reading and writing each day, followed by substantial rest. Its name refers to maintaining this practice for two years.