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 hwl668/Scientific-learning-skills- --skill mistake-reviewgit clone --depth 1 https://github.com/hwl668/Scientific-learning-skills-Wrote 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/hwl668/scientific-learning-skills-/mistake-review)<a href="https://agentmods.dev/skills/hwl668/scientific-learning-skills-/mistake-review"><img src="https://agentmods.dev/badge/skills/hwl668/scientific-learning-skills-/mistake-review/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/hwl668/scientific-learning-skills-/mistake-review"><img src="https://agentmods.dev/badge/skills/hwl668/scientific-learning-skills-/mistake-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00073 | $0.01411 |
| Opus 5 | $0.00036 | $0.00705 |
| Sonnet 5 | $0.00015 | $0.00282 |
| Haiku 4.5 | $0.00007 | $0.00141 |
Grade A, and why
mistake-review 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 12d 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
目标
把错题变成学习资源。不只看"正确答案是什么"，而是搞清楚"为什么我会错"和"怎么不再错"。
适用场景
- 考试/作业中做错的题
- 感觉会但做错了的题
- 同样的错误反复出现
- 粗心做错的题（往往不是"粗心"那么简单）
Memory 系统
类型：分析记忆（不参与间隔复习）。
存储位置：memory/mistake-review/
存储内容：
- 高频错因模式库：哪类题型的哪种错因最常见（如"定义域问题→条件漏看→忽略负半轴"）
- 有效检查清单：哪些检查项在不同题目上反复有效
读/写规则：
- 写入：每次复盘结束后，记录"题型→错因类型→关键误区→有效检查项"。
- 读取：下次分析同类错题时，优先匹配已记录的错因模式，加速定位。
- 管理：说"清除 mistake-review 记忆"删除。
输入判断
需要学习者提供：
- 原题完整内容
- 你的错误解答（重要！）
- 正确答案
- 你当时是怎么想的？
如果学习者只能提供"我做错了"但说不出当时的思路，先引导他回忆。
错因分类
| 错因类型 | 表现 | 修复方向 |
|---|---|---|
| 概念错 | 用错了定义，混淆了概念 | 重新辨析概念 |
| 公式错 | 记错或套错公式 | 理解公式来源，不靠死记 |
| 条件漏看 | 忽略了定义域、边界条件等 | 建立检查清单 |
| 计算错 | 符号、代数运算出错 | 分步书写，中间验证 |
| 模型建错 | 题目翻译成数学语言时出错 | 加强建模训练 |
| 边界情况漏掉 | 特例未处理（如 x=0, 空集等） | 建立边界检查习惯 |
| 题型识别错 | 用错了方法体系 | 训练题型识别能力 |
执行流程
重现错误 → 定位错因 → 分析误区 → 正确思路 → 同类识别方法 → 检查清单 → 变式训练
1. 重现错误
让学习者完整展示错误解答，理解当时的思考路径。
2. 定位错因
从上述分类中精确归类。一次可能涉及多个错因，但一定有主因。
3. 分析误区
这一步不只是说"你错了"，而是要指出："你当时可能这样想，实际上问题出在这里。"
4. 正确思路
展示正确的解题思路，但要和错误思路对比，指出在哪个分叉口出了问题。
5. 同类识别方法
教学习者：当你在题中看到什么特征时，就要警惕这种错误。
6. 检查清单
提供 2-3 条具体的检查项，可以直接用在下次做题时。
7. 变式训练
给一道类似的题（不是原题重做），确保真正掌握。
输出格式
## 错因类型
[主要错因 + 次要错因]
## 关键误区
[当时可能怎么想的，实际哪里不对]
## 常见误区
| 常见错误 | 为什么错 | 正确理解 |
|----------|---------|---------|
| [该题型常见错误 1] | [错误机制] | [正确理解] |
| [该题型常见错误 2] | [错误机制] | [正确理解] |
## 正确思路
[分步展示，和错误思路对比]
## 识别同类陷阱
[看到什么特征要警惕]
## 检查清单
- [ ] 检查项 1
- [ ] 检查项 2
## 变式训练
[一道新题]
反例：什么时候不要这样做
- 不要只看正确答案而不管错误原因
- 不要把"粗心"当成万能错因——"粗心"背后往往是概念不牢或习惯不好
- 不要跳过学习者的错误思路直接讲正确解法
- 不要只给变式题不总结方法
- 不要用"多做题就行"敷衍
测试样例
输入：
- 题目：求 f(x) = ln(x² - 1) 的定义域
- 我的答案：x > 1
- 正确答案：x < -1 或 x > 1
期望输出方向：
- 错因：条件漏看——只考虑了 ln 的变量要为正，但没有解完整不等式 x² - 1 > 0
- 误区分析：求解 x² > 1 时忘记绝对值，直接写成 x > 1
- 正确思路：x² > 1 → |x| > 1 → x < -1 或 x > 1
- 同类陷阱：凡是 x² > a (a > 0) 或含根号的定义域问题都要警惕遗漏
- 检查清单：解不等式时画出数轴验证；检查负半轴
- 变式：求 f(x) = √(4 - x²) 的定义域
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.
- 12d ago First seen · 139 lines · 73 tokens per session scan A b5b4f8ec82a2
mistake-review is a skill published in the GitHub repository hwl668/Scientific-learning-skills- (13 stars, last pushed 1mo ago), licensed MIT. It adds 73 tokens to every session and 1,411 once invoked, about $0.0004 per session on Opus 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 2026-08-30.
Other skills, from other repositories
deeptutor-cli
Configure, manage, and use DeepTutor through its CLI, including capabilities, knowledge bases, partners, memory, sessions, notebooks, providers, skills, and the server or Web app.
exam-study-guide
A study-guide builder for a completed exam chapter that has not yet passed its required checks. It creates a structured teaching checklist and, in full mode, a self-contained HTML and printable PDF guide with readable formulas, visible images, explanations, examples, and answers.
exam-ingest
A workspace setup tool for exam preparation. It reads PDFs, Word documents, presentations, spreadsheets, images, text files, and Markdown, then creates chapter notes, a question bank, and tracked preparation data.
exam-cram
An exam-preparation guide for studying shortly before a test. It turns course materials into chapter notes and a question bank, then manages teaching, practice, grading, mistake review, and progress tracking.
exam-tutor
A teaching workflow for learning one chapter from a study wiki at a time, using everyday comparisons and step-by-step explanations of formulas and important questions. TDD is not involved here; the material concerns guided study and exam preparation.
exam-audit
A read-only health check for an exam-preparation workspace, meaning the folder that stores study materials, questions, notes, plans, and progress. It reports missing, inconsistent, or incomplete parts without changing them.