复习错题本 · Wrong Answer Coach
把错题变成提分清单:归类错因、生成同类变式题与间隔复习表,盯住薄弱点直到不再错。 Turn mistakes into higher scores: categorize causes, generate similar practice items, and build a spaced-review table until weak points stop recurring.
$7
Works with the AI Agents you already use
Claude Code
Cursor
Codex CLI
Muse
Dots+22 moreClaude CodeCursorCodex CLIMuseDots
OpenClaw
Manus
Grok
Grok Bot+18 agents复习错题本 · Wrong Answer Coach
Example session with this skill installed
我数学错题本里有23道错题,快期末了,帮我分类错因并做间隔复习计划,顺便出几道同类变式题。
- Read your context and instructions
- Compiled the wrong answer coach
错题诊断
23 道错题分类:计算错误 9 道、知识盲区 7 道、审题失误 4 道、思路偏差 3 道。计算类占比最高,建议先专项练,再补知识盲区。
一、错因分类
| 错因 | 数量 | 特征 | 对策 |
|---|---|---|---|
| 计算错误 | 9 | 步骤对,数字错 | 草稿分区 + 验算 |
| 知识盲区 | 7 | 公式不会用 | 回归课本例题 |
| 审题失误 | 4 | 看错条件 | 圈关键词 |
| 思路偏差 | 3 | 方法选错 | 归纳题型套路 |
二、变式题示例(知识盲区:二次函数最值)
原题:求 y=x²-4x+5 的最小值。
变式 1:求 y=-x²+6x-2 的最大值;
变式 2:x 在 [0,3] 内,求 y=x²-4x+5 的最值;
变式 3:利润 w=(x-10)(40-x),求最大利润对应的定价。
三、间隔复习表
| 轮次 | 时间 | 内容 | 达标标准 |
|---|---|---|---|
| 第 1 轮 | 明天 | 9 道计算错题重做 | 全对 |
| 第 2 轮 | 3 天后 | 7 道盲区题 + 变式 | 对 5 道以上 |
| 第 3 轮 | 7 天后 | 全部 23 道重做 | 错 2 道以内 |
四、出本规则
- 连续两轮全对的题移出错题本;
- 第 3 轮仍错的题,标记为重点并找老师讲解。
下一步
- 今晚先重做 9 道计算错题,计时 25 分钟;
- 把 7 道盲区题对应的课本例题翻出来看;
- 后天我按变式题思路再出 3 道新题。
Connects securely to your tools. The creator never sees your data.
About this skill
它解决什么问题
错题抄了一本,考前翻一遍就完,下次同样错:因为没分类错因,也没间隔重练。直接让 AI 讲错题,常只讲这道题,不追根因也不出变式题。
这个技能做什么
先把错题按「知识盲区 / 审题失误 / 计算错误 / 思路偏差」分类,再针对高频错因讲解并生成 2-3 道变式题;输出间隔复习表(1 天 / 3 天 / 7 天),每轮标注掌握度,直到连续两轮全对再移出错题本。
为什么比裸提示词强
- 追根因:先分类再讲解,不再盲目刷题。
- 出变式:同考点换数字换问法,防止背答案。
- 带节奏:间隔复习表保证真正记住。
典型用例
- 考前把错题本变成冲刺清单。
- 给孩子的作业错题做分类讲解。
- 整理成团队共用的易错题库。
局限
讲解质量依赖题目信息完整;高难度竞赛题请结合老师指导。
English · 英文介绍
The problem
I copied a wrong question and read it over before taking the exam. I will make the same mistake next time: because I didn’t classify the cause of the mistake and there was no interval to practice again. Directly asking the AI to answer the wrong question will often only tell the question without tracing the root cause or asking for variations.
What it does
First, classify wrong questions according to "knowledge blind spots/question review errors/calculation errors/ideas deviations", then explain the causes of high-frequency errors and generate 2-3 variant questions; output an interval review table (1 day / 3 days / 7 days), mark the mastery level in each round, and then move the wrong questions to the correct book after two consecutive rounds.
Why is it better than naked prompt words?
- Tracing the root cause: Classify first and then explain, no more blindly answering questions.
- Variation: Change the numbers in the same test point and change the question method to avoid memorizing the answers.
- Rhymed: Spaced review sheets guarantee true retention.
Typical use cases
- Before the exam, turn the wrong question book into a sprint list.
- Classify and explain the children's homework mistakes.
- Organized into a common error-prone question bank shared by the team.
Limitations
The quality of the explanation depends on the complete information of the questions; for difficult competition questions, please use the teacher's guidance.
How to use
Skills on Agensi run inside your AI agent. Copy the prompt, paste it into your agent, and it connects to Agensi and installs this skill for you. If a payment is needed, your agent shows it to you first.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scanned
Verified clean 1 month ago
- Passed all security checks, Safe to install