Mistake Analyzer

Analyze incorrect answers from text, documents, or images; identify root causes of mistakes; classify error types; explain correct reasoning; and generate targeted improvement suggestions, wrong-question notebook entries, or similar practice questions. Use when the user provides a wrong answer, asks why they were wrong, uploads a marked question, or wants help reviewing mistakes.

341 stars 39 forksImages, Video & Audio

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add mingchen666/Reviva --skill mistake-analyzer
Manual install
git clone --depth 1 https://github.com/mingchen666/Reviva.git /tmp/Reviva
mkdir -p ~/.claude/skills
cp -r /tmp/Reviva/electron/builtin-assets/skills/mistake-analyzer ~/.claude/skills/mistake-analyzer

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Mistake Analyzer

## Purpose

This skill helps the agent analyze mistakes in learning and assessment contexts.

It identifies:

- what went wrong;
- where the reasoning failed;
- why the mistake happened;
- what the correct reasoning should be;
- how the user can avoid similar mistakes;
- what practice should come next.

The goal is to turn mistakes into targeted learning opportunities.

---

## When to Use

Use this skill when the user asks to:

- analyze a wrong answer;
- review a mistake;
- understand why they got a question wrong;
- compare their answer with the correct answer;
- diagnose a weak point;
- analyze teacher feedback;
- analyze a screenshot or photo of a wrong question;
- analyze handwritten work;
- analyze marked homework or teacher comments;
- generate a wrong-question notebook entry;
- create similar practice questions from a mistake;
- identify patterns across multiple mistakes.

Examples:

- “我这题为什么错?”
- “帮我分析这道错题。”
- “这是我的答案和标准答案,差在哪里?”
- “我总是这种题错,帮我找原因。”
- “根据这些错题生成巩固练习。”
- “把这道错题整理成错题本。”
- “我上传了一张错题图片,帮我看看。”
- “这张试卷截图里我错在哪里?”

---

## When Not to Use

Do not use this skill when:

- the user only wants a general explanation of a concept;
- the user wants a quiz generated from scratch;
- the user wants direct tutoring without mistake analysis;
- no question, answer, image, or mistake information is available;
- the user asks for dishonest academic behavior;
- the user wants fabricated grading standards or answer keys.
Read the full skill on GitHub

Details

Skill name
mistake-analyzer
Path
electron/builtin-assets/skills/mistake-analyzer/SKILL.md
Repo updated
15 November 2026

FAQ

What does the Mistake Analyzer skill do?

Analyze incorrect answers from text, documents, or images; identify root causes of mistakes; classify error types; explain correct reasoning; and generate targeted improvement suggestions, wrong-question notebook entries, or similar practice questions. Use when the user provides a wrong answer, asks why they were wrong, uploads a marked question, or wants help reviewing mistakes.

How do I install the Mistake Analyzer skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add mingchen666/Reviva --skill mistake-analyzer. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Mistake Analyzer popular?

It lives in mingchen666/Reviva, which has 341 GitHub stars and 39 forks.

Related skills

Web Access

341

mingchen666/Reviva

所有联网操作必须通过此 skill 处理,包括:搜索、网页抓取、登录后操作、网络交互等。 触发场景:用户要求搜索信息、查看网页内容、访问需要登录的网站、操作网页界面、抓取社交媒体内容(小红书、微博、推特等)、读取动态渲染页面、以及任何需要真实浏览器环境的网络任务。

Other39

AI Animation Skill

341

mingchen666/Reviva

将科普内容文本转换为可视化PPT风格网页的完整工作流。当用户输入科普内容并希望生成演示页面时触发。支持两种模式:(1) 默认模式:将科普内容生成为仿PPT轮播的单页HTML动画网页;(2) 流程图模式:使用Animation模板将已生成的AI_Animation.html按平面UI样式重构。模板已内置于Skill中。触发词包括"生成PPT"、"生成演示网页"、"生成流程图"等。

Frontend & Design39

Bili Note

341

mingchen666/Reviva

Turn Bilibili videos that are already registered and parsed in MindSpace, or Bilibili opus/article posts, into evidence-linked Markdown learning notes. Use whenever the user asks to 提取、提炼、总结、整理 B站/Bilibili 视频、课程、动态、图文或专栏,保存学习笔记,结合评论区补充观点,或从已解析视频中查找带时间戳的内容和关键画面。Video tasks require an authorized mediaId from the current attachment context; this skill never installs or runs its own ASR models.

Productivity & Notes39

Attention Control

149

aaddrick/attention-control

Shape output for a reader with ADHD, then write each sentence in controlled English: action first, one word one meaning, active voice, simple tenses, state restated every turn. Invoke with /attention-control; stays on until "stop attention control".

Images, Video & AudioIn 1 list

Math Explainer

341

mingchen666/Reviva

Generate math explanation videos (animated with Manim) and interactive web pages from a user's request. Use when the user asks to explain, teach, visualize, or animate a math/physics concept, wants a "math video", "讲解视频", "数学动画", "动画演示", a Manim animation, an interactive math demo, an interactive webpage/可视化/网页演示, or to turn a formula/theorem/problem into a visual explainer. By default produces BOTH a Manim-rendered MP4 video and a paired self-contained interactive HTML page sharing the same concept, notation, parameters, and palette. Covers planning the script, writing Manim scenes, rendering

Images, Video & Audio39

Imagegen

398

JetBrains/skills

Use when the user asks to generate or edit images via the OpenAI Image API (for example: generate image, edit/inpaint/mask, background removal or replacement, transparent background, product shots, concept art, covers, or batch variants); run the bundled CLI (`scripts/image_gen.py`) and require `OPENAI_API_KEY` for live calls.

Images, Video & Audio35

Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.