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.
Install
npx skills add mingchen666/Reviva --skill mistake-analyzergit 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-analyzerPersonal 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.
Details
- Skill name
mistake-analyzer- Repository
- mingchen666/Reviva
- 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
341mingchen666/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。
AI Animation Skill
341mingchen666/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。
Bili Note
341mingchen666/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.
Attention Control
149aaddrick/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".
Math Explainer
341mingchen666/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
Imagegen
398JetBrains/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.
Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.