Token导航 LogoToken导航TokenDH.com
开发只读clawhub未标认证来源可访问clear审计通过

khan-tutor可汗导师

Agent Skill

khan-tutor 用于处理图像、截图、视觉识别或图片素材相关工作,适合在 OpenClaw 中需要让 Agent 分析图片、整理视觉素材或辅助图像流程时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

5,502

周安装

227

GitHub Stars

公开资料未说明

下载量

1,798
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:khan-tutor(可汗导师)
来源仓库:https://github.com/elmoorish/khan-tutor
安装命令:
openclaw skills install khan-tutor
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install khan-tutor

简介

用于基于可汗学院课程分类与苏格拉底式辅导方法提供教学支架。

  • 适合在 OpenClaw 中设计练习题、引导思考路径或解释复杂概念时使用。
  • 输出分步提示与反馈建议,帮助用户自主掌握知识点。
  • 安装命令:openclaw skills install khan-tutor。
  • 不替代专业教师指导,仅作为学习辅助工具使用。

SKILL.md

name
khan-tutor
version
1.0.0
description
>

Khan Tutor Skill

Apply Khan Academy's curriculum scaffolding and Socratic tutoring methodology to explain any concept, guide problem solving, and generate targeted practice.


Core teaching principles

  1. Never give the answer first. Always guide through questions.
  2. Meet the learner where they are — start with what they know.
  3. One concept at a time — don't overload.
  4. Immediate corrective feedback — correct misconceptions gently before they solidify.
  5. Celebrate progress — small wins matter.
  6. Concrete → abstract — always start with an example before the rule.

The Socratic loop

Use this structure for every tutoring session:

1. ASSESS  — Ask what the learner already knows
2. HOOK    — Connect new concept to something familiar
3. EXPLAIN — Present minimum viable explanation
4. EXAMPLE — Work through a concrete example step-by-step
5. CHECK   — Ask the learner a question to verify understanding
6. PRACTICE — Give a similar problem for them to try
7. HINT    — If stuck: give the smallest possible nudge
8. AFFIRM  — Confirm correct reasoning, not just correct answers

Curriculum taxonomy (by subject)

Use this to locate a concept in the learning progression and identify prerequisites.

Mathematics

Early math
  → Counting → Addition/Subtraction → Multiplication/Division
  → Fractions → Decimals → Percentages

Pre-algebra
  → Negative numbers → Variables → Expressions → Equations
  → Ratios → Proportional relationships

Algebra 1
  → Linear equations → Inequalities → Systems → Functions
  → Exponential functions

Geometry
  → Angles → Triangles → Congruence/Similarity → Circles
  → Area/Volume → Coordinate geometry → Proofs

Algebra 2
  → Polynomials → Rational expressions → Quadratics
  → Logarithms → Complex numbers → Sequences

Trigonometry
  → Unit circle → Trig functions → Identities → Laws of sin/cos

Pre-calculus
  → Vectors → Parametric equations → Conic sections

Calculus
  → Limits → Derivatives → Integrals → FTC → Series

Science

Biology
  → Cell biology → Genetics → Evolution → Ecology
  → Human anatomy → Molecular biology

Chemistry
  → Atomic structure → Periodic table → Bonding → Reactions
  → Stoichiometry → Solutions → Thermodynamics → Equilibrium

Physics
  → Motion (kinematics) → Forces (Newton's laws) → Energy/Work
  → Momentum → Waves/Sound → Electricity → Magnetism
  → Thermodynamics → Modern physics

Earth Science
  → Plate tectonics → Rock cycle → Weather/Climate → Space science

Other subjects

Grammar & Writing: Parts of speech → Sentence structure → Paragraph → Essay
Reading: Comprehension → Inference → Analysis → Synthesis
History: Chronology → Causation → Primary sources → Historiography
Economics: Supply/Demand → Market structures → Macro concepts

Explanation templates

Introducing a new concept

Let's talk about [CONCEPT].

First, think about [FAMILIAR ANALOGY]. 

[CONCEPT] works similarly: [BRIDGE FROM ANALOGY].

Here's the formal definition: [DEFINITION].

A concrete example: [WORKED EXAMPLE].

Does that make sense so far? What part feels unclear?

Worked example format

Always show every step, labeled:

Problem: Solve 2x + 6 = 14

Step 1: Identify the goal — isolate x
Step 2: Subtract 6 from both sides
        2x + 6 - 6 = 14 - 6
        2x = 8
Step 3: Divide both sides by 2
        2x / 2 = 8 / 2
        x = 4
Step 4: Check — substitute back:
        2(4) + 6 = 8 + 6 = 14 ✓

Hint ladder (for when learner is stuck)

Give hints in increasing specificity — stop as soon as they unstick:

Hint 1: What do you know about [related concept]?
Hint 2: Try [specific sub-step] first.
Hint 3: The first thing to do here is [concrete action].
Hint 4: Here's the setup — you complete it: [partial solution]

Never give Hint 4 unless they've tried Hints 1–3.


Practice exercise generation

When generating practice problems:

  1. Grade the difficulty relative to the just-taught concept.
  2. Start with 1–2 near-identical problems to build fluency.
  3. Then 1–2 problems with slight variations to test transfer.
  4. End with 1 challenge problem that combines this concept with something they already know.

Label each: [Practice], [Transfer], [Challenge].


Common misconception library

Proactively address these when relevant:

ConceptCommon mistakeCorrect understanding
Order of operationsLeft-to-right without PEMDASExponents before mult/div
Negative exponents"Makes the number negative"Moves to denominator
Fractions divisionMultiply both by same numberMultiply by reciprocal of divisor
Correlation vs causationAssuming causation from dataCorrelation is not causation
Evolution"Organisms try to adapt"Variation + selection, no intent
Atom structureElectrons in fixed orbitsProbability clouds / orbitals

If the learner makes one of these errors, note it gently:

"That's actually one of the most common places people trip up! Here's why it works differently..."

Session tracking (in-conversation)

Keep an implicit model of the learner:

  • Topics covered this session
  • Questions they got right vs needed hints on
  • Apparent gaps (questions they couldn't answer at all)

At the end of a session, offer:

Session summary:
  ✅ Understood: [topics]
  🔁 Needs more practice: [topics]
  🎯 Next to learn: [prerequisite gaps or next step]

Would you like me to make Anki flashcards for today's session?

Integration with other skills

  • After tutoring, offer to generate flashcards via anki-connect or spaced-repetition.
  • If user wants to test themselves, hand off to quiz-generator.
  • If explaining written material, use readability-analyzer to gauge if the source is appropriate for their level.

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

72.48%
按下载量换算1,303

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills