Atlas / Skills / leoyeai / Rootcraft Learning System

Rootcraft Learning SystemSAFE

skills/leoyeai/rootcraft-learning-system

🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai

Verdict
SAFE
Grade
B
Trust score
89 /100
Version
1.1.4
Hosts
1 documented
License
MIT
Stars
2,160
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

A high-efficiency learning methodology for deep knowledge mastery

[](https://github.com/zhangquan/rootcraft-learning-system) [](LICENSE)

📖 Overview

RootCraft Learning System integrates four powerful learning methodologies into a unified framework:

  1. First Principles Thinking → Trace to fundamental facts and concepts
  2. Taxonomy-Based Classification → Systematically decompose and structure
  3. Feynman Technique → Validate through output, identify gaps
  4. Recursive Questioning → Chase "aha moments" through layered inquiry

🎯 Key Features

  • ✅ 9-Step Learning Flow - Complete process from goal setting to knowledge mastery
  • ✅ Recursive Questioning Framework - 5 sub-steps for deep understanding
  • ✅ Aha Moment Tracking - Document breakthrough insights
  • ✅ Practical Examples - Real-world learning scenarios (Diffusion Models, Machine Learning)
  • ✅ File Organization Templates - Structured directory for learning materials
  • ✅ Spaced Repetition Plan - Long-term retention strategy

🚀 Quick Start

Installation

# Install via ClawHub
clawhub install rootcraft-learning-system

Usage

When you want to learn something new, simply say:

  • "I want to learn..."
  • "How to learn efficiently..."
  • "Help me create a study plan..."
  • "This concept is unclear..."

The system will guide you through the 9-step learning flow.

📚 Core Methodology

Step 1-3: Foundation

  • Define goals and evaluation criteria
  • Apply first principles thinking
  • Build taxonomy-based classification

Step 4: Deep Understanding (Core)

The Feynman Technique with Recursive Questioning:

4.1 Start with a Real Problem
4.2 Generate Questions Through Practice
4.3 Recursive Downward Questioning
4.4 Restate in Your Own Words
4.5 Chase t
Read from source at commit 4f3b4a2a472eOBSERVED · 2026-10-08
02

Host compatibility

What the documentation claims. We have not run a compatibility test.

HostStatusNotes
openclawmentioned
03

What it tells the agent

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: rootcraft-learning-system
version: 1.1.4
author: 张权 (Zhang Quan)
author_website: https://www.luckydesigner.space
author_brand: Luckydesigner(行运设计师)
author_pen_name: 伯衡君
name_display: 格物本质赋能学习法
description: RootCraft Learning System - An integrated learning methodology combining First Principles Thinking, Taxonomy-Based Classification, Feynman Technique, and Recursive Questioning for deep knowledge mastery and "aha moment" discovery. Includes Anki memory cards generation based on Ebbinghaus forgetting curve. Chinese name: 格物本质赋能学习法.
trigger_keywords: learning method, first principles, taxonomy classification, feynman technique, recursive questioning, aha moment, efficient learning, study system, knowledge mastery, how to learn, learn about, 格物致知, 学习方法, 啊哈时刻, 如何学习, 想学习, 帮我学习, 我想学习, 学习教程, 教学, 培训
---

# RootCraft Learning System (格物本质赋能学习法)

---

## 🎓 User Guide / 使用指南

> When user asks "how to use this skill" or "如何使用", show this guide.

### 中文引导 (Chinese Guide)

```
🎓 欢迎使用格物本质赋能学习法!

这是一个高效学习系统,帮你从"学了就忘"变成"学了就懂"。

┌─────────────────────────────────────────────────────────────┐
│  📚 核心方法                                              │
├─────────────────────────────────────────────────────────────┤
│  🔍 第一性原理    →  追问本质,挖到不能再挖为止           │
│  📊 分类学        →  系统拆解,构建 MECE 结构             │
│  🎤 费曼 technique →  讲给别人听,发现知识缺口            │
│  ❓ 递归追问      →  层层深挖,追到"啊哈"时刻            │
└─────────────────────────────────────────────────────────────┘

📋 9 步学习流程:
1. 设定目标 & 评估标准
2. 应用第一性原理
3. 分类学拆解
4. 费曼 + 递归追问(核心)
5. 多视角学习
6. 实践应用
7. 反馈与迭代
8. 持续复习
9. 思维导图与笔记

🚀 快速开始:
• 直接说"我想学习【主题】" → 直接开始完整学习流程
• 或说"帮我用格物本质赋能学习法学习【内容】"
• 说"我想制定学习计划"让我帮你规划

⚡ **直接学习模式**:
当用户说"我想学习XX"时,直接输出完整的9步学习流程,不要问问题!

流程模板:
```
🎓 好的,让我们开始学习【主题】!

--- 9步学习流程 ---

1. 设定目标 & 评估标准
(直接给出该主题的学习目标和评估标准)

2. 第一性原理
(解释该主题的本质是什么)

3. 分类学拆解(MECE)
(系统化拆解该主题的知识体系)

4. 费曼 + 递归追问
(核心概念检验 + 追问链)

5. 多视角学习
(从数学、工程、应用等角度分析)

6. 实践应用
(给出一个最小可运行的代码示例)

7. 反馈与迭代
(含**试卷生成**功能)
```
🎯 试卷生成:根据所学内容自动生成测试题

题型包括:
• 选择题(3-5题)- 检验概念理解
• 填空题(3-5题)- 检验关键术语记忆
• 简答题(2-3题)- 检验逻辑表达能力
• 操作题(1-2题)- 检验实际应用能力

每道题标注:难度等级、知识点归属、参考答案
```

8. 持续复习
(艾宾浩斯遗忘曲线复习计划)

9. 思维导图与笔记
(输出知识图谱)

💡 Aha Moment记录
📦 Anki卡片

--- 自动保存详细内容 ---
⚠️ 必须将上述9步的详细内容保存到文件,而不是只保存模板!

保存方式:
```python
import sys
sys.path.insert(0, '/root/.openclaw/skills/rootcraft-learning-system')
from study_writer import create_study_files

# 将详细内容保存到文件
content = {
    "goals": """# 学习目标\n\n(详细内容)""",
    "first_principles": """# 第一性原理\n\n(详细内容)""",
    # ... 其他步骤的详细内容\n}
result = create_study_files('主题', content, anki_cards)
```

> 💡 **内容质量提示**:为了生成高质量文档,请在content中提供详细、完整的内容。\n> \n> **详细模板示例**:\n```python\ncontent = {\n    'goals': \"\"\"# 学习目标\n\n## 短期目标(1-4周)\n- 理解AI的基本概念和核心原理\n- 掌握机器学习基础知识\n\n## 中期目标(1-3个月)\n- 深入理解机器学习核心理论\n- 能够独立完成ML项目\n\n## 长期目标(3-12个月)\n- 达到专业水平\n- 能够创新和解决问题\n\n## 评估标准\n- [ ] 掌握核心概念≥10个\n- [ ] 完成项目≥3个\n- [ ] 学习时长≥100小时\n\"\"\",\n    \n    'first_principles': \"\"\"# 第一性原理\n\n## 核心公理\n\n### 公理1:机器学习是函数拟合\n- 输入x → f(x) → 输出y\n- 关键是找到最好的f\n\n### 公理2:数据决定模型上限\n- Garbage In, Garbage Out\n- 特征工程决定效果\n\n### 公理3:没有免费午餐\n- 没有最优算法\n\n### 公理4:奥卡姆剃刀\n- 简单模型往往更好\n\n## 核心定义\nAI的本质是[填写]\n\n## 关键洞察\n> 一句话总结核心领悟\n\"\"\",\n    \n    'taxonomy': \"\"\"# 知识分类体系\n\n## 算法分类\n\n### 监督学习\n| 类型 | 算法 | 场景 |\n|------|------|------|\n| 分类 | 逻辑回归、SVM | 分类预测 |\n| 回归 | 线性回归、GBDT | 数值预测 |\n\n### 无监督学习\n| 类型 | 算法 | 场景 |\n|------|------|------|\n| 聚类 | K-Means | 用户分群 |\n| 降维 | PCA | 可视化 |\n\n### 深度学习\n| 模型 | 应用场景 |\n|------|------|\n| CNN | 图像 |\n| Transformer | NLP |\n\"\"\",\n    \n    'feynman': \"\"\"# 费曼检验\n\n## 核心概念检验\n\n### Q1: 什么是梯度下降?\nA: 像下山找最低点,每次往低处走一点\n\n### Q2: 过拟合是什么?\nA: 记住题库而不是学会做题\n\n## 递归追问链\n- 最根本的原因是什么?\n- 还有更基础的原因吗?\n\n## Aha Moment\n记录你的领悟时刻\n\"\"\",\n    \n    'multi_perspective': \"\"\"# 多视角学习\n\n## 技术视角\n- 算法原理\n- 实现方法\n- 优缺点\n\n## 应用视角\n- CV、NLP、推荐系统\n- 行业案例\n\n## 历史视角\n- 发展历程\n- 关键里程碑\n\n## 哲学视角\n- 思维方式\n- 底层逻辑\n\"\"\",\n    \n    'practice': \"\"\"# 实践应用\n\n## 最小可运行方案\n\n### 环境准备\n```bash\npip install numpy pandas scikit-learn\n```\n\n### 核心代码\n```python\nimport numpy as np\nfrom sklearn.linear_model import LinearRegression\n\n# 示例代码\nmodel = LinearRegression()\nmodel.fit(X_train, y_train)\n```\n\n## 实战项目\n- 项目1:入门级\n- 项目2:进阶级\n\"\"\",\n    \n    'feedback': \"\"\"# 反馈与迭代\n\n## 常见问题\n\n### Q1: 数学不够怎么办?\nA: 够用即可:梯度、矩阵、概率\n\n### Q2: 调参玄学怎么办?\nA: 网格搜索→贝叶斯优化\n\n## 解决方案\n1. 制定计划\n2. 定期复盘\n\"\"\",\n    \n    'review': \"\"\"# 复习计划\n\n## 艾宾浩斯复习表\n\n| 时间点 | 内容 |\n|--------|------|\n| 10分钟 | 核心概念 |\n| 1天 | 基础知识点 |\n| 3天 | 进阶知识 |\n| 7天 | 整体串联 |\n| 14天 | 重点强化 |\n| 30天 | 全面复盘 |\n\n## 记忆技巧\n- 联想记忆\n- 间隔重复\n\"\"\",\n    \n    'mindmap': \"\"\"# 思维导图\n\n## 中心主题\n机器学习\n\n## 一级分支\n- 基础:数学、Python\n- 算法:监督、无监督、深度学习\n- 工程:数据处理、模型训练、部署\n- 应用:CV、NLP、推荐\n\n## 关键连接\n- 基础→算法→应用\n\"\"\"\n}\n```\n
✅ 文件保存到 /root/.openclaw/workspace/study/{主题}/
✅ 包含12个md文件 + anki_cards.csv
✅ 新增:08-exam.md(试卷文件)

⚠️ **重要**:每次学习流程结束后,必须调用文件生成模块:
```python
import sys
sys.path.insert(0, '/root/.openclaw/skills/rootcraft-learning-system/study_writer')
from study_writer import generate_and_save, quality_check, print_quality_report, save_exam_paper

# 1. 生成学习文件
result = generate_and_save('主题名称')

# 2. 手动生成试卷(可选)
exam_path = save_exam_paper('主题名称')

# 3. 执行质检
qc_result = quality_check('主题名称')
print_quality_report(qc_result)
```

📋 **质检模块** (Quality Check) - v1.1.1:
每次学习流程结束后,系统检查以下内容:

| 检查项 | 文件 | 说明 |
|--------|------|------|
| ✅ 学习目标 | 01-goals.md | 1.设定目标&评估标准 |
| ✅ 第一性原理 | 02-first-principles.md | 2.第一性原理分析 |
| ✅ 分类学拆解 | 03-taxonomy.md | 3.MECE结构拆解 |
| ✅ 费曼+追问 | 04-feynman.md | 4.核心概念检验 |
| ✅ 多视角学习 | 05-multi-perspective.md | 5.多角度分析 |
| ✅ 实践应用 | 06-practice.md | 6.最小可运行示例 |
| ✅ 反馈与迭代 | 07-feedback.md | 7.常见问题+试卷 |
| ✅ 持续复习 | 08-review.md | 8.艾宾浩斯计划 |
| ✅ 思维导图 | 09-mindmap.md | 9.知识图谱 |
| ✅ Aha Moment | 10-aha-moment.md | 啊哈时刻记录 |
| ✅ Anki卡片 | anki_cards.csv | 可导入的记忆卡片 |
| ⭐ **试卷文件** | 08-exam.md | **选择题+填空题+简答题+操作题** |

**质检函数**:
```python
from study_writer import quality_check, print_quality_report

qc = quality_check('主题名称')
print_q
04

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codeWARN
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
declared (1 observation(s))
Network
none-observed
Shell
none-observed
Dependencies
pinned
Secrets in source
none-found

Findings (1)

MEDIUMObfuscation / stealth · obf.base64_blob · CWE-506, CWE-94
skills/compdf-conversion-cli/scripts/license.xml:9
<key>k5Ey9KFlkqpj+SDkUw+5ED9lTA3En/qUi0zdrydUCH3kMWTE3Eh65NXnFCaxlY2omY2JHnlEoK7Li7oOEvM7eG5VPdcO/sFlMfoCRdnLYdepJ+uLzYwOWR8W4yQVve/clxVFTVRL4DFleKInGdpAxIbHZT2yi4ADAMENls1N1XSLojRuqXePXDeAT/4Mv4TTx0s

Gates applied: no_behavioural_pass.

Audited 2026-10-08 · audit v0.4.1 · source sha 4f3b4a2a472efull audit observations/trust-audit/skill/leoyeai__rootcraft-learning-system.json · Report an issue / request a re-scan
05

Audit history

Every audit this skill has had.

DateSourceVerdictGradeScoreChange
2026-10-084f3b4a2a472eSAFEB89first audit
06

Questions

What does the Rootcraft Learning System skill do?

🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai

Is Rootcraft Learning System safe to install?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.

What can Rootcraft Learning System access on my machine?

The audit observed that it reads or writes files. Each of those is consistent with what it says it does. Secrets in the source: none found.

Which assistants does Rootcraft Learning System work with?

Its documentation mentions openclaw. That is what the text claims, not a compatibility test we ran.

How current is this page?

The grade is for one exact copy of the source (4f3b4a2a472e), read on 2026-10-08. The repository is watched, and a new audit runs when it changes — this is the first audit.

Advertisement