返回技能列表

golden-jupyter

yusufkaraaslan
更新于 Today
14,131
1,453
14,131
在 GitHub 上查看
testingdesign

关于

This skill provides a Jupyter notebook environment for testing and understanding the golden_jupyter golden build. It includes code examples, outputs, and analysis workflows using Python 3.11.4 with key data science libraries like numpy, pandas, and sklearn. Developers should use it to reproduce analysis steps, review methodologies, and reference implementation patterns.

快速安装

Claude Code

推荐
主要方式
npx skills add yusufkaraaslan/Skill_Seekers -a claude-code
插件命令备选方式
/plugin add https://github.com/yusufkaraaslan/Skill_Seekers
Git 克隆备选方式
git clone https://github.com/yusufkaraaslan/Skill_Seekers.git ~/.claude/skills/golden-jupyter

在 Claude Code 中复制并粘贴此命令以安装该技能

技能文档

Golden_Jupyter Notebook Skill

Use when testing the golden_jupyter golden build

📋 Notebook Information

Kernel: Python 3

Language: python 3.11.4

💡 When to Use This Skill

Use this skill when you need to:

  • Understand golden_jupyter concepts and analysis workflow
  • Reference code examples and their outputs
  • Reproduce data analysis or computation steps
  • Review methodology, visualizations, and results
  • Find library usage patterns and best practices

📖 Section Overview

Total Sections: 5

Content Breakdown:

  • analysis: 5 sections

🔑 Key Concepts

Main topics covered in this notebook

Major Topics:

  • Getting Started

Subtopics:

  • Modeling Results

📦 Dependencies

3 package(s) imported

  • numpy
  • pandas
  • sklearn

⚡ Quick Reference

Common documentation patterns found:

Getting Started (1 sections):

  • Getting Started (section 1)

Modeling (1 sections):

  • Modeling Results (section 5)

📝 Code Examples

High-quality code cells from notebook

Bash Examples (1)

Example 1 (Quality: 5.0/10):

pip install pandas

Python Examples (3)

Example 1 (Quality: 9.5/10):

def long_example():
    x0 = 0
    x1 = 1
    x2 = 2
    x3 = 3
    x4 = 4
    x5 = 5
    x6 = 6
    x7 = 7
    x8 = 8
    x9 = 9
    x10 = 10
    x11 = 11
    x12 = 12
    x13 = 13
    x14 = 14
    x15 = 15
    x16 = 16
    x17 = 17
    x18 = 18
    x19 = 19
    x20 = 20
    x21 = 21
    x22 = 22
    x23 = 23
    x24 = 24
    x25 = 25
    x26 = 26
    x27 = 27
    x28 = 28
    x29 = 29
    x30 = 30
    x31 = 31
    x32 = 32
    x33 = 33
    x34 = 34
    x35 = 35
    x36 = 36
    x37 = 37
    x3
...

In [2] (Quality: 7.5/10):

import pandas as pd
df = pd.read_csv('data.csv')
df.head()

Example 3 (Quality: 2.0/10):

%timeit broken()

📊 Notebook Statistics

  • Total Sections: 5
  • Code Cells: 2
  • Markdown Cells: 2
  • Raw Cells: 1
  • Notebooks: 1
  • Programming Languages: 2

Language Breakdown:

  • python: 3 code cells
  • bash: 1 code cells

🗺️ Navigation

Reference Files:

  • references/analysis.md - analysis

See references/index.md for complete notebook structure.


Generated by Skill Seeker | Jupyter Notebook Scraper

GitHub 仓库

yusufkaraaslan/Skill_Seekers
路径: tests/golden/phase2/jupyter
0
ai-toolsast-parserautomationclaude-aiclaude-skillscode-analysis

相关推荐技能

content-collections

Content Collections 是一个 TypeScript 优先的构建工具,可将本地 Markdown/MDX 文件转换为类型安全的数据集合。它专为构建博客、文档站和内容密集型 Vite+React 应用而设计,提供基于 Zod 的自动模式验证。该工具涵盖从 Vite 插件配置、MDX 编译到生产环境部署的完整工作流。

查看技能

polymarket

这个Claude Skill为开发者提供完整的Polymarket预测市场开发支持,涵盖API调用、交易执行和市场数据分析。关键特性包括实时WebSocket数据流,可监控实时交易、订单和市场动态。开发者可用它构建预测市场应用、实施交易策略并集成实时市场预测功能。

查看技能

creating-opencode-plugins

该Skill帮助开发者创建OpenCode插件,用于接入命令、文件、LSP等25+种事件。它提供了插件结构、事件API规范和JavaScript/TypeScript实现模式,适合需要拦截操作、扩展功能或自定义事件处理的场景。开发者可通过它快速构建响应式模块来增强OpenCode AI助手的能力。

查看技能

sglang

SGLang是一个专为LLM设计的高性能推理框架,特别适用于需要结构化输出的场景。它通过RadixAttention前缀缓存技术,在处理JSON、正则表达式、工具调用等具有重复前缀的复杂工作流时,能实现极速生成。如果你正在构建智能体或多轮对话系统,并追求远超vLLM的推理性能,SGLang是理想选择。

查看技能