Skip to content

brycewang-stanford/Auto-Empirical-Research-Skills / skills/33-Galaxy-Dawn-claude-scholar/skills/kaggle-learner

kaggle-learner

Verified

This skill should be used when the user asks to "learn from Kaggle", "study Kaggle solutions", "analyze Kaggle competitions", or mentions Kaggle competition URLs. Provides access to extracted knowledge from winning Kaggle solutions across NLP, CV, time series, tabular, and multimodal domains.

Kaggle Learner

Extract and apply knowledge from Kaggle competition winning solutions. This skill provides access to a continuously updated knowledge base of techniques, code patterns, and best practices from top Kaggle competitors.

Overview

Kaggle competitions are at the forefront of practical machine learning. Winning solutions often innovate with novel techniques, clever feature engineering, and optimized pipelines. This skill captures that knowledge and makes it accessible for your projects.

When to Use

Use this skill when:

  • Studying for a Kaggle competition
  • Looking for proven techniques in a specific domain (NLP, CV, etc.)
  • Need code templates for common ML tasks
  • Want to learn from competition winners

Knowledge Categories

CategoryFocusDirectory
NLPText classification, NER, translation, LLM applicationsreferences/knowledge/nlp/
CVImage classification, detection, segmentation, generationreferences/knowledge/cv/
Time SeriesForecasting, anomaly detection, sequence modelingreferences/knowledge/time-series/
TabularFeature engineering, traditional ML, structured datareferences/knowledge/tabular/
MultimodalCross-modal tasks, vision-language modelsreferences/knowledge/multimodal/

文件组织结构:每个竞赛一个独立的 markdown 文件,按 domain 分类到对应目录。

示例:

  • time-series/birdclef-plus-2025.md
  • nlp/aimo-2-2025.md

Quick Reference

To learn from a competition:

  1. Provide the Kaggle competition URL
  2. The kaggle-miner agent will extract the winning solution
  3. Knowledge is automatically added to the relevant category
  4. 前排方案详细技术分析 (Front-runner Detailed Technical Analysis) is automatically included

To browse existing knowledge:

  • 浏览相关 domain 目录:references/knowledge/[domain]/
  • 每个竞赛一个独立文件,包含:
    • Competition Brief (竞赛简介)
    • 前排方案详细技术分析 (前排方案详细技术分析) ⭐
    • Code Templates (代码模板)
    • Best Practices (最佳实践)

Self-Evolving

This skill automatically updates its knowledge base when the kaggle-miner agent processes new competitions. The more you use it, the smarter it becomes.

Knowledge Extraction Standard

每次从 Kaggle 竞赛提取知识时,必须包含以下标准部分:

必需内容清单

部分说明必需性
Competition Brief竞赛背景、任务描述、数据规模、评估指标✅ 必需
Original Summaries前排方案的简要概述✅ 必需
前排方案详细技术分析Top 20 方案的核心技巧和实现细节✅ 必需 ⭐
Code Templates可复用的代码模板✅ 必需
Best Practices最佳实践和常见陷阱✅ 必需
Metadata数据源标签和日期✅ 必需

前排方案详细技术分析格式

每个前排方案应包含:

  • 排名和团队/作者
  • 核心技巧列表 (3-6 个关键技术点)
  • 实现细节 (具体的参数、配置、数据)

示例格式:

**排名 Place - 核心技术名称 (作者)**

核心技巧:
- **技巧1**: 简短说明
- **技巧2**: 简短说明

实现细节:
- 具体参数、模型、配置
- 数据和实验结果

建议覆盖 Top 20 方案,获取更多前排选手的创新技巧

Additional Resources

Knowledge Directories

  • references/knowledge/nlp/ - NLP competition techniques
  • references/knowledge/cv/ - Computer vision techniques
  • references/knowledge/time-series/ - Time series methods
  • references/knowledge/tabular/ - Tabular data approaches
  • references/knowledge/multimodal/ - Multimodal solutions

Competition Examples

  • BirdCLEF+ 2025 (time-series/birdclef-plus-2025.md) - 包含完整的 Top 14 前排方案详细技术分析
  • BirdCLEF 2024 (time-series/birdclef-2024.md) - 包含 Top 3 方案详细技术分析
  • AIMO-2 (nlp/aimo-2-2025.md) - 包含 Top 12+ 前排方案技术总结
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall