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
| Category | Focus | Directory |
|---|---|---|
| NLP | Text classification, NER, translation, LLM applications | references/knowledge/nlp/ |
| CV | Image classification, detection, segmentation, generation | references/knowledge/cv/ |
| Time Series | Forecasting, anomaly detection, sequence modeling | references/knowledge/time-series/ |
| Tabular | Feature engineering, traditional ML, structured data | references/knowledge/tabular/ |
| Multimodal | Cross-modal tasks, vision-language models | references/knowledge/multimodal/ |
File Organization Structure: One independent markdown file per competition, categorized into corresponding directories by domain.
Example:
time-series/birdclef-plus-2025.mdnlp/aimo-2-2025.md
Quick Reference
To learn from a competition:
- Provide the Kaggle competition URL
- The kaggle-miner agent will extract the winning solution
- Knowledge is automatically added to the relevant category
- Detailed Technical Analysis of Top Solutions (Front-runner Detailed Technical Analysis) is automatically included
To browse existing knowledge:
- Browse the relevant domain directory:
references/knowledge/[domain]/ - One independent file per competition, containing:
- Competition Brief
- Detailed Technical Analysis of Top Solutions (Detailed Technical Analysis of Top Solutions) ⭐
- Code Templates
- Best Practices
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
Each time knowledge is extracted from a Kaggle competition,mustinclude the following standard sections:
Required Content Checklist
| Section | Description | Requirement |
|---|---|---|
| Competition Brief | Competition background, task description, data scale, evaluation metrics | ✅ Required |
| Original Summaries | Brief overview of top solutions | ✅ Required |
| Detailed Technical Analysis of Top Solutions | Core techniques and implementation details of Top 20 solutions | ✅ Required ⭐ |
| Code Templates | Reusable code templates | ✅ Required |
| Best Practices | Best practices and common pitfalls | ✅ Required |
| Metadata | Data source tags and dates | ✅ Required |
Format for Detailed Technical Analysis of Top Solutions
Each top solution should include:
- Ranking and team/author
- List of core techniques (3-6 key technical points)
- Implementation details (specific parameters, configurations, data)
Example format:
**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
It is recommended to cover Top 20 solutions to capture more innovative techniques from top contestants
Additional Resources
Knowledge Directories
references/knowledge/nlp/- NLP competition techniquesreferences/knowledge/cv/- Computer vision techniquesreferences/knowledge/time-series/- Time series methodsreferences/knowledge/tabular/- Tabular data approachesreferences/knowledge/multimodal/- Multimodal solutions
Competition Examples
- BirdCLEF+ 2025 (
time-series/birdclef-plus-2025.md) - Includes detailed technical analysis of the complete Top 14 top solutions - BirdCLEF 2024 (
time-series/birdclef-2024.md) - Includes detailed technical analysis of Top 3 solutions - AIMO-2 (
nlp/aimo-2-2025.md) - Includes technical summary of Top 12+ top solutions