agentleFS
Sign inStart free
shkodnik1917shkodnik1917/claude-brainlab/skills/kaggle-learner/SKILL.md

kaggle-learner

Skill35 starsChanged 2 months agoMITView on GitHub

Extracts reusable ML techniques, code patterns, and feature engineering ideas from Kaggle competition winning solutions and maps where they apply. Use when the user shares a Kaggle competition, asks to learn from top solutions, or wants competition tricks for their own model or pipeline.

3 other projects use a version of this, 2 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when:

    line 17
  2. Distinctive:

    Every time knowledge is extracted from a Kaggle competition, must include the following standard sections:

    line 61

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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/

File structure: one markdown file per competition, organized by domain directory.

Examples:

  • 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. Front-runner Detailed Technical Analysis is automatically included

To browse existing knowledge:

  • Browse the relevant domain directory: references/knowledge/[domain]/
  • Each competition has one file containing:
    • Competition Brief
    • Front-runner Detailed Technical Analysis ⭐
    • 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

Every time knowledge is extracted from a Kaggle competition, must include the following standard sections:

Required Content Checklist

SectionDescriptionRequired
Competition BriefBackground, task description, data scale, evaluation metric✅ Required
Original SummariesBrief overview of top solutions✅ Required
Front-runner Detailed Technical AnalysisCore techniques and implementation details for top 20 solutions✅ Required ⭐
Code TemplatesReusable code templates✅ Required
Best PracticesBest practices and common pitfalls✅ Required
MetadataData source tags and date✅ Required

Front-runner Detailed Technical Analysis Format

Each front-runner solution should include:

  • Rank and team/author
  • Core techniques list (3-6 key technical points)
  • Implementation details (specific parameters, configs, data)

Example format:

**Rank Place - Core Technique Name (Author)**

Core techniques:
- **Technique 1**: brief description
- **Technique 2**: brief description

Implementation details:
- Specific parameters, models, configs
- Data and experimental results

Recommended to cover Top 20 solutions to capture more innovative techniques from top competitors

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) - Complete Top 14 front-runner detailed technical analysis
  • BirdCLEF 2024 (time-series/birdclef-2024.md) - Top 3 solutions detailed technical analysis
  • AIMO-2 (nlp/aimo-2-2025.md) - Top 12+ front-runner technical summary

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free