All skills
shepsci avatar

/kaggle

@256664c

Unified Kaggle skill. Use when the user explicitly mentions Kaggle, kaggle.com, a Kaggle URL, Kaggle competitions, Kaggle datasets/models/notebooks, Kaggle forums/discussions/writeups, Kaggle benchmarks, hackathons hosted on Kaggle, Kaggle badges, or Kaggle account setup. Do not use for generic ML, GPU/TPU, notebook, dataset, benchmark, or data-science tasks unless the user clearly ties them to Kaggle.

Use this Skill: https://skilld.dev/gh/shepsci/kaggle-skill/kaggle

This session only. Nothing lands on disk.

modulescompetitionsreferencescompetition-categories.md

≈658 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Kaggle Competition Categories

Reference for mapping competition types to API categories.

API Category Mapping

Competition Type API category Value Notes
Featured Prediction featured Standard prize competitions
Research Prediction research Research-oriented, often with novel evaluation
Playground playground Learning-focused, smaller prizes or swag
Getting Started gettingStarted Semi-permanent tutorials (Titanic, Housing, etc.)
Recruitment recruitment Company-sponsored talent search
Masters masters Restricted to Masters/Grandmasters tier
Simulation featured Tags contain "simulation"; uses agent-based eval
Game Arena featured or all Tags contain "game" or "arena"
Featured Hackathon featured Tags contain "hackathon"; shorter duration
Community (varies) Catch-all; query category="" minus known types

Identifying Special Types

Some competition types share the featured category but can be distinguished by tags:

  • Simulation: Look for tags like simulation, agent, game-theory
  • Game Arena: Look for tags like game, arena, multi-agent
  • Hackathon: Look for tags like hackathon; also tend to have deadlines < 7 days from launch. Hackathons are classified as active until winners are announced (no leaderboard — results appear on a Winners tab after judging, often weeks/months after deadline)
  • Code competitions: Check isKernelsSubmissionsOnly == true

Notes on Getting Started Competitions

Getting Started competitions (Titanic, Housing Prices, Digit Recognizer, etc.) are semi-permanent and don't have meaningful "launch" or "completion" dates. They should generally be excluded from "recently launched" reports unless specifically requested.

Querying Strategy

  1. Query each specific category (featured, research, playground, etc.) with sort_by=recentlyCreated to get the latest in each bucket.
  2. Also query with no category filter (empty string) to catch competitions that may not appear under specific categories.
  3. Deduplicate by slug since the same competition may appear in multiple queries.

Source: SKILL.md on GitHub

1 alert16d5 checks · Risk SAFE
  • Gen Agent Trust Hub16d

    The 'kaggle' skill is a comprehensive and secure integration for Kaggle platform operations. It implements multiple security best practices, including credential masking, restrictive file permissions, and protection against token leakage to third-party sites. It also handles untrusted user-generated content from forums using explicit boundary markers to prevent prompt injection.

  • Socket16d

    No alerts

  • Snyk16d

    Risk: MEDIUM · 1 issue

  • Runlayer6mo

    28/45 files flagged

  • ZeroLeaks5mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at 256664c. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 2 months ago.

Activeupdated 3 months ago
homepage
https://github.com/shepsci/kaggle-skill
All 1 allowed tools
Bash Read WebFetch Grep Glob
Other metadata
compatibility
Python 3.11+, pip packages kagglehub>=1.0.0, kaggle>=2.2.3, kagglesdk>=0.1.33,<1.0, requests, python-dotenv. Optional: playwright for browser badges; kaggle-benchmarks for local benchmark task authoring. The competitions module's SPA-scraping steps assume Playwright MCP tools are provided by the host agent; the skill itself does not bundle them.
metadata
{
  "author": "shepsci",
  "version": "2.4.0",
  "primaryEnv": "KAGGLE_API_TOKEN",
  "openclaw": {
    "requires": {
      "bins": [
        "python3",
        "pip3"
      ],
      "env": [
        "KAGGLE_API_TOKEN"
      ]
    }
  }
}

README badge

README badge for shepsci/kaggle-skill