
Kaggle
A comprehensive Kaggle integration that handles everything from account setup to competition submissions through five specialized modules. Built around the kagglehub library and Kaggle's MCP server, it covers dataset downloads, notebook execution, competition reports, hackathon writeup retrieval, and even systematic badge earning across 38+ achievements. The comp-report module can scrape problem statements and evaluation details if your host agent provides Playwright tools, though most overview content works through the Python API alone. Credential handling is well documented with support for both modern API tokens and legacy keys. This is your go-to if you're building Kaggle workflows into an LLM agent and want battle-tested scripts instead of starting from scratch.
- skills.sh installs
- 584
- GitHub stars
- 111
- last updated
- Jun 3, 2026
Install
$ npx -y skills add shepsci/kaggle-skill --skill kaggle --agent claude-codeInstalls into .claude/skills of the current project.
Files
Kaggle
Kaggle for coding agents: competition research, running a competition (status, submissions, scores), datasets, models, notebooks, discussions and solution writeups, benchmarks, and badges.
This is an independent, unofficial project. It is not affiliated with, endorsed by, or sponsored by Kaggle or Google.
Do not use this skill for generic machine learning, GPU, notebook, dataset, model, benchmark, or data-science work unless the user ties the task to Kaggle.
Run a command
Everything is one command with a name:
python3 scripts/kaggle_skill.py <command> [arguments]
python3 scripts/kaggle_skill.py <command> --help
Paths in this file are relative to the skill folder, the one that holds this
SKILL.md. Run every command from the user's working directory as
python3 <skill folder>/scripts/kaggle_skill.py <command>, so that downloads
and records land in the user's project. Do not cd into the skill folder.
Sponsors
Details
- Repository
- github.com/shepsci/kaggle-skill
- First seen
- Jun 3, 2026