kaggle agent skill by shepsci
Handles Kaggle tasks when explicitly requested, covering competitions, datasets, models, notebooks, forums, benchmarks, hackathons, badges, and account setup.
- Publisher
- shepsci
- License
- MIT
- Installs via skills.sh
- 581
- Bundled scripts
- 52 files
- Credentials
- KAGGLE_API_TOKEN, KAGGLE_MCP_TOKEN, KAGGLE_TOKEN
- Outside hosts
- www.kaggle.com
- MCP server
- Yes
- Security scan
- Not scanned by the directory. Third-party audits on skills.sh
- Listed since
- October 19, 2026 or earlier
At a glance
| Publisher | shepsci |
|---|---|
| Repository | github.com/shepsci/kaggle-skill |
| Category | Data, Analytics and Databases |
| Topics | Data Analysis, Machine Learning, Notebooks |
| Cost | Free skill, needs a service |
| Capabilities | Quality badge, Bundles scripts, Declares tool permissions, Declares compatibility, Uses an MCP server, Needs an API key or account, Calls outside services |
| License | MIT |
| Last commit | October 3, 2026 (repository) |
| Listed since | October 19, 2026 or earlier |
| SKILL.md | 183 lines, 1,456 words |
| Bundled files | 88 files, including scripts |
| Quality score | 90/100 · A Passes all seven graded checks |
| Security scan | Not scanned |
| README badge | Get the badges for this listing |
Before you install
Read from the skill's files at the directory's October 22, 2026 snapshot: what ships with it, what its code reads, and the terms it is published under.
- Bundled scripts: 52 script files (52 Python). Your agent may run them, so read them first.
- Environment variables its scripts read:
KAGGLE_API_TOKEN,KAGGLE_MCP_TOKEN,KAGGLE_TOKEN. Check SKILL.md for which ones it needs. - Network: its scripts use an HTTP client or a cloud SDK, and name
www.kaggle.com. - MCP: SKILL.md mentions an MCP server.
- Tool permissions requested:
Read Grep Glob(theallowed-toolsfield of SKILL.md). - License: MIT, an open-source or open-content license.
Install kaggle
The skills CLI works with Claude Code, Codex, Cursor and other agents; the other routes copy the folder by hand.
npx skills add https://github.com/shepsci/kaggle-skill/tree/main/skills/kaggle
tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/shepsci/kaggle-skill.git "$tmp/repo"
mkdir -p .claude/skills
cp -R "$tmp/repo/"skills/kaggle .claude/skills/
rm -rf "$tmp"
tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/shepsci/kaggle-skill.git "$tmp/repo"
mkdir -p .agents/skills
cp -R "$tmp/repo/"skills/kaggle .agents/skills/
rm -rf "$tmp"
For a user-level install, copy the folder to ~/.claude/skills/ (Claude Code) or ~/.agents/skills/ (Codex). Inside Codex, $skill-installer can also fetch a skill from GitHub. New to skills? Read How to install agent skills in Claude Code, Codex and Cursor.
shepsci/kaggle-skill is third-party code. Read SKILL.md and any bundled scripts before you install it.
Directory summary
kaggle handles Kaggle tasks when explicitly requested, covering competitions, datasets, models, notebooks, forums, benchmarks, hackathons, badges, and account setup. Listed in Data, Analytics and Databases, it is built for Claude Code users working on data, analytics and databases. It scores 90/100, grade A, on the Suede Skill Check, with full points for structural checks, recent maintenance and instruction depth. shepsci publishes it under MIT, an open-source or open-content license, so you can use and adapt it at no cost under those terms. It installs in Claude Code, Codex, Cursor and other agents that read the Agent Skills format.
How the author describes it
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.
From the description field of SKILL.md. Agents read this line to decide when to load the skill.
Compatibility, from SKILL.md
| Compatibility | Python 3.11+. Public reads need nothing else. Downloads, submissions, notebooks and publishing need the pip packages kaggle>=2.2.4 and kagglehub>=1.0.2. Optional: kaggle-benchmarks>=0.6 for writing… |
|---|
Sections in SKILL.md
- Run a command
- Pick the command
- Before any action that changes the account
- Reading the output
- Credentials
- Exit codes
- References
Files in the skill folder
SKILL.mdmodules/README.mdmodules/badges/README.mdmodules/badges/references/badge-catalog.mdmodules/badges/scripts/badge_registry.pymodules/badges/scripts/badge_tracker.pymodules/badges/scripts/orchestrator.pymodules/badges/scripts/phase_1_instant_api.pymodules/badges/scripts/phase_2_competition.pymodules/badges/scripts/phase_3_pipeline.pymodules/badges/scripts/phase_4_browser.pymodules/badges/scripts/phase_5_streaks.pymodules/badges/scripts/templates/README_dataset.mdmodules/badges/scripts/templates/dataset-metadata.jsonmodules/badges/scripts/templates/kernel-metadata.jsonmodules/badges/scripts/templates/model-instance-metadata.jsonmodules/badges/scripts/templates/model-metadata.jsonmodules/badges/scripts/templates/python_notebook.ipynbmodules/badges/scripts/templates/r_notebook.ipynbmodules/badges/scripts/templates/submission_titanic.csvmodules/badges/scripts/templates/utility_script.pymodules/badges/scripts/utils.pymodules/benchmarks/README.mdmodules/benchmarks/references/benchmark-endpoints.md
Showing 24 of 88 files. Browse the folder on GitHub.
Suede Skill Check: 90/100 · A
Report snapshot · · graded-v2
The rubric totals 100 points; published scores are capped at 99. Security scan: not scanned.
Source revision: a47bff9830af. Report version dc4e1c26b073. Badge URLs follow the latest listing; save the report to keep this version.
Download report · Request a fresh review
What to review next
- Example request: 0 of 3 points. 3 when the description quotes an example request (3–60 characters in quotation marks).
- Reference files: 0 of 3 points. 3 when the skill folder ships a references/, reference/ or docs/ folder.
Add declarations and bundled files when they describe the skill’s actual needs. Update the source, then request a fresh review with the changed commit or PR.
kaggle passes the required frontmatter check and all seven graded checks, which cover the SKILL.md format, a declared license and a commit in the last year. Those checks earn 56 of the score’s points; the rest come from description quality, instruction depth, bundled files, maintenance and curated-list citations. How the score works.
See the checks and points
| Check | Result |
|---|---|
| Frontmatter parses and declares a name and a description | Pass |
| Name uses lowercase letters, digits and hyphens, 64 characters or fewer | Pass |
| Name matches the skill's folder name | Pass |
| Description is between 50 and 1,024 characters | Pass |
| Description says when an agent should use the skill | Pass |
| SKILL.md body is 500 lines or fewer | Pass |
| A license is declared in the frontmatter or the repository | Pass |
| Repository has a commit in the last 12 months | Pass |
| Score component | Points |
|---|---|
| Structural checks | 56 of 56 |
| Description length | 5 of 5 |
| Boundary clause | 4 of 4 |
| Example request | 0 of 3 |
| Instruction depth | 7 of 7 |
| Reference files | 0 of 3 |
| Bundled scripts | 2 of 2 |
| Recent maintenance | 9 of 9 |
| Curated-list citations | 3 of 7 |
| Tool permissions declared | 2 of 2 |
| Compatibility declared | 2 of 2 |
Where this skill is cited
shepsci/kaggle-skill appears in 2 curated lists: BehiSecc/awesome-claude-skills, heilcheng/awesome-agent-skills.
Strengths and open points
What it does well
- Full points for structural checks (56 of 56).
- Full points for recent maintenance (9 of 9).
- Full points for instruction depth (7 of 7).
- Full points for description length (5 of 5).
- Full points for boundary clause (4 of 4).
- Full points for bundled scripts (2 of 2).
- Full points for tool permissions declared (2 of 2).
- Full points for compatibility declared (2 of 2).
- Its repository is cited by 2 curated lists.
What to check
- Example request: 0 of 3 points.
- Reference files: 0 of 3 points.
- Needs KAGGLE_API_TOKEN, KAGGLE_MCP_TOKEN and KAGGLE_TOKEN set in your environment.
- Connects to an MCP server you configure separately.
- Security scan: not scanned by the directory. Read SKILL.md and any scripts before you install.
Reviews and ratings
Directory rating: 90/100 · A on the Suede Skill Check, computed from the skill's published files.
Used kaggle? Reader reviews are published on GitHub as issues credited to their authors. They never change the score.
Questions and answers
What does kaggle do?
Handles Kaggle tasks when explicitly requested, covering competitions, datasets, models, notebooks, forums, benchmarks, hackathons, badges, and account setup. It is listed in Data, Analytics and Databases on SuedeAI.directory.
Is kaggle free?
The skill is free under MIT. Its files reads KAGGLE_API_TOKEN, KAGGLE_MCP_TOKEN and KAGGLE_TOKEN, mentions an MCP server and names www.kaggle.com, so the service it talks to may need an account or a paid plan.
How do I install kaggle?
Run npx skills add https://github.com/shepsci/kaggle-skill/tree/main/skills/kaggle from your project, or copy the folder into .claude/skills/ for Claude Code or .agents/skills/ for Codex. The install section lists each route.
Does kaggle need an API key or MCP server?
Yes. At the October 22, 2026 snapshot its files reads KAGGLE_API_TOKEN, KAGGLE_MCP_TOKEN and KAGGLE_TOKEN, mentions an MCP server and names www.kaggle.com. The Before you install section lists the details.
How good is kaggle?
It scores 90/100, grade A, on the Suede Skill Check, which adds structure, description quality, instruction depth, bundled files, maintenance and curated-list citations from its published files.
What are alternatives to kaggle?
Skills that share its topics include data-scientist from tronghieu/agent-skills, google-cloud-solution-agentic-analytics-spark-knowledge-catalog from google/skills and pandas-pro from jeffallan/claude-skills.
Similar skills
Skills from other publishers that share the most topics with kaggle.
Read next
More data and database skills
Two badges for kaggle
Choose the numeric badge, the letter badge, or both. Each links to this skill’s Suede AI listing; either valid linked badge can qualify for the feature offer.
[](https://skills.suedeai.ai/directory/shepsci/kaggle-skill/kaggle/)
[](https://skills.suedeai.ai/directory/shepsci/kaggle-skill/kaggle/)<a href="https://skills.suedeai.ai/directory/shepsci/kaggle-skill/kaggle/"><img src="https://skills.suedeai.ai/directory/shepsci/kaggle-skill/kaggle/score.svg" alt="Suede Skill Check: 90/100" width="160" height="175"></a>
<a href="https://skills.suedeai.ai/directory/shepsci/kaggle-skill/kaggle/"><img src="https://skills.suedeai.ai/directory/shepsci/kaggle-skill/kaggle/badge.svg" alt="Suede Skill Check: Grade A" width="160" height="175"></a>Suede Certified on the shield refers to this published structural quality check. Security scan: not scanned. Read the methodology.
Limited-time feature offer: Display either quality badge in your repository or skill README, linked to your listing, then request verification. Suede AI checks the rendered README at a recorded commit. Eligible skills scoring 80–99 with a verified badge can receive a featured placement while the offer is open. Request badge verification.
Publishers: read How to get your agent skill found in search and cited by AI assistants.