skilld
All skills
shepsci avatar

/kaggle

@256664c
by Shep Scientificshepsci/kaggle-skill95 stars
8

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.

Ask your Agent

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

This session only. Nothing lands on disk.

modulesbenchmarksreferencesbenchmark-endpoints.md

≈483 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Benchmark Endpoints

Two MCP tools, both in the AGI/evaluation surface.

create_benchmark_task_from_prompt — ✅ PASS

Create a new benchmark task on Kaggle from a prompt + assertion.

Parameters:

  • taskDescription (string) — natural-language description of what the task is
  • assertionDescription (string) — natural-language description of how to score

Returns: an object with kernel_url pointing at the created benchmark task.

from skills.kaggle.shared.mcp_client import mcp_call, resolve_token

token = resolve_token()
resp = mcp_call("create_benchmark_task_from_prompt", {
    "taskDescription": "Compute the Fibonacci sequence up to n=20",
    "assertionDescription": "Output must be a comma-separated list matching the canonical sequence",
}, token=token)

get_benchmark_leaderboard — ✅ PASS (was 🔒 BLOCKED)

Read the leaderboard for an existing benchmark.

Parameters:

  • benchmarkSlug (string)
  • ownerSlug (string)

Auth: Was permission-gated in the 2026-04-22 audit. Verified PASS in the 2026-05-04 retest with an ordinary KGAT token — no elevated access needed. A non-existent benchmark/owner pair returns a not-found error rather than a permission denial; treat both as data-not-available and surface the response.

resp = mcp_call("get_benchmark_leaderboard", {
    "benchmarkSlug": "some-benchmark",
    "ownerSlug": "owner-handle",
}, token=token)

When to use which

  • Creating tasks for evaluation runs → create_benchmark_task_from_prompt. Returns a kernel_url — keep it; that's how downstream submissions reference the task.
  • Reading leaderboard data for a hackathon writeup that links to a benchmark → get_benchmark_leaderboard. Works with an ordinary KGAT token as of 2026-05-04. If the response is empty / not-found, surface that as evidence rather than silently falling back to scraping.

Source: SKILL.md on GitHub

Third-party checks

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

Provenance

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

Capability

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