Skip to content

shepsci/kaggle-skill / skills/kaggle

kaggle

Flagged

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.

FileKindSize
SKILL.mdskill md10.3 KB
modules/README.mdmarkdown2.3 KB
modules/badges/README.mdmarkdown1.6 KB
modules/badges/references/badge-catalog.mdmarkdown6.6 KB
modules/badges/scripts/badge_registry.pyscript8.5 KB
modules/badges/scripts/badge_tracker.pyscript4.1 KB
modules/badges/scripts/orchestrator.pyscript5.3 KB
modules/badges/scripts/phase_1_instant_api.pyscript24.0 KB
modules/badges/scripts/phase_2_competition.pyscript13.5 KB
modules/badges/scripts/phase_3_pipeline.pyscript11.7 KB
modules/badges/scripts/phase_4_browser.pyscript2.2 KB
modules/badges/scripts/phase_5_streaks.pyscript5.6 KB
modules/badges/scripts/templates/README_dataset.mdmarkdown573 B
modules/badges/scripts/templates/dataset-metadata.jsonconfig871 B
modules/badges/scripts/templates/kernel-metadata.jsonconfig412 B
modules/badges/scripts/templates/model-instance-metadata.jsonconfig253 B
modules/badges/scripts/templates/model-metadata.jsonconfig355 B
modules/badges/scripts/templates/python_notebook.ipynbother1.3 KB
modules/badges/scripts/templates/r_notebook.ipynbother1.1 KB
modules/badges/scripts/templates/submission_titanic.csvother2.8 KB
modules/badges/scripts/templates/utility_script.pyscript802 B
modules/badges/scripts/utils.pyscript3.9 KB
modules/benchmarks/README.mdmarkdown1.2 KB
modules/benchmarks/references/benchmark-endpoints.mdmarkdown1.6 KB
modules/benchmarks/references/benchmarks-cli.mdmarkdown4.4 KB
modules/competitions/README.mdmarkdown5.8 KB
modules/competitions/hackathons/README.mdmarkdown2.9 KB
modules/competitions/hackathons/references/episode-endpoints.mdmarkdown2.2 KB
modules/competitions/hackathons/references/hackathon-endpoints.mdmarkdown4.6 KB
modules/competitions/hackathons/scripts/fetch_writeup.pyexecutablescript10.5 KB
modules/competitions/hackathons/scripts/hackathon_overview.pyexecutablescript1.5 KB
modules/competitions/hackathons/scripts/list_writeups.pyexecutablescript9.9 KB
modules/competitions/references/competition-categories.mdmarkdown2.1 KB
modules/competitions/references/competition-operations.mdmarkdown5.7 KB
modules/competitions/references/competition-overview.mdmarkdown3.9 KB
modules/competitions/references/competition-research.mdmarkdown3.0 KB
modules/competitions/scripts/competition_brief.pyscript5.4 KB
modules/competitions/scripts/competition_details.pyscript8.2 KB
modules/competitions/scripts/competition_download.pyscript5.1 KB
modules/competitions/scripts/competition_episodes.pyscript9.2 KB
modules/competitions/scripts/competition_leaderboard.pyscript12.3 KB
modules/competitions/scripts/competition_ledger.pyscript3.3 KB
modules/competitions/scripts/competition_pages.pyexecutablescript1.7 KB
modules/competitions/scripts/competition_status.pyscript9.0 KB
modules/competitions/scripts/competition_submit.pyscript8.9 KB
modules/competitions/scripts/competition_validate.pyscript14.2 KB
modules/competitions/scripts/competition_watch.pyscript5.9 KB
modules/competitions/scripts/list_competitions.pyscript13.3 KB
modules/datasets/README.mdmarkdown2.1 KB
modules/datasets/references/kagglehub-datasets.mdmarkdown2.6 KB
modules/datasets/scripts/dataset_download.pyscript4.1 KB
modules/datasets/scripts/dataset_publish.pyscript5.5 KB
modules/discussions/README.mdmarkdown2.1 KB
modules/discussions/references/writeups.mdmarkdown5.8 KB
modules/discussions/scripts/forums.pyscript22.0 KB
modules/discussions/scripts/leaderboard_writeups.pyscript24.8 KB
modules/models/README.mdmarkdown2.6 KB
modules/models/references/kagglehub-models.mdmarkdown1.7 KB
modules/models/scripts/model_download.pyscript4.5 KB
modules/models/scripts/model_publish.pyscript8.7 KB
modules/notebooks/README.mdmarkdown2.6 KB
modules/notebooks/scripts/notebook_push.pyscript5.7 KB
modules/notebooks/scripts/notebook_run.pyscript2.8 KB
modules/notebooks/scripts/notebook_wait.pyscript3.7 KB
modules/references/README.mdmarkdown454 B
modules/references/cli-reference.mdmarkdown13.4 KB
modules/references/kaggle-knowledge.mdmarkdown7.6 KB
modules/references/mcp-reference.mdmarkdown18.9 KB
modules/setup/README.mdmarkdown3.0 KB
modules/setup/references/kaggle-setup.mdmarkdown6.7 KB
modules/setup/scripts/check_all_credentials.pyscript5.7 KB
modules/setup/scripts/doctor.pyscript10.2 KB
modules/setup/scripts/save_credentials.pyscript3.9 KB
scripts/kaggle_skill.pyscript11.5 KB
shared/__init__.pyscript0 B
shared/competition.pyscript20.0 KB
shared/credentials.pyscript9.6 KB
shared/hub.pyscript2.9 KB
shared/kaggle_cli.pyscript20.7 KB
shared/ledger.pyscript3.6 KB
shared/mcp_client.pyscript11.6 KB
shared/net.pyscript6.9 KB
shared/notebook.pyscript4.4 KB
shared/preflight.pyscript5.1 KB
shared/safe_extract.pyscript2.7 KB
shared/script.pyscript11.2 KB
shared/text.pyscript10.5 KB
shared/untrusted.pyscript7.6 KB

modules/competitions/scripts/competition_download.py

View on GitHub
#!/usr/bin/env python3
"""Download the data of a Kaggle competition.

    competition_download.py titanic                    into ./downloads/titanic
    competition_download.py titanic ./data --unzip
    competition_download.py titanic --file train.csv

Uses the Kaggle CLI, so it needs the CLI and a credential, and the
competition's rules must have been accepted on kaggle.com: there is no command
for that.

Before a full download the total size is read from Kaggle. Data above
--max-gb (default 20) is not downloaded: some competitions hold hundreds of
gigabytes. Fetch single files with --file, or raise the limit on purpose.

--unzip extracts the archives with a path check (the CLI has no --unzip for
competition downloads). File names come from the host, so the listing is
printed as untrusted content.
"""

from __future__ import annotations

import argparse
import sys
import zipfile
from pathlib import Path

SKILL_ROOT = Path(__file__).resolve().parents[3]
sys.path.insert(0, str(SKILL_ROOT))

from shared import (  # noqa: E402
    competition,
    credentials,
    kaggle_cli,
    mcp_client,
    safe_extract,
    script,
    text,
    untrusted,
)

DEFAULT_MAX_GB = 20.0


def data_size(slug: str) -> tuple[int, int] | None:
    """``(files, bytes)`` of the competition's data, or None when Kaggle does not say."""
    result = mcp_client.request(
        "get_competition_data_files_summary", {"competitionName": slug}, token=""
    )
    info = result.data.get("file_summary_info") if isinstance(result.data, dict) else None
    if not result.ok or not isinstance(info, dict):
        return None
    try:
        total = sum(int(t.get("total_size") or 0) for t in info.get("file_types") or [])
        return int(info.get("total_file_count") or 0), total
    except (TypeError, ValueError, AttributeError):
        return None


def main(argv: list[str] | None = None) -> int:
    parser = argparse.ArgumentParser(
        description="Download the data of a Kaggle competition.",
        epilog="Needs the Kaggle CLI, a credential, and the competition's rules accepted.",
    )
    script.add_competition(parser, "dir?")
    parser.add_argument("--file", metavar="NAME", help="Download only this file")
    parser.add_argument(
        "--unzip", action="store_true", help="Extract downloaded archives, with a path check"
    )
    parser.add_argument(
        "--max-gb",
        type=float,
        default=DEFAULT_MAX_GB,
        metavar="N",
        help=f"Refuse a full download above N gigabytes (default: {DEFAULT_MAX_GB:g})",
    )
    args = script.parse(parser, argv)
    slug, folder = script.positionals(parser, args, "dir?")
    target = Path(folder or Path("downloads") / slug)

    credentials.load_configured_env_file()
    if not kaggle_cli.installed():
        return script.missing_package("kaggle", "downloading competition data")
    if credentials.resolve() is None:
        return script.no_credential("downloading competition data")

    if not args.file:
        size = data_size(slug)
        if size is None:
            script.warn("Kaggle did not report the size of the data; downloading without a check")
        else:
            files, total = size
            print(f"The data of {slug}: {files:,} files, {text.human_size(total)}.")
            if total > args.max_gb * 1e9:
                print(
                    f"error: that is above the {args.max_gb:g} GB limit, so nothing was "
                    "downloaded.\n"
                    "       Download one file with --file NAME, or raise the limit with "
                    f"--max-gb {total / 1e9 + 1:.0f}.",
                    file=sys.stderr,
                )
                return script.EXIT_REFUSED

    target.mkdir(parents=True, exist_ok=True)
    cli_args = ["competitions", "download", slug, "--path", str(target), "--quiet"]
    if args.file:
        cli_args += ["--file", args.file]
    status = kaggle_cli.run_wrapped(cli_args, tool="competitions.download")
    if status != 0:
        if status == script.EXIT_DENIED:
            print(
                f"Kaggle refused. Accept the rules first: {competition.url(slug)}/rules",
                file=sys.stderr,
            )
        return status

    if args.unzip:
        extracted = 0
        archives = sorted(target.glob("*.zip"))
        for archive in archives:
            try:
                names = safe_extract.safe_extract(archive, target)
            except safe_extract.UnsafeArchiveError as exc:
                print(f"error: refusing to extract: {exc.reason}:", file=sys.stderr)
                untrusted.emit_text(
                    exc.member, source="local", tool="safe_extract", file=sys.stderr
                )
                return script.EXIT_REFUSED
            except (zipfile.BadZipFile, OSError) as exc:
                return script.fail(f"could not extract an archive ({type(exc).__name__})")
            extracted += len(names)
        # Archive names can come from Kaggle; the listing below shows them inside a block.
        if archives:
            print(f"Extracted {extracted} file(s) from {len(archives)} archive(s).")

    kaggle_cli.print_folder(target)
    return script.EXIT_OK


if __name__ == "__main__":
    sys.exit(main())
deprecation-and-migrationaddyosmani/agent-skillsManages deprecation and migration. Use when removing old systems, APIs, or features. Use when migrating users from one implementation to another. Use when migrating a database schema in production, such as renaming or dropping a column without downtime (expand/contract). Use when deciding whether to maintain or sunset existing code.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
performance-optimizationaddyosmani/agent-skillsOptimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance regressions, when Core Web Vitals or load times need improvement, when N+1 query patterns need fixing, or when profiling reveals bottlenecks.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
agent-cost-reportthedotmack/claude-memBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json.Stars: 118kUpdated Claude CodeCodexVerifiedInstall
agent-cost-reportthedotmack/claude-memBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json.Stars: 118kUpdated Claude CodeCodexVerifiedInstall