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/README.md

View on GitHub
# Competitions

Research a competition, then run it: status, data, submissions, scores.
Hackathons are in [hackathons/README.md](hackathons/README.md).

## Research (no credential for a public competition)

```bash
python3 scripts/kaggle_skill.py brief titanic
python3 scripts/kaggle_skill.py pages titanic
python3 scripts/kaggle_skill.py pages titanic --page evaluation
```

- `brief` is one screen: metric, deadline with the time left, prize, team
  size, daily submission limit, whether it is a code competition, whether it
  awards medals, how much data there is, and the names of its pages. With a
  credential it adds whether you have entered and your rank.
- `pages` lists the pages with their sizes. `--page NAME` prints one as text
  (part of the name is enough); a page longer than 12,000 characters is cut
  with a note, and `--max-chars 0` prints all of it. `--all` prints every
  page, `--raw` keeps the stored HTML or Markdown.

Start with `brief`. A rules page alone is 6,000 to 9,000 tokens, so read a
page only when the question needs it.

## Find competitions (credential)

```bash
python3 scripts/kaggle_skill.py competitions --days 30
python3 scripts/kaggle_skill.py competitions --mine
python3 scripts/kaggle_skill.py competitions --category featured,research --status active
python3 scripts/kaggle_skill.py details titanic --top 10
```

- `competitions` prints two lines per competition: the deadline and the
  title, then the slug, category, teams, prize and metric. Community
  competitions with fewer than ten teams are left out unless `--min-teams`
  says otherwise. `--search TEXT`, `--limit N`. The competitions you have
  entered are marked, unless `KAGGLE_SKILL_HIDE_ACCOUNT=1` is set.
- `details` prints the data files with sizes, the top of the leaderboard and
  the most-voted notebooks. A lookup that fails is reported and the others
  are still printed.

## Where you stand (credential)

```bash
python3 scripts/kaggle_skill.py status rsna-knee-abnormality-detection
python3 scripts/kaggle_skill.py leaderboard rsna-knee-abnormality-detection
```

- `status`: the deadline, your rank, submissions made today and left, the
  submissions still being scored, your best and latest scores, and this
  week's GPU and TPU hours. Facts only.
- `leaderboard`: the top rows, your row with the gap to the leader, and the
  score at each medal line when the competition awards medals. Each run saves
  a snapshot under `./.kaggle-skill/leaderboard/`, and the next run says what
  moved. The public leaderboard is not the final one; after the deadline,
  `--private` shows the one that decides the final ranks.

## Data

```bash
python3 scripts/kaggle_skill.py download titanic ./data --unzip
python3 scripts/kaggle_skill.py download titanic --file train.csv
```

Needs the Kaggle CLI, a credential, and the competition's rules accepted on
kaggle.com. The total size is read first and a download above `--max-gb`
(default 20) is refused: some competitions hold hundreds of gigabytes.
`--unzip` extracts archives and refuses any member that would land outside
the folder.

## Submit

```bash
python3 scripts/kaggle_skill.py validate titanic ./submission.csv
python3 scripts/kaggle_skill.py submit titanic ./submission.csv -m "baseline" --expect 0.77
python3 scripts/kaggle_skill.py submit titanic ./submission.csv -m "baseline" --expect 0.77 --yes
python3 scripts/kaggle_skill.py watch titanic
python3 scripts/kaggle_skill.py ledger
```

- `validate` compares a CSV with the sample submission: columns, row count,
  ids, empty values, non-finite numbers. An empty value in a text column the
  sample never leaves empty is a warning (WARN), since some competitions take
  an empty prediction. It checks the shape, not the predictions.
- `submit` without `--yes` runs validate's checks on the file, prints what
  would be sent and how many submissions are left today, and stops. With
  `--yes` it submits and adds a line to
  `./.kaggle-skill/ledger.jsonl`. A code competition takes
  `--notebook OWNER/NAME --version N` instead of a file.
- `watch` waits until the submission is scored, prints the score, records it,
  and reports the difference from `--expect`. `--ref ID` watches another of
  your submissions; one that is not among your latest 100 in the competition
  is shown but not recorded, since it may belong to another competition.
- `ledger` shows the record.

Submit only after the user confirms. Read
[competition-operations.md](references/competition-operations.md) first.

The ledger and the leaderboard snapshots are plain files in
`./.kaggle-skill/`, in the folder the commands are run from. They are local
records: nothing reads them but these commands. A project that should not
carry them can list `.kaggle-skill/` in its `.gitignore`.

## Simulation competitions

```bash
python3 scripts/kaggle_skill.py episodes 56699264
python3 scripts/kaggle_skill.py episodes --replay 117015562
python3 scripts/kaggle_skill.py episodes --logs 117015562 --agent 0
```

The first lists a submission's games with rewards and opponents. The other
two save a replay or your agent's log under `./downloads/episodes/`.

## Scripts

`scripts/competition_brief.py`, `competition_pages.py`, `list_competitions.py`,
`competition_details.py`, `competition_status.py`,
`competition_leaderboard.py`, `competition_download.py`,
`competition_validate.py`, `competition_submit.py`, `competition_watch.py`,
`competition_ledger.py`, `competition_episodes.py`. Each answers `--help`.

## References

- [competition-operations.md](references/competition-operations.md): before
  and after a submission
- [competition-research.md](references/competition-research.md)
- [competition-overview.md](references/competition-overview.md)
- [competition-categories.md](references/competition-categories.md)
- [hackathon-endpoints.md](hackathons/references/hackathon-endpoints.md)
- [episode-endpoints.md](hackathons/references/episode-endpoints.md)
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