shepsci/kaggle-skill / skills/kaggle
kaggle
FlaggedUnified 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.
modules/badges/README.md
View on GitHub# Badges
Badge inventory, dry run, phases, and the streak helper.
```bash
python3 modules/badges/scripts/orchestrator.py --dry-run
python3 modules/badges/scripts/orchestrator.py --status
python3 modules/badges/scripts/orchestrator.py --phase 1
python3 modules/badges/scripts/orchestrator.py --resume
```
Always run `--dry-run` first and get the user's go-ahead before a phase.
## What a phase does to the account
| Phase | Actions |
|---|---|
| 1 | Pushes notebooks, creates datasets and models. All private, named `kaggle-badges-...` |
| 2 | Submits to Titanic, and to one playground and one community competition that the CLI lists at that time |
| 3 | Pushes notebooks, waits for the runs, creates a dataset and a model from the output |
| 4 | Nothing. It prints the steps to do on kaggle.com |
| 5 | Lists datasets and submits to Titanic once, then writes a daily script you can schedule yourself |
Submissions use the day's submission slots, and notebook runs use quota.
## Progress
- `earned` means the action that earns the badge completed. The scripts cannot
see your profile; check it for the badge itself.
- `skipped` means there is a manual step. The reason is shown by `--status`.
- Streak badges stay `attempting`. Run `--resume` each day; without it, a
badge left as `attempting` or `skipped` is not tried again.
- Progress is saved in `badge-progress.json` in the skill folder. Set
`KAGGLE_BADGES_STATE_DIR` to keep it, and the scratch files, somewhere else.
Nothing here posts comments or votes.
## References
- [badge-catalog.md](references/badge-catalog.md)
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 119k | Updated | Claude CodeCodex | Verified | Install |
| 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: 119k | Updated | Claude CodeCodex | Verified | Install |
| 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: 118k | Updated | Claude CodeCodex | Verified | Install |
| 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: 118k | Updated | Claude CodeCodex | Verified | Install |