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/benchmarks/references/benchmark-endpoints.md
View on GitHub# Benchmark Endpoints
The Kaggle MCP server has two benchmark tools. Arguments go inside a `request`
object; see [mcp-reference.md](../../references/mcp-reference.md).
## `get_benchmark_leaderboard` (read)
Reads the leaderboard of a published benchmark. It needs no credential.
Checked on 2026-09-30.
| Argument | Meaning |
|---|---|
| `ownerSlug` | The benchmark's owner, for example `kaggle` |
| `benchmarkSlug` | The benchmark, for example `icml-2025-experts` |
| `versionNumber` | Optional |
The answer has `rows`, one per model version, each with `model_version_name`,
`model_version_slug`, and `task_results`. A benchmark that does not exist
gives `Not found`.
```python
import sys
sys.path.insert(0, ".") # run from the skill folder
from shared.mcp_client import classify_result, extract_json, mcp_call
response = mcp_call(
"get_benchmark_leaderboard",
{"request": {"ownerSlug": "kaggle", "benchmarkSlug": "icml-2025-experts"}},
)
if classify_result(response) == "ok":
for row in extract_json(response)["rows"][:5]:
print(row["model_version_name"])
```
The Kaggle CLI has the same data: `kaggle benchmarks leaderboard
kaggle/icml-2025-experts --show`.
## `create_benchmark_task_from_prompt` (write)
Creates a benchmark task on the account from two texts: `taskDescription` and
`assertionDescription`. It was not called for this reference, because it
changes the account. Ask the user before using it, and say that it creates a
task and a backing notebook.
For writing tasks in code, use `kaggle benchmarks tasks push` with a task
file; see [benchmarks-cli.md](benchmarks-cli.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 |