nvidia-kaggle-skill

Name: nvidia-kaggle-skill
Author: NVIDIA

264stars24forks

How to install nvidia-kaggle-skill?

nvidia/nvidia-kaggle/nvidia-kaggle-skill

$npx -y skills add NVIDIA/nvidia-kaggle --skill nvidia-kaggle-skill

Installs into the current project.

Summary

Use for Kaggle competition overview fetches, writeups, discussion/kernel research, submissions, and dataset uploads. Not for unrelated ML code.

Files · 1

View on GitHub

SKILL.md

1	# NVIDIA Kaggle Skill
2
3	## Purpose
4
5	Use this skill for Kaggle competition work: context gathering, writeups, discussions, kernels, local reproduction, submission, and dataset upload.
6
7	Do not use it for unrelated ML training, generic notebook editing, general data analysis, or non-Kaggle dataset management unless the user explicitly ties the task to Kaggle.
8
9	## Inputs
10
11	\| Input \| Required \| Description \|
12	\|---\|---\|---\|
13	\| Kaggle slug, URL, writeup URL, kernel ref, or local folder \| Depends on task \| Primary target for the requested Kaggle action. \|
14	\| `KAGGLE_API_TOKEN` \| Required for API/CLI-backed workflows \| KGAT token string for Kaggle API, CLI, and SDK calls. \|
15	\| Disk space \| Required for kernel setup \| Must fit input datasets, competition data, models, and extracted archives. \|
16
17	## Prerequisites
18
19	- Run commands from this skill directory unless a referenced workflow says otherwise.
20	- Install only the runtime packages needed for the requested workflow.
21	- Set `KAGGLE_API_TOKEN` before API, CLI, kernel, discussion, dataset, or submission workflows.
22	- Confirm local disk space before downloading competition data, kernel inputs, or extracted archives.
23	- Require explicit user confirmation before sensitive, externally visible actions: competition submissions (each can consume a daily slot), dataset uploads, and creating a public dataset. Treat `KAGGLE_API_TOKEN` as a secret — never print, log, or echo it.
24
25	## Runtime Dependencies
26
27	Install only the packages needed for the requested task into the current environment, then run scripts with `python`.
28
29	Kaggle API, CLI, kernels, discussions, datasets, competition pages, and writeups:
30
31	```bash
32	if command -v uv >/dev/null 2>&1; then
33	uv pip install httpx kaggle kagglesdk nbformat pydantic python-dotenv rich
34	else
35	python -m pip install httpx kaggle kagglesdk nbformat pydantic python-dotenv rich
36	fi
37	```
38
39	For API/CLI tasks, verify credentials before calling Kaggle:
40
41	```bash
42	: "${KAGGLE_API_TOKEN:?ERROR: KAGGLE_API_TOKEN environment variable is not set}"
43	```
44
45	## Workflows
46
47	Use this workflow catalog to choose the right path. Run the direct script commands for quick tasks. For workflows that point to another markdown file, read that file only when the request needs that workflow.
48
49	Prefer the runtime's `run_script` helper when it exists, for example `run_script("scripts/fetch_competition_info.py", args=["titanic"])`. Otherwise run the equivalent `python ./scripts/<script>.py ...` command from this skill directory.
50
51	### Competition Details
52
53	Use this when the user asks to retrieve or summarize a Kaggle competition overview, rules, evaluation, timeline, or dataset description.
54
55	Fetch overview:
56
57	```bash
58	python ./scripts/fetch_competition_info.py <competition-slug-or-url>
59	```
60
61	Fetch dataset description:
62
63	```bash
64	python ./scripts/fetch_dataset_info.py <competition-slug-or-url>
65	```
66
67	The scripts accept a bare competition slug or `https://www.kaggle.com/competitions/<slug>` URL and extract the slug automatically. Convert output to markdown when the user asks for saved documentation, using `{slug}_competition_overview.md` and `{slug}_dataset_description.md` in the current working directory.
68
69	### Research Brief
70
71	Use this when the user asks you to **research a competition and write a strategy
72	brief** in natural terms (e.g. "research this competition and brief me, with
73	links and a few charts"). You chain the skill's individual research workflows
74	yourself, write your own analysis/plotting code, and produce the brief. Read
75	`./research-brief.md` for the principles that keep the brief accurate, informative,
76	and useful to a reader — how to cite real sources as links, and how to make plots
77	honest and legible (every plotted number traces to what you gathered). These
78	principles live in the skill so the user does not have to spell them out.
79
80	### Writeups
81
82	Use this when the user asks to fetch one writeup, fetch top-k writeups, discover leaderboard writeup links, or summarize solution posts. Read `./writeups.md`.
83
84	### Discussions
85
86	Use this when the user asks for Kaggle competition discussions, community insights, qu

People who liked this also viewed

6 picks

Type

azure-kustoQuery and analyze data in Azure Data Explorer (Kusto/ADX) using KQL for log analytics, telemetry, and time series analysis. WHEN: KQL queries, Kusto database queries, Azure Data Explorer, ADX clustersSkillsJul 2026470k1.3k
lark-base飞书多维表格（Base）操作：建表、字段、记录、视图、统计、公式/lookup、表单、仪表盘、workflow、角色权限；遇到 Base/多维表格/bitable 或 /base/ 链接时使用。文件导入转 lark-drive，认证/授权转 lark-shared。SkillsJul 2026382k16k
lark-calendar飞书日历：管理日历日程和会议室。查看/搜索日程、创建/更新日程、管理参会人、查询忙闲和推荐时段、预定会议室。当用户需要查看日程安排、创建/修改会议、查询/预定会议室时使用。不负责：查询过去的视频会议记录（走 lark-vc）、待办任务（走 lark-task）。SkillsJul 2026380k16k
shadcnManages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. AppliSkillsJul 2026246k120k
xlsxUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.SkillsJul 2026139k163k
firebase-data-connectAgent Skills for FirebaseSkillsJul 2026108k387

nvidia-kaggle-skill

264stars24forks

View on GitHub

How to install nvidia-kaggle-skill?

nvidia/nvidia-kaggle/nvidia-kaggle-skill

$npx -y skills add NVIDIA/nvidia-kaggle --skill nvidia-kaggle-skill

Installs into the current project.

Summary

Use for Kaggle competition overview fetches, writeups, discussion/kernel research, submissions, and dataset uploads. Not for unrelated ML code.

Files · 1

View on GitHub

SKILL.md

1	# NVIDIA Kaggle Skill
2
3	## Purpose
4
5	Use this skill for Kaggle competition work: context gathering, writeups, discussions, kernels, local reproduction, submission, and dataset upload.
6
7	Do not use it for unrelated ML training, generic notebook editing, general data analysis, or non-Kaggle dataset management unless the user explicitly ties the task to Kaggle.
8
9	## Inputs
10
11	\| Input \| Required \| Description \|
12	\|---\|---\|---\|
13	\| Kaggle slug, URL, writeup URL, kernel ref, or local folder \| Depends on task \| Primary target for the requested Kaggle action. \|
14	\| `KAGGLE_API_TOKEN` \| Required for API/CLI-backed workflows \| KGAT token string for Kaggle API, CLI, and SDK calls. \|
15	\| Disk space \| Required for kernel setup \| Must fit input datasets, competition data, models, and extracted archives. \|
16
17	## Prerequisites
18
19	- Run commands from this skill directory unless a referenced workflow says otherwise.
20	- Install only the runtime packages needed for the requested workflow.
21	- Set `KAGGLE_API_TOKEN` before API, CLI, kernel, discussion, dataset, or submission workflows.
22	- Confirm local disk space before downloading competition data, kernel inputs, or extracted archives.
23	- Require explicit user confirmation before sensitive, externally visible actions: competition submissions (each can consume a daily slot), dataset uploads, and creating a public dataset. Treat `KAGGLE_API_TOKEN` as a secret — never print, log, or echo it.
24
25	## Runtime Dependencies
26
27	Install only the packages needed for the requested task into the current environment, then run scripts with `python`.
28
29	Kaggle API, CLI, kernels, discussions, datasets, competition pages, and writeups:
30
31	```bash
32	if command -v uv >/dev/null 2>&1; then
33	uv pip install httpx kaggle kagglesdk nbformat pydantic python-dotenv rich
34	else
35	python -m pip install httpx kaggle kagglesdk nbformat pydantic python-dotenv rich
36	fi
37	```
38
39	For API/CLI tasks, verify credentials before calling Kaggle:
40
41	```bash
42	: "${KAGGLE_API_TOKEN:?ERROR: KAGGLE_API_TOKEN environment variable is not set}"
43	```
44
45	## Workflows
46
47	Use this workflow catalog to choose the right path. Run the direct script commands for quick tasks. For workflows that point to another markdown file, read that file only when the request needs that workflow.
48
49	Prefer the runtime's `run_script` helper when it exists, for example `run_script("scripts/fetch_competition_info.py", args=["titanic"])`. Otherwise run the equivalent `python ./scripts/<script>.py ...` command from this skill directory.
50
51	### Competition Details
52
53	Use this when the user asks to retrieve or summarize a Kaggle competition overview, rules, evaluation, timeline, or dataset description.
54
55	Fetch overview:
56
57	```bash
58	python ./scripts/fetch_competition_info.py <competition-slug-or-url>
59	```
60
61	Fetch dataset description:
62
63	```bash
64	python ./scripts/fetch_dataset_info.py <competition-slug-or-url>
65	```
66
67	The scripts accept a bare competition slug or `https://www.kaggle.com/competitions/<slug>` URL and extract the slug automatically. Convert output to markdown when the user asks for saved documentation, using `{slug}_competition_overview.md` and `{slug}_dataset_description.md` in the current working directory.
68
69	### Research Brief
70
71	Use this when the user asks you to **research a competition and write a strategy
72	brief** in natural terms (e.g. "research this competition and brief me, with
73	links and a few charts"). You chain the skill's individual research workflows
74	yourself, write your own analysis/plotting code, and produce the brief. Read
75	`./research-brief.md` for the principles that keep the brief accurate, informative,
76	and useful to a reader — how to cite real sources as links, and how to make plots
77	honest and legible (every plotted number traces to what you gathered). These
78	principles live in the skill so the user does not have to spell them out.
79
80	### Writeups
81
82	Use this when the user asks to fetch one writeup, fetch top-k writeups, discover leaderboard writeup links, or summarize solution posts. Read `./writeups.md`.
83
84	### Discussions
85
86	Use this when the user asks for Kaggle competition discussions, community insights, qu

People who liked this also viewed

6 picks

Type