Back to Details

kaggle

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Kaggle — Unified Skill

Kaggle — 统一技能

Complete Kaggle integration for any LLM or agentic coding system (Claude Code, gemini-cli, Cursor, etc.): account setup, competition reports, dataset/model downloads, notebook execution, competition submissions, badge collection, and general Kaggle questions. Four integrated modules working together.
Overlap guard: For hackathon grading evaluation and alignment analysis, use the kaggle-hackathon-grading skill instead.
Network requirements: outbound HTTPS to 
api.kaggle.com
, 
www.kaggle.com
, and 
storage.googleapis.com
.
为任何LLM或智能编码系统（Claude Code、gemini-cli、Cursor等）提供完整的Kaggle集成支持：涵盖账户设置、竞赛报告、数据集/模型下载、Notebook执行、竞赛提交、徽章收集以及各类Kaggle相关通用问题。由四个集成模块协同工作。
重叠防护： 若用于黑客松评分评估和一致性分析，请使用kaggle-hackathon-grading技能替代。
网络要求： 需能对外访问HTTPS地址
api.kaggle.com
、
www.kaggle.com
和
storage.googleapis.com
。

Modules

模块

ModulePurpose
registrationAccount creation, API key generation, credential storage
comp-reportCompetition landscape reports with Playwright scraping
kllmCore Kaggle interaction (kagglehub, CLI, MCP, UI)
badge-collectorSystematic badge earning across 5 phases
模块用途
registration账户创建、API密钥生成、凭证存储
comp-report基于Playwright爬取的竞赛格局报告
kllm核心Kaggle交互（kagglehub、CLI、MCP、UI）
badge-collector分5个阶段系统性获取徽章

Credential Setup

凭证设置

Always run the credential checker first:
bash
python3 skills/kaggle/shared/check_all_credentials.py
Three credential types are needed for full compatibility:
VariableFormatPurpose
KAGGLE_USERNAME
Kaggle handleIdentity for all tools
KAGGLE_KEY
32-char hexLegacy key (CLI, kagglehub, most MCP)
KAGGLE_API_TOKEN
KGAT_
-prefixed		Scoped token (some MCP endpoints)
If any are missing, follow the registration walkthrough: 
Read modules/registration/README.md
for the full step-by-step guide.
Security: Never echo, log, or commit actual credential values.
请始终先运行凭证检查工具：
bash
python3 skills/kaggle/shared/check_all_credentials.py
完整兼容需要三种类型的凭证：
变量格式用途
KAGGLE_USERNAME
Kaggle用户名所有工具的身份标识
KAGGLE_KEY
32位十六进制字符串传统密钥（适用于CLI、kagglehub、大多数MCP场景）
KAGGLE_API_TOKEN
以
KGAT_
为前缀		范围限定令牌（适用于部分MCP端点）
若缺少任何凭证，请遵循注册指南操作：查看
modules/registration/README.md
获取完整分步指引。
安全提示： 切勿回显、记录或提交实际凭证值。

Module: Registration

模块：注册

Walks users through creating a Kaggle account and generating all three API credentials. Saves to 
.env
and 
~/.kaggle/kaggle.json
.
Key commands:
bash
python3 skills/kaggle/modules/registration/scripts/check_registration.py
bash skills/kaggle/modules/registration/scripts/setup_env.sh
Read modules/registration/README.md
for the complete walkthrough.
引导用户完成Kaggle账户创建及所有三种API凭证的生成流程。将凭证保存至
.env
和
~/.kaggle/kaggle.json
。
关键命令：
bash
python3 skills/kaggle/modules/registration/scripts/check_registration.py
bash skills/kaggle/modules/registration/scripts/setup_env.sh
查看
modules/registration/README.md
获取完整操作指南。

Module: Competition Reports

模块：竞赛报告

Generates comprehensive landscape reports of recent Kaggle competition activity. Uses Python API for metadata + Playwright MCP tools for SPA content.
6-step workflow:
  1. Verify credentials
  2. Gather competition list across all categories
  3. Get structured details per competition (files, leaderboard, kernels)
  4. Scrape problem statements, evaluation metrics, writeups via Playwright
  5. Compose markdown report with Methods & Insights analysis
  6. Present inline
bash
python3 skills/kaggle/modules/comp-report/scripts/list_competitions.py --lookback-days 30 --output json
python3 skills/kaggle/modules/comp-report/scripts/competition_details.py --slug SLUG
Read modules/comp-report/README.md
for full details including hackathon handling.
生成近期Kaggle竞赛活动的全面格局报告。结合Python API获取元数据，以及Playwright MCP工具爬取SPA内容。
6步工作流：
  1. 验证凭证
  2. 收集全品类竞赛列表
  3. 获取每个竞赛的结构化详情（文件、排行榜、代码内核）
  4. 通过Playwright爬取问题描述、评估指标、技术文档
  5. 撰写包含方法与洞察分析的Markdown报告
  6. 在线展示报告
bash
python3 skills/kaggle/modules/comp-report/scripts/list_competitions.py --lookback-days 30 --output json
python3 skills/kaggle/modules/comp-report/scripts/competition_details.py --slug SLUG
查看
modules/comp-report/README.md
获取完整详情，包括黑客松场景处理方式。

Module: Kaggle Interaction (kllm)

模块：Kaggle交互（kllm）

Four methods to interact with kaggle.com:
MethodBest For
kagglehubQuick dataset/model download in Python
kaggle-cliFull workflow scripting
MCP ServerAI agent integration
Kaggle UIAccount setup, verification
Capability matrix:
Taskkagglehubkaggle-cliMCPUI
Download dataset
dataset_download()
datasets download
YesYes
Download model
model_download()
models instances versions download
YesYes
Execute notebook—
kernels push/status/output
YesYes
Submit to competition—
competitions submit
YesYes
Publish dataset
dataset_upload()
datasets create
YesYes
Publish model
model_upload()
models create
YesYes
Known issues:
  • dataset_load()
    broken in kagglehub v0.4.3 — use 
    dataset_download()
    + 
    pd.read_csv()
  • competitions download
    has no 
    --unzip
    in CLI >= 1.8
  • Competition-linked datasets return 403 — use standalone copies
Read modules/kllm/README.md
for full details and all task workflows.
提供四种与kaggle.com交互的方式：
方式适用场景
kagglehubPython环境下快速下载数据集/模型
kaggle-cli全流程脚本化操作
MCP ServerAI Agent集成
Kaggle UI账户设置、验证操作
能力矩阵：
任务kagglehubkaggle-cliMCPUI
下载数据集
dataset_download()
datasets download
支持支持
下载模型
model_download()
models instances versions download
支持支持
执行Notebook—
kernels push/status/output
支持支持
提交竞赛结果—
competitions submit
支持支持
发布数据集
dataset_upload()
datasets create
支持支持
发布模型
model_upload()
models create
支持支持
已知问题：
  • kagglehub v0.4.3中
    dataset_load()
    功能损坏 — 请使用
    dataset_download()
    + 
    pd.read_csv()
    替代
  • CLI版本 >=1.8时
    competitions download
    命令无
    --unzip
    参数
  • 竞赛关联数据集返回403错误 — 请使用独立副本
查看
modules/kllm/README.md
获取完整详情及所有任务工作流。

Module: Badge Collector

模块：徽章收集器

Systematically earns ~38 automatable Kaggle badges across 5 phases:
PhaseNameBadgesTime
1Instant API~165-10 min
2Competition~710-15 min
3Pipeline~315-30 min
4Browser~85-10 min
5Streaks~4Setup only
bash
python3 skills/kaggle/modules/badge-collector/scripts/orchestrator.py --dry-run
python3 skills/kaggle/modules/badge-collector/scripts/orchestrator.py --phase 1
python3 skills/kaggle/modules/badge-collector/scripts/orchestrator.py --status
Read modules/badge-collector/README.md
for full details.
分5个阶段系统性获取约38个可自动化获取的Kaggle徽章：
阶段名称徽章数量耗时
1即时API类~165-10分钟
2竞赛类~710-15分钟
3工作流类~315-30分钟
4浏览器操作类~85-10分钟
5连续操作类~4仅需初始设置
bash
python3 skills/kaggle/modules/badge-collector/scripts/orchestrator.py --dry-run
python3 skills/kaggle/modules/badge-collector/scripts/orchestrator.py --phase 1
python3 skills/kaggle/modules/badge-collector/scripts/orchestrator.py --status
查看
modules/badge-collector/README.md
获取完整详情。

Orchestration Workflow

编排工作流

This skill is primarily a reference — use the modules and scripts as needed based on the user's request. When explicitly asked to run the full Kaggle workflow, follow these steps:
本技能主要作为参考工具使用 — 根据用户需求选用相应模块和脚本。当用户明确要求运行完整Kaggle工作流时，请遵循以下步骤：

Step 1: Check Credentials

步骤1：检查凭证

bash
python3 skills/kaggle/shared/check_all_credentials.py
If any credentials are missing, walk through the registration module. Never echo or log actual credential values.
bash
python3 skills/kaggle/shared/check_all_credentials.py
若缺少任何凭证，请引导用户完成注册模块流程。切勿回显或记录实际凭证值。

Step 2: Generate Competition Landscape Report

步骤2：生成竞赛格局报告

Run the comp-report workflow: list competitions, get details, scrape with Playwright, compose report. Output inline.
运行comp-report工作流：列出竞赛、获取详情、通过Playwright爬取内容、撰写报告。在线输出报告。

Step 3: Summarize Kaggle Interaction Methods

步骤3：总结Kaggle交互方式

Present a concise summary of the four ways to interact with Kaggle (kagglehub, kaggle-cli, MCP Server, UI) with the capability matrix from the kllm module.
简要介绍四种与Kaggle交互的方式（kagglehub、kaggle-cli、MCP Server、UI），并展示kllm模块中的能力矩阵。

Step 4: Present Interactive Menu

步骤4：展示交互式菜单

Ask the user what they'd like to do next:
  • Earn Kaggle badges — Run the badge collector (5 phases, ~38 automatable badges)
  • Explore recent competitions — Dive deeper into specific competitions from the report
  • Enter a Kaggle competition — Register, download data, build a submission, submit
  • Download a Kaggle dataset — Search for and download any public dataset
  • Download a Kaggle model — Download pre-trained models (LLMs, CV, etc.)
  • Run a notebook on Kaggle — Push and execute a notebook on KKB with free GPU/TPU
  • Publish to Kaggle — Upload a dataset, model, or notebook
  • Learn about Kaggle progression — Tiers, medals, how to rank up
  • Something else — Free-form Kaggle help
询问用户下一步操作：
  • 获取Kaggle徽章 — 运行徽章收集器（5个阶段，约38个可自动化获取的徽章）
  • 探索近期竞赛 — 深入分析报告中的特定竞赛
  • 参与Kaggle竞赛 — 注册、下载数据、构建提交结果、提交竞赛
  • 下载Kaggle数据集 — 搜索并下载任意公开数据集
  • 下载Kaggle模型 — 下载预训练模型（LLM、CV等）
  • 在Kaggle上运行Notebook — 推送并在KKB上执行Notebook，使用免费GPU/TPU
  • 发布内容至Kaggle — 上传数据集、模型或Notebook
  • 了解Kaggle进阶体系 — 等级、奖牌、晋升方式
  • 其他需求 — 自定义Kaggle相关帮助

Step 5: Execute and Continue

步骤5：执行并循环

Handle the user's choice using the appropriate module, then loop back to offer more options.
使用对应模块处理用户选择，然后返回菜单提供更多选项。

Security

安全注意事项

  • Never commit 
    .env
    , 
    kaggle.json
    , or any credential files
  • Never echo or log actual credential values in terminal output
  • The 
    .gitignore
    excludes 
    .env
    , 
    kaggle.json
    , and related files
  • Set file permissions: 
    chmod 600 .env ~/.kaggle/kaggle.json
  • If credentials are accidentally exposed, rotate them immediately at https://www.kaggle.com/settings
  • 切勿提交
    .env
    、
    kaggle.json
    或任何凭证文件
  • 切勿在终端输出中回显或记录实际凭证值
  • .gitignore
    已排除
    .env
    、
    kaggle.json
    及相关文件
  • 设置文件权限：
    chmod 600 .env ~/.kaggle/kaggle.json
  • 若凭证意外泄露，请立即在https://www.kaggle.com/settings页面轮换凭证

Scope of Operations

操作范围

This skill performs both read-only and write operations on kaggle.com.
Read-only operations (no account side-effects):
  • List/search competitions, datasets, models, notebooks
  • Download datasets, models, competition data
  • View leaderboards, competition details, badge progress
  • Generate competition landscape reports
Write operations (create or modify resources on your account):
  • Create/publish datasets, notebooks, models (always private by default)
  • Submit predictions to competitions
  • Push and execute notebooks on Kaggle Kernel Backend (KKB)
  • Earn badges through API activity (profile-visible)
Phase 5 (Streaks) generates a local shell script for daily execution but does not auto-install cron jobs or launchd plists. Users must manually configure scheduling if desired.
本技能可在kaggle.com上执行只读和写入操作。
只读操作（无账户副作用）：
  • 列出/搜索竞赛、数据集、模型、Notebook
  • 下载数据集、模型、竞赛数据
  • 查看排行榜、竞赛详情、徽章进度
  • 生成竞赛格局报告
写入操作（在账户中创建或修改资源）：
  • 创建/发布数据集、Notebook、模型（默认设为私有）
  • 提交竞赛预测结果
  • 在Kaggle Kernel Backend（KKB）上推送并执行Notebook
  • 通过API活动获取徽章（将显示在个人主页）
阶段5（连续操作类）会生成本地Shell脚本用于每日执行，但不会自动安装cron任务或launchd配置。用户需手动配置调度任务（若需要）。

Scripts Index

脚本索引

Shared:
  • shared/check_all_credentials.py
    — Unified credential checker (all 3 types)
Registration:
  • modules/registration/scripts/check_registration.py
    — Check all 3 credentials
  • modules/registration/scripts/setup_env.sh
    — Auto-configure credentials from env/dotenv
Competition Reports:
  • modules/comp-report/scripts/utils.py
    — Credential check, API init, rate limiting
  • modules/comp-report/scripts/list_competitions.py
    — Fetch competitions across categories
  • modules/comp-report/scripts/competition_details.py
    — Files, leaderboard, kernels per competition
Kaggle Interaction (kllm):
  • modules/kllm/scripts/setup_env.sh
    — Auto-configure credentials (with .env loading)
  • modules/kllm/scripts/check_credentials.py
    — Verify and auto-map credentials
  • modules/kllm/scripts/network_check.sh
    — Check Kaggle API reachability
  • modules/kllm/scripts/cli_download.sh
    — Download datasets/models via CLI
  • modules/kllm/scripts/cli_execute.sh
    — Execute notebook on KKB
  • modules/kllm/scripts/cli_competition.sh
    — Competition workflow (list/download/submit)
  • modules/kllm/scripts/cli_publish.sh
    — Publish datasets/notebooks/models
  • modules/kllm/scripts/poll_kernel.sh
    — Poll kernel status and download output
  • modules/kllm/scripts/kagglehub_download.py
    — Download via kagglehub
  • modules/kllm/scripts/kagglehub_publish.py
    — Publish via kagglehub
Badge Collector:
  • modules/badge-collector/scripts/orchestrator.py
    — Main entry point
  • modules/badge-collector/scripts/badge_registry.py
    — 59 badge definitions
  • modules/badge-collector/scripts/badge_tracker.py
    — Progress persistence
  • modules/badge-collector/scripts/utils.py
    — Shared utilities
  • modules/badge-collector/scripts/phase_1_instant_api.py
    — Instant API badges
  • modules/badge-collector/scripts/phase_2_competition.py
    — Competition badges
  • modules/badge-collector/scripts/phase_3_pipeline.py
    — Pipeline badges
  • modules/badge-collector/scripts/phase_4_browser.py
    — Browser badges
  • modules/badge-collector/scripts/phase_5_streaks.py
    — Streak automation
共享脚本：
  • shared/check_all_credentials.py
    — 统一凭证检查工具（支持所有3种凭证类型）
注册模块：
  • modules/registration/scripts/check_registration.py
    — 检查所有3种凭证
  • modules/registration/scripts/setup_env.sh
    — 从环境变量/.env自动配置凭证
竞赛报告模块：
  • modules/comp-report/scripts/utils.py
    — 凭证检查、API初始化、速率限制
  • modules/comp-report/scripts/list_competitions.py
    — 获取全品类竞赛列表
  • modules/comp-report/scripts/competition_details.py
    — 获取单个竞赛的文件、排行榜、代码内核信息
Kaggle交互模块（kllm）：
  • modules/kllm/scripts/setup_env.sh
    — 自动配置凭证（支持加载.env文件）
  • modules/kllm/scripts/check_credentials.py
    — 验证并自动映射凭证
  • modules/kllm/scripts/network_check.sh
    — 检查Kaggle API可达性
  • modules/kllm/scripts/cli_download.sh
    — 通过CLI下载数据集/模型
  • modules/kllm/scripts/cli_execute.sh
    — 在KKB上执行Notebook
  • modules/kllm/scripts/cli_competition.sh
    — 竞赛工作流（列出/下载/提交）
  • modules/kllm/scripts/cli_publish.sh
    — 发布数据集/Notebook/模型
  • modules/kllm/scripts/poll_kernel.sh
    — 轮询内核状态并下载输出结果
  • modules/kllm/scripts/kagglehub_download.py
    — 通过kagglehub下载内容
  • modules/kllm/scripts/kagglehub_publish.py
    — 通过kagglehub发布内容
徽章收集器模块：
  • modules/badge-collector/scripts/orchestrator.py
    — 主入口脚本
  • modules/badge-collector/scripts/badge_registry.py
    — 59个徽章的定义信息
  • modules/badge-collector/scripts/badge_tracker.py
    — 进度持久化工具
  • modules/badge-collector/scripts/utils.py
    — 共享工具函数
  • modules/badge-collector/scripts/phase_1_instant_api.py
    — 即时API类徽章获取
  • modules/badge-collector/scripts/phase_2_competition.py
    — 竞赛类徽章获取
  • modules/badge-collector/scripts/phase_3_pipeline.py
    — 工作流类徽章获取
  • modules/badge-collector/scripts/phase_4_browser.py
    — 浏览器操作类徽章获取
  • modules/badge-collector/scripts/phase_5_streaks.py
    — 连续操作类自动化

References Index

参考文档索引

  • modules/registration/references/kaggle-setup.md
    — Full credential setup guide with troubleshooting
  • modules/comp-report/references/competition-categories.md
    — Competition types and API mapping
  • modules/kllm/references/kaggle-knowledge.md
    — Comprehensive Kaggle platform knowledge
  • modules/kllm/references/kagglehub-reference.md
    — Full kagglehub Python API reference
  • modules/kllm/references/cli-reference.md
    — Complete kaggle-cli command reference
  • modules/kllm/references/mcp-reference.md
    — Kaggle MCP server reference
  • modules/badge-collector/references/badge-catalog.md
    — Complete 59-badge catalog
  • modules/registration/references/kaggle-setup.md
    — 完整凭证设置指南及故障排除
  • modules/comp-report/references/competition-categories.md
    — 竞赛类型及API映射
  • modules/kllm/references/kaggle-knowledge.md
    — 全面的Kaggle平台知识
  • modules/kllm/references/kagglehub-reference.md
    — 完整的kagglehub Python API参考
  • modules/kllm/references/cli-reference.md
    — 完整的kaggle-cli命令参考
  • modules/kllm/references/mcp-reference.md
    — Kaggle MCP服务器参考
  • modules/badge-collector/references/badge-catalog.md
    — 完整的59个徽章目录