Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add topprismdata/cultivating-ml-agent --skill kaggle-competition-best-practicesgit clone --depth 1 https://github.com/topprismdata/cultivating-ml-agentWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/topprismdata/cultivating-ml-agent/kaggle-competition-best-practices)<a href="https://agentmods.dev/skills/topprismdata/cultivating-ml-agent/kaggle-competition-best-practices"><img src="https://agentmods.dev/badge/skills/topprismdata/cultivating-ml-agent/kaggle-competition-best-practices/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/topprismdata/cultivating-ml-agent/kaggle-competition-best-practices"><img src="https://agentmods.dev/badge/skills/topprismdata/cultivating-ml-agent/kaggle-competition-best-practices.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00127 | $0.06186 |
| Opus 5.5 | $0.00051 | $0.02474 |
| Sonnet 5.5 | $0.00025 | $0.01237 |
| Haiku 4.5 | $0.00013 | $0.00619 |
Grade A, and why
kaggle-competition-best-practices scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
subprocess.run([ How it starts
The opening of the file, as written. The whole thing — 738 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kaggle竞赛最佳实践与知识库管理
Problem
Kaggle竞赛涉及大量领域知识、获胜技巧和策略。每次竞赛都重新学习效率低下。需要:
- 系统化的竞赛工作流程
- 可复制的获胜方案
- 竞赛知识的快速查询
- 为每个竞赛建立RAG知识库
Context / Trigger Conditions
使用此技能当:
- 开始新的Kaggle竞赛项目 - 建立完整工作计划
- 查询竞赛策略 - 提问: "这个竞赛的最佳实践是什么?"
- 分析获胜方案 - 需要理解top方案的思路
- 特征工程困惑 - 需要有效的特征灵感
- 提交策略 - Stage1/Stage2规则和策略
- 创建竞赛知识库 - 为新竞赛整理资料
Solution
Phase 1: 竞赛规划与知识库建立
1.1 创建竞赛NotebookLM知识库
为每个竞赛创建独立的NotebookLM notebook用于RAG查询:
# 创建新notebook
notebooklm create "{竞赛名称} 竞赛资料"
# 记录notebook ID
notebooklm list | grep "{竞赛名称}"
1.2 收集和上传资料
爬取并整理以下内容上传:
必须上传的资料:
- 官方规则和数据说明
- 论坛置顶讨论
- TOP20高赞Notebooks摘要
- 获奖方案解析
资料整理模板:
# {竞赛名称} - 论坛讨论
## 置顶/官方讨论
- 竞赛规则更新
- 数据发布通知
- 重要时间节点
## 热门讨论
- 按投票排序的TOP20
## 技术讨论
- 数据质量问题
- 特征工程技巧
- 模型架构
---
# {竞赛名称} - Notebooks分析
## TOP30 Notebooks
## 技术栈统计
## 获奖方案深度解析
---
# {竞赛名称} - 竞赛指南
## 任务理解
## 数据结构
## 评估指标
## 提交规则(Stage1/Stage2)
## 关键时间节点
## 最佳实践
上传命令:
notebooklm source add 论坛.md -n {notebook_id} --title "论坛讨论"
notebooklm source add notebooks.md -n {notebook_id} --title "Notebooks"
notebooklm source add guide.md -n {notebook_id} --title "竞赛指南"
1.3 获取Notebooks列表(推荐方法)
首选方法: Kaggle CLI ✅
# 安装kaggle CLI(如果未安装)
pip install kaggle
# 配置API密钥
# 从 https://www.kaggle.com/settings 下载kaggle.json
# 放置在 ~/.kaggle/kaggle.json
# 获取竞赛notebooks列表(按投票排序)
kaggle kernels list --competition {competition-slug} --sort-by voteCount --page-size 50
# 示例
kaggle kernels list --competition march-machine-learning-mania-2026 --sort-by voteCount --page-size 50
kaggle kernels list --competition vesuvius-challenge-surface-detection --sort-by voteCount --page-size 50
优势:
- ✅ 无需登录
- ✅ 数据结构化(包含投票数、作者、更新时间)
- ✅ 100%可靠
- ✅ 可排序和分页
备用方法: Playwright爬虫 ⚠️
- 仅当kaggle CLI不可用时使用
- 可能需要登录
- 参见
discover-undocumented-web-apisskill
1.4 批量下载和上传Notebooks(完整工作流)
问题: 直接上传Kaggle notebooks到NotebookLM会失败
.ipynb和.Rmd文件返回400 Bad Request- NotebookLM只支持:
.md,.txt,.pdf,.docx,.xlsx等格式
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 738 lines · 127 tokens per session scan A c45f23d35f20
kaggle-competition-best-practices is a skill published in the GitHub repository topprismdata/cultivating-ml-agent (5 stars, last pushed 24d ago), licensed MIT. It adds 127 tokens to every session and 6,186 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
kaggle-competition-best-practices compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| kaggle-competition-best-practicestopprismdata/cultivating-ml-agent | Skill | 5 | 24d ago | MIT | A | 127 | Claude Code, Codex |
| knowledge-orgbojieli/ai-agent-book | Skill | 57k | 29d ago | Apache-2.0 | A | 96 | Claude Code, Codex |
| rag-pipelinebojieli/ai-agent-book | Skill | 57k | 29d ago | Apache-2.0 | A | 125 | Claude Code, Codex |
| xerjxerj-org/xerj | Skill | 19k | yesterday | Apache-2.0 | A | 38 | Claude Code, Codex |
| install-openviking-memoryvolcengine/OpenViking | Skill | 42k | yesterday | AGPL-3.0 | A | 191 | Claude Code, Codex |
| using-agent-brainSpillwaveSolutions/agent-brain | Skill | 119 | 1mo ago | MIT | A | 249 | Claude Code |
| cartographer-kb-ingest-planBeppeTemp/cartographer | Skill | 55 | yesterday | Apache-2.0 | A | 88 | Claude Code, Codex |