🤖 AI Agent-driven Kaggle competition workflow. Battle-tested patterns for score stabilization, submission troubleshooting, kernel workflows, and spec-driven development.
# Add to your Claude Code skills
git clone https://github.com/FrankS-IntelLab/agentic-kaggle-skillGuides for using ai agents skills like agentic-kaggle-skill.
Last scanned: 6/10/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-06-10T08:08:38.213Z",
"npmAuditRan": true,
"pipAuditRan": true
}agentic-kaggle-skill is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by FrankS-IntelLab. 🤖 AI Agent-driven Kaggle competition workflow. Battle-tested patterns for score stabilization, submission troubleshooting, kernel workflows, and spec-driven development. It has 108 GitHub stars.
Yes. agentic-kaggle-skill passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/FrankS-IntelLab/agentic-kaggle-skill" and add it to your Claude Code skills directory (see the Installation section above). agentic-kaggle-skill ships a SKILL.md manifest, so compatible agents can discover and load it automatically.
agentic-kaggle-skill is primarily written in Python. It is open-source under FrankS-IntelLab on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh agentic-kaggle-skill against similar tools.
No comments yet. Be the first to share your thoughts!
Treat every competition as a validation problem first and a modeling problem second. The default target platform is Kaggle, so prefer Kaggle-native notebooks/scripts, datasets, model artifacts, competition submissions, and score receipts. For code competitions, assume the final notebook/kernel will be rerun by Kaggle against hidden data unless the competition docs prove otherwise.
/kaggle/input/....references/method-map.md for the neutral workflow map behind the skill.references/information-sharing-policy.md before publishing competition code, notebooks, datasets, models, artifacts, or reports outside the active team or workspace.references/competition-intel.md when a Kaggle competition slug, URL, title, public leaderboard context, open solutions, or discussion activity may inform the approach.references/cross-validation-and-metrics.md when choosing folds, metrics, thresholds, or leakage checks.references/tabular-workflow.md for categorical variables, feature engineering, selection, and hyperparameter tuning.references/image-text-workflow.md for image, segmentation, and NLP competition approaches.references/kaggle-code-competition-pipeline.md when the target is a Kaggle code competition, hidden rerun, final notebook scoring flow, or model artifact handoff between producer and consumer notebooks.references/advanced-notebook-architecture.md when a stronger solution may need multiple model families, staged feature/embedding/model producers, pseudo-labeling, distillation, postprocessing, blending, stacking, or parallel Kaggle GPU notebooks.references/kaggle-offload.md when local runs are heavy, GPU is useful, Kaggle data access is needed, or remote notebook results must be collected.references/kaggle-pipeline-datasets.md when using multiple Kaggle notebooks, intermediate datasets, notebook output sources, or kagglehub.references/submission-endgame.md before stopping work; this skill is not done until Kaggle scoring has been attempted and the result has been collected or a concrete blocker is documented.references/code-competition-debugging.md when a Kaggle code competition submission fails, times out, OOMs, produces no score, or reports a vague hidden-run/scoring error.references/ensembling-and-reproducibility.md for project layout, OOF artifacts, stacking, blending, and repeatability.references/research/ or examples/ only when the user asks for historical case studies, Hermes-era patterns, or concrete competition lessons from this repository.scripts/scaffold_competition.py to create a competition workspace.scripts/make_folds.py to add a fold column to a training CSV.scripts/prepare_kaggle_kernel.py to create a Kaggle kernel folder with metadata and retrievable experiment logs.scripts/prepare_kaggle_dataset.py to create metadata and commands for versioned intermediate artifact datasets.Start with the metric and validation:
kaggle-competition-intel MCP tools when available: top_open_solutions for score-ranked plus latest high-vote notebooks, and competition_discussions for top-voted plus recently active discussion topics before choosing expensive baselines.Then build baselines in this order:
Do not wait for the user to explicitly ask for sophistication when the competition warrants it. After a stable baseline, propose and execute a stronger staged architecture if public solutions, discussion intel, data modality, metric pressure, or CV plateau suggests that a single notebook/model will underperform. Keep the architecture gated by OOF evidence, artifact manifests, and final Kaggle scoring.
When a run is likely to exceed local RAM/VRAM, require a GPU/TPU, or needs Kaggle-only data mounts, prepare a Kaggle kernel run instead of forcing it locally. The remote run must emit experiment_log.json, metrics.jsonl, and an artifact manifest so results can be retrieved and interpreted after kaggle kernels output.
When the solution has multiple heavy stages, keep the remote graph shallow and inspectable:
/kaggle/input/..., and perform hidden-test-safe inference.kernel_sources only for short-lived chains where durability/versioning is unnecessary.kagglehub inside Python when it is more convenient to download datasets, competition files, notebook outputs, or upload dataset versions programmatically.Do not stop at a plan, scaffold, trained model, notebook run, downloaded output, or local validation score. Continue until one of these is true:
Use this quick mapping:
StratifiedKFold.KFold for ordinary targets, binned stratified folds for skewed or multimodal targets.GroupKFold or stratified group splitting.Create a competition skeleton:
python3 <skill-dir>/scripts/scaffold_competition.py --root .
Create stratified folds:
python3 <skill-dir>/scripts/make_folds.py \
--input input/train.csv \
--output input/train_folds.csv \
--target target \
--strategy stratified \
--n-splits 5
Create grouped folds:
python3 <skill-dir>/scripts/make_folds.py \
--input input/train.csv \
--output input/train_folds.csv \
--target target \
--group-col patient_id \
--strategy group
Prepare a Kaggle GPU kernel experiment folder:
python3 <skill-dir>/scripts/prepare_kaggle_kernel.py \
--output kaggle_kernels/exp_lgbm_gpu \
--username kaggle-user \
--slug exp-lgbm-gpu \
--title "exp lgbm gpu" \
--competition playground-series-sample \
--accelerator NvidiaTeslaT4
Prepare a private Kaggle dataset folder for intermediate artifacts:
python3 <skill-dir>/scripts/prepare_kaggle_dataset.py \
--output kaggle_datasets/exp_features_v1 \
--username kaggle-user \
--slug exp-features-v1 \
--title "exp features v1" \
--description "OOF-safe feature artifacts for experiment exp_features_v1"
Prepare a private Kaggle dataset folder for trained model artifacts:
python3 <skill-dir>/scripts/prepare_kaggle_dataset.py \
--output kaggle_datasets/exp_model_v1 \
--username kaggle-user \
--slug exp-model-v1 \
--title "exp model v1" \
--description "Trained model artifacts for experiment exp_model_v1" \
--artifact-kind model
Distilled from real Kaggle competition experience 提炼自真实 Kaggle 竞赛实践
Including: RL Game AI | Audio Classification | LLM Reasoning | Multi-stage debugging journeys 包括:强化学习游戏 AI | 音频分类 | LLM 推理 | 多阶段调试实践
| Agent | Status 状态 | Notes 说明 |
|---|---|---|
| Codex | First-class 一等支持 | Uses SKILL.md, agents/openai.yaml, references/, and scripts/. |
| Hermes | Supported 支持 | Uses the same skill folder. Hermes-era examples remain in references/research/. |
This repository keeps one canonical skill identity:
本仓库使用一个统一的 skill 名称:
name: agentic-kaggle-skill
The skill is written in the open agent skills format so it can be used by multiple agents. Codex-specific metadata lives in agents/openai.yaml; Hermes users can consume the same root SKILL.md and bundled resources.
该 skill 使用开放 agent skill 格式编写,可被多个智能体使用。Codex 专属元数据放在 agents/openai.yaml;Hermes 用户可以直接使用根目录的 SKILL.md 以及配套的 references/ 和 scripts/。
Transform Kaggle work from scattered manual iteration into an agent-assisted competition loop:
将 Kaggle 工作从零散的手动试错转为智能体辅助的竞赛闭环:
| Before 之前 | After 之后 |
|---|---|
| Manual notebook analysis 手动分析 notebook | Agent scouts public notebooks and discussions as signals 智能体将公开 notebook 和讨论作为线索 |
| Guess why submissions fail 猜测提交失败原因 | Agent diagnoses format, path, runtime, and hidden rerun issues 智能体诊断格式、路径、运行时和隐藏重跑问题 |
| Try random improvements 随机尝试改进 | Fold-driven validation and OOF-safe iteration 基于 fold 和 OOF 的稳健迭代 |
| One overloaded notebook 一个超载 notebook | Producer/consumer pipeline with private artifact datasets 使用私有 artifact dataset 的生产者/消费者流水线 |
Core capabilities:
核心能力:
Install as a user-level Codex skill:
作为用户级 Codex skill 安装:
mkdir -p ~/.agents/skills
git clone https://github.com/FrankS-IntelLab/agentic-kaggle-skill.git \
~/.agents/skills/agentic-kaggle-skill
Restart Codex if the skill does not appear immediately. Invoke it explicitly with:
如果 skill 没有立即出现,请重启 Codex。可以这样显式调用:
Use $agentic-kaggle-skill to help me start this Kaggle competition.
For repo-scoped development, place or symlink this folder under a repository's .agents/skills/ directory:
如果只想在某个仓库中启用,可以把该目录放到或软链接到仓库的 .agents/skills/:
mkdir -p .agents/skills
ln -s /path/to/agentic-kaggle-skill .agents/skills/agentic-kaggle-skill
Install the whole skill folder so references and scripts are available:
安装完整 skill 目录,确保 references 和 scripts 都可用:
mkdir -p ~/.hermes/skills/data-science
git clone https://github.com/FrankS-IntelLab/agentic-kaggle-skill.git \
~/.hermes/skills/data-science/agentic-kaggle
Then ask Hermes to use the agentic Kaggle skill for competition work.
然后让 Hermes 使用 agentic Kaggle skill 来处理竞赛任务。
Most scripts use only the Python standard library. scripts/make_folds.py requires pandas and numpy; scikit-learn is recommended for standard splitters.
大部分脚本只依赖 Python 标准库。scripts/make_folds.py 需要 pandas 和 numpy;推荐安装 scikit-learn 以使用标准切分器。
python3 -m pip install -r requirements.txt
agentic-kaggle-skill/
├── SKILL.md
├── agents/
│ └── openai.yaml
├── references/
│ ├── method-map.md
│ ├── information-sharing-policy.md
│ ├── competition-intel.md
│ ├── cross-validation-and-metrics.md
│ ├── tabular-workflow.md
│ ├── image-text-workflow.md
│ ├── kaggle-code-competition-pipeline.md
│ ├── advanced-notebook-architecture.md
│ ├── kaggle-offload.md
│ ├── kaggle-pipeline-datasets.md
│ ├── submission-endgame.md
│ ├── code-competition-debugging.md
│ ├── ensembling-and-reproducibility.md
│ └── research/
├── scripts/
│ ├── scaffold_competition.py
│ ├── make_folds.py
│ ├── prepare_kaggle_kernel.py
│ └── prepare_kaggle_dataset.py
├── examples/
│ ├── rl-game-case-study.md
│ └── audio-classification-case-study.md
├── requirements.txt
├── README.md
└── LICENSE
| Lesson 教训 | Details 详情 |
|---|---|
| Feature completeness 功能完整性 | Top agents used much richer decision logic; simplified agents underperformed. 顶级 agent 使用更完整的决策逻辑,简化版表现明显较弱。 |
| Time budget 时间预算 | Strict turn limits require profiling after each change. 严格回合限制要求每次改动后都做性能分析。 |
| Lesson 教训 | Details 详情 |
|---|---|
| Hybrid ensemble 混合集成 | Temporal model plus SED-style models can improve robustness. 时序模型加 SED 风格模型可提升稳健性。 |
| Silent failures 静默失败 | Log exceptions during feature extraction and inference. 特征提取和推理阶段需要记录异常。 |
SKILL.md is the canonical entry point. It stays concise and tells the agent which reference file to load for each Kaggle workflow.
SKILL.md 是统一入口,保持简洁,并告诉智能体在不同 Kaggle 工作流中应该加载哪个参考文件。
agents/openai.yaml is Codex-facing UI metadata. It does not fork the workflow; it only improves how the skill appears and is invoked in Codex.
agents/openai.yaml 是面向 Codex 的 UI 元数据,不分叉工作流,只改善该 skill 在 Codex 中的展示与调用体验。
references/ contains detailed workflow guidance loaded only when relevant. The references/research/ folder preserves earlier Hermes-era lessons, troubleshooting notes, automation patterns, and case-specific insights.
references/ 存放按需加载的详细流程说明。references/research/ 保留早期 Hermes 阶段的经验、故障排除、自动化模式和具体案例洞察。
scripts/ contains repeatable utilities for scaffolding a Kaggle project, making folds, preparing Kaggle kernels, and preparing private Kaggle artifact datasets.
scripts/ 存放可复用工具,用于创建 Kaggle 项目骨架、生成 folds、准备 Kaggle kernels,以及准备私有 Kaggle artifact datasets。
This skill is source-agnostic. It packages general competitive ML and Kaggle workflow procedures rather than copying named public notebooks, books, or papers.
该 skill 是 source-agnostic 的。它封装的是通用竞赛机器学习和 Kaggle 工作流流程,而不是复制某个公开 notebook、书籍或论文。
When using public notebooks or discussions during an active competition, treat them as scouting signals. Do not copy code, text, model artifacts, generated features, or data-derived outputs without checking the competition rules, data license, third-party license obligations, and attribution requirements.
在进行中的竞赛中使用公开 notebook 或讨论时,应将其视作侦察信号。不要在未检查竞赛规则、数据许可、第三方许可证义务和归属要求前复制代码、文本、模型 artifact、生成特征或数据派生输出。
Keep the public identity aligned everywhere:
请保持所有位置的公开名称一致:
agentic-kaggle-skill
When updating the skill:
更新 skill 时:
SKILL.md.
将统一工作流保留在 SKILL.md。references/.
将详细流程放入 references/。scripts/.
将确定性辅助工具放入 scripts/。agents/openai.yaml when the skill name, scope, or default prompt changes.
当 skill 名称、范围或默认 prompt 变化时,更新 agents/openai.yaml。Found a new pattern or solved a tricky error?
发现了新模式或解决了棘手错误?
references/research/, references/, or examples/.
将你的洞察添加到 references/research/、references/ 或 examples/。MIT. See LICENSE.
MIT。见 LICENSE。
**Made by [Frank S (IntelLab)](http