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-type-strategygit 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-type-strategy)<a href="https://agentmods.dev/skills/topprismdata/cultivating-ml-agent/kaggle-competition-type-strategy"><img src="https://agentmods.dev/badge/skills/topprismdata/cultivating-ml-agent/kaggle-competition-type-strategy/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-type-strategy"><img src="https://agentmods.dev/badge/skills/topprismdata/cultivating-ml-agent/kaggle-competition-type-strategy.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 | $0.00145 | $0.02418 |
| Opus 5 | $0.00072 | $0.01209 |
| Sonnet 5 | $0.00029 | $0.00484 |
| Haiku 4.5 | $0.00015 | $0.00242 |
Grade A, and why
kaggle-competition-type-strategy scanned grade A with 0 findings 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 11d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kaggle Competition Type Strategy
The 6 Competition Types
Kaggle competitions are NOT all the same. The type determines your entire strategy.
Type 1: Standard Prediction (Tabular)
Examples: House Prices, TPS series, Spaceship Titanic, s6e7 Mechanism: Upload CSV file. Scored immediately on fixed test set. Scoring: Deterministic (RMSE, AUC, logloss — same formula every time) Public kernel value: ★★★★★ (best public kernel ≈ 95-99% of winning score) GPU needed: Usually no (CPU GBDT sufficient) Quota: 5/day, no convergence delay
Strategy:
- Day 1: Fork best public kernel → submit → establish baseline
- Day 2-3: AutoGluon best_quality → compare with public → blend if complementary
- Day 4-7: Feature engineering (highest ROI lever for tabular)
- Day 8+: Model diversity (LGB+XGB+CAT blend), pseudo-labeling (cautious)
- Final: Submit best blend, stop tuning 24h before deadline
Validation: 5-fold StratifiedKFold + adversarial validation. Trust OOF if N>10K.
Type 2: Code Competition (Notebook Required)
Examples: ROGII Wellbore, Biohub Cell Tracking, NeuroGolf Mechanism: Submit Kaggle Notebook. Runs on hidden test set. No internet. Scoring: Deterministic on hidden test (may differ significantly from public) Public kernel value: ★★★★☆ (fork is main strategy, but artifacts/dependencies) GPU needed: Often yes (UNet, LLM inference, model training) Quota: 5/day or 10/day, kernel run time limit (9-12h)
Strategy:
- Day 1: Read top 10 public kernels. Identify required datasets (artifacts).
- Day 2: Fork best kernel. Add ALL required datasets as inputs. Push → verify COMPLETE.
- Day 3: If kernel ERRORs → read log → fix dependencies (see code-competition-artifact-pipeline)
- Day 4-7: Modify pipeline (trim crashing components, tune parameters)
- Final: Ensure kernel COMPLETES (ERROR → no score, even if submission.csv exists)
Critical: Code competitions do NOT score ERROR-status kernels. A kernel that crashes mid-pipeline produces NO submission, even if submission.csv was written before the crash. Always trim or try/except around risky cells.
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.
- 11d ago First seen · 207 lines · 145 tokens per session scan A 70adf037c517
kaggle-competition-type-strategy is a skill published in the GitHub repository topprismdata/cultivating-ml-agent (5 stars, last pushed 14d ago), licensed MIT. It adds 145 tokens to every session and 2,418 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
huggingface-hub
Hugging Face Hub CLI (hf) — search, download, and upload models and datasets, manage repos, query datasets with SQL, deploy inference endpoints, manage Spaces and buckets.
tensorboard
Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML visualization toolkit.
mlflow
Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platform.
datachain-knowledge
Use whenever datasets, cloud storage buckets, or data pipelines are mentioned — creating, saving, querying, listing, exploring, deleting, or processing data in S3, GCS, Azure Blob, or local storage. Also use when running any script that may create datasets as a side effect. Maintains a knowledge base at dc-knowledge/…
prompt-scanner
A scanner for text sent to an AI agent, looking for prompt injection and jailbreak attempts. Prompt injection is text that tries to override an agent's instructions; a jailbreak tries to bypass its safety limits.
install-openviking-memory
Install and configure the OpenViking long-term memory plugin for OpenClaw via natural conversation. Once installed, the plugin automatically captures facts from chats and recalls relevant context before each reply (auto-capture + auto-recall, cross-session). Covers prerequisites, install through OpenClaw's plugin…