A self-improving ML agent that compounds capability across projects through knowledge crystallization, reusable skills and shared ML/MLOps infrastructure.
This repository also configures its own agents. See what cultivating-ml-agent tells them →
topprismdata/cultivating-ml-agent
Skill Claude CodeCodex
Use when running Python code via sandbox, when an experiment fails with a runtime error, when building self-correcting ML agents, or when debugging auto-generated code. Triggers on subprocess failures, ImportError, CUDA OOM, shape mismatch, or any "agent gets stuck on syntax error" pattern.
topprismdata/cultivating-ml-agent
Skill Claude CodeCodex
Self-Consistency with Tool-Integrated Reasoning (SC-TIR) for mathematical problem solving. Use when: (1) Building mathematical reasoning systems, (2) Competing in math competitions (AIMO, AIME, MATH), (3) Need precise calculation beyond text generation, (4) LLM outputs contain calculation errors. Covers: SC-TIR…
topprismdata/cultivating-ml-agent
Skill Claude CodeCodex
Use when adding new skills to the library, when extracting insights from completed experiments, when consolidating lessons learned, or when running a project retrospective. Triggers after a successful Kaggle competition, after major model breakthrough, or when "we should remember this" comes up.
topprismdata/cultivating-ml-agent
Skill Claude CodeCodex
Use when: (1) Your skill repository has grown to 30+ skills and quality is inconsistent, (2) You need to audit skills for stale references, broken links, or missing evidence, (3) You want to automatically generate standardized summary cards for each skill, (4) You're onboarding a new agent and need a quick inventory…
topprismdata/cultivating-ml-agent
Skill Claude CodeCodex
Feature engineering patterns for spatiotemporal graph prediction tasks. Use when: (1) Working with time series on graph structures, (2) Predicting node-level outcomes over time, (3) Network dynamics with spatial dependencies, (4) Kaggle competitions involving traffic, flood, power grid, or social networks. Covers…
topprismdata/cultivating-ml-agent
Skill Claude CodeCodex
Blend a foundation model (Chronos-2) with a tree model (darts LightGBMModel) for Kaggle Store Sales time-series forecasting. Validated 2026-07-26: Chronos-2 ensemble (LB 0.39387) + darts per-family LightGBM top-1 method (LB 0.39953) → geometric blend w=0.55 → LB RMSLE 0.38444 (best, -0.012 vs single-model). Use when…
topprismdata/cultivating-ml-agent
Skill Claude CodeCodex
Polynomial features breakthrough for small tabular datasets. Use when: (1) Baseline model performance plateaus after hyperparameter tuning, (2) Dataset has <10K samples with <50 features, (3) Model optimization shows diminishing returns (<0.005 improvement), (4) Tree-based models (XGBoost/LightGBM) used but still…
topprismdata/cultivating-ml-agent
Skill Claude CodeCodex
A structured method for turning a completed experiment or project into reusable lessons. It records what happened, identifies domain-specific insights, and then extracts broader principles.
topprismdata/cultivating-ml-agent
Skill Claude CodeCodex
Use when working on time series forecasting, sequence prediction, or any task with temporal data (weekly/daily orders, retail SKU recommendation, demand forecasting, user churn prediction). Triggers when you need to set up cross-validation, evaluate a temporal model, or audit temporal leakage. Always use instead of…
topprismdata/cultivating-ml-agent
Skill Claude CodeCodex
Use when: (1) Competing in Kaggle simulation competitions (PTCG, Orbit Wars, etc.) where agents are rated by TrueSkill Bayesian scoring, (2) Your LB score swings ±200 points day-to-day with no code changes, (3) You're tempted to re-submit frequently to "test" improvements, (4) You see identical agents scoring 150-400…
topprismdata/cultivating-ml-agent
Skill Claude CodeCodex
Day-specific (direct) multi-step time series forecasting. Trains N separate models, one per prediction horizon day, with all features computed from the last known date. Eliminates stale lag feature problem entirely — predictions at correct magnitude without post-processing. CRITICAL: Do NOT apply geometric mean…
topprismdata/cultivating-ml-agent
Skill Claude CodeCodex
Complete methodology for solving multi-step time series forecasting competitions where lag features cause systematic underprediction at test time. Documents the full journey from LB 1.859 → 0.399, including every failed approach and the key breakthrough. Use when: (1) Starting a new time series forecasting…
topprismdata/cultivating-ml-agent
Skill Claude CodeCodex
Use when: (1) deciding between unified vs day-specific models for multi-step forecasting, (2) considering blending day-specific with unified predictions, (3) CV shows day-specific worse than unified but unsure if LB will agree, (4) building multi-step time series models with >7 day horizons. KEY FINDING: Unified model…
topprismdata/cultivating-ml-agent
Skill Claude CodeCodex
Use when: (1) building time series features for data with annual seasonality, (2) working with retail/sales forecasting where year-over-year patterns matter, (3) looking for features that capture long-term seasonal patterns beyond short lags, (4) the 1st place solution mentions "364-day" or "YoY" features. NOT for…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: