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
Standard Operating Procedure for ANY Kaggle experiment or competition entry. Execute sequentially from Phase 0 to Phase 3. Each phase has explicit checklist items with pass/fail criteria. Covers: memory recall, competition type identification, public kernel evaluation, baseline establishment, controlled iteration…
topprismdata/cultivating-ml-agent
Skill Claude CodeCodex
Use when: (1) Your OOF score improved but LB didn't (or got worse), (2) You need to decide whether to submit based on OOF alone, (3) You're comparing models for ensemble inclusion and unsure which OOF signal to trust, (4) You see OOF/LB gap larger than 1% and don't know if it's overfitting or distribution shift.…
topprismdata/cultivating-ml-agent
Skill Claude CodeCodex
Optimal blending strategy for Kaggle competitions: 80/20 rule (re-ranking vs raw). Use when: (1) Re-ranking gives unexpected results, (2) Simple average blending underperforms, (3) Single model dominates ensemble. Avoids the trap of 100% re-ranking or equal-weight ensembles. UPDATED 2026-06-14: Added…
topprismdata/cultivating-ml-agent
Skill Claude CodeCodex
Match the submission file format to the competition's evaluation metric BEFORE submitting. For ranking-based metrics (AUC, logloss, MAP, NDCG, RMSLE) you MUST submit continuous probability/score values, not 0/1 class labels or rounded integers. Use when: (1) Preparing the final submission for any Kaggle competition…
topprismdata/cultivating-ml-agent
Skill Claude CodeCodex
Systematically replicate and learn from top Kaggle performers. Use when: (1) Stuck at a plateau and need new ideas, (2) Want to understand how top performers achieved their scores, (3) Looking for proven techniques from successful submissions, (4) OOF keeps improving but LB stays same or gets worse. Covers: code…
topprismdata/cultivating-ml-agent
Skill Claude CodeCodex
Use when: (1) You've completed a competition or experiment and want to extract reusable knowledge, (2) Your agent keeps repeating the same mistakes across competitions because lessons weren't crystallized, (3) You have 50+ memory files but can't find relevant knowledge when starting a new task, (4) You need to decide…
topprismdata/cultivating-ml-agent
Skill Claude CodeCodex
Use when: (1) Your agent's LB score drops dramatically week-over-week without code changes, (2) You're tempted to add "meta-aware" bonuses (priority targets, matchup bonuses, deck-type detection) to a strong heuristic, (3) Testing agent variants on small samples (60-80 games) and getting noisy/conflicting results, (4)…
topprismdata/cultivating-ml-agent
Skill Claude CodeCodex
Use when: (1) You have a strong hand-crafted baseline (heuristic, rule-based agent, domain-expert system) and want to improve it with ML, (2) Naive augmentation (search, behavioral cloning, type-classification) is making things WORSE, not better, (3) You're deciding between "more training data" vs "a learned value…
topprismdata/cultivating-ml-agent
Skill Claude CodeCodex
Use when: (1) Entering an LLM-based Kaggle competition (open-source model required, prompt engineering, few-shot), (2) Need to choose between base models (Qwen, DeepSeek, LLaMA), (3) Designing a prompt strategy (zero-shot, few-shot, chain-of-thought), (4) Deciding whether fine-tuning is worth the GPU cost vs prompt…
topprismdata/cultivating-ml-agent
Skill Claude CodeCodex
Use when exploring hyperparameter combinations for ML models, when doing Top-1% push on Kaggle, when grid search is too expensive, or when needing systematic exploration of pipeline variants. Triggers for neural architecture search, ensemble weight tuning, or feature subset selection.
topprismdata/cultivating-ml-agent
Skill Claude CodeCodex
Use when extracting entities and relationships from text, when building dynamic knowledge graphs, when wanting to upgrade from static OKF to entity-aware memory, or when analyzing papers/discussions for concepts. Triggers when ingesting new papers, processing Kaggle writeups, or when existing skills can't capture…
topprismdata/cultivating-ml-agent
Skill Claude CodeCodex
Use when context window is getting crowded, when agent needs to recall past experiences, or when starting a long-running task that spans multiple sessions. Triggers when you have 43+ skills and can't fit them all in context, when you need to decide "what should be in working memory right now", or when persisting new…
topprismdata/cultivating-ml-agent
Skill Claude CodeCodex
ML optimization sweet spot principle: "More is not always better". Use when: (1) Increasing model complexity but validation score plateaus or drops, (2) OOF keeps improving but LB stays same or gets worse, (3) Debating between simpler vs more complex models, (4) Feature selection or hyperparameter tuning, (5)…
topprismdata/cultivating-ml-agent
Skill Claude CodeCodex
Avoid ensembling models with significantly different performance. Use when: (1) Considering weighted average of models with divergent OOF/LB scores, (2) One model clearly underperforms another, (3) Ensemble shows lower validation score than best individual model. Covers the negative weight effect where adding a weaker…
topprismdata/cultivating-ml-agent
Skill Claude CodeCodex
Use when designing a multi-agent system, when a single agent has too many responsibilities, when planning complex ML pipelines, or when observing "agent attention fragmentation" symptoms. Triggers when a task involves planning + coding + review steps.
topprismdata/cultivating-ml-agent
Skill Claude CodeCodex
Use when: (1) considering adding family-level or store-level aggregation features to day-specific models, (2) tempted to copy hierarchical features from 1st place solutions, (3) CV improves but LB degrades after adding aggregated features. WARN: Multi-level aggregation features that work in unified models may OVERFIT…
topprismdata/cultivating-ml-agent
Skill Claude CodeCodex
Use Google's Open Knowledge Format (OKF) to convert any directory of markdown files into a force-directed knowledge graph. Validated on docs/ml-agent-memory/: 12 concepts / 35 edges rendered in 5 seconds. Use when: (1) You have a directory of markdown notes with cross-references, (2) You want to visualize how your…
topprismdata/cultivating-ml-agent
Skill Claude CodeCodex
Use when: (1) Competing in ONNX-based competitions (NeuroGolf, model compression), (2) Need to design minimal neural networks as ONNX graphs, (3) Want to replace verbose agent-generated circuits with compact hand-designed nets. Key principles: single-node graphs have zero memory cost (output is free), Conv is a linear…
topprismdata/cultivating-ml-agent
Skill Claude CodeCodex
Per-category/per-family models can produce WORSE leaderboard scores than a single global model, even when per-category CV is better. Use when: (1) Considering training separate models per product category/family/store in tabular competitions, (2) Per-category CV improves but LB degrades, (3) Each category has <100K…
topprismdata/cultivating-ml-agent
Skill Claude CodeCodex
Progressive verification methodology for debugging complex systems. Use when: (1) Facing mysterious crashes or errors with no clear cause, (2) System works in some environments but not others, (3) Multiple potential failure points exist, (4) Need to isolate whether issue is environment configuration vs code bug. Core…
topprismdata/cultivating-ml-agent
Skill Claude CodeCodex
Augment a BC Transformer agent with 2-ply bounded search using the cg library's SearchBegin/SearchStep API. Validated 2026-07-30 on Pokemon TCG AI Battle: search-enhanced agent submitted as v8 (LB pending). Use when: (1) you have a trained BC policy/value model, (2) the cg library exposes a search API…
topprismdata/cultivating-ml-agent
Skill Claude CodeCodex needs its repo
Submit a BC (behavioral cloning) Transformer agent for the Pokémon TCG AI Battle competition. Validated 2026-07-30: best.pth (15-epoch BC Large, dmodel=256) → public LB 600.0 (vs prior 165.6 — 3.6× improvement from using the best checkpoint instead of a stale submission). Use when: (1) training a BC agent on Kaggle…
topprismdata/cultivating-ml-agent
Skill Claude CodeCodex
Comprehensive EDA approach for retail/fashion/tabular ML using best-in-class libraries. Use during stage 1 (data understanding) of any ML pipeline. Built around 5-stage pipeline: (1) data quality with ydata-profiling + missingno, (2) statistical profiling with sweetviz, (3) domain-specific (RFM, transaction patterns…
topprismdata/cultivating-ml-agent
Skill Claude CodeCodex
Use when: (1) optimizing post-processing thresholds for RMSLE-evaluated competitions, (2) considering zeroing out small predictions, (3) implementing min-sales or adaptive thresholds for time series forecasting, (4) CV improves but LB degrades after changing post-processing, (5) comparing "smart" vs "simple" zeroing…
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: