Skill Claude CodeCodex
Tests and evaluates any Claude Code skill for structural validity, quality, and trigger accuracy. Implements the cc-plugin-eval 4-stage pipeline (Analysis → Generation → Execution → Evaluation) and the 4D scoring rubric (Documentation/Code/Completeness/Usability 25% each). Use before packaging or deploying any skill.
topprismdata/cultivating-ml-agent
Agent Claude Code
Build a submission for a Kaggle/MLE-Bench competition. Iterates on models and produces submission.csv.
topprismdata/cultivating-ml-agent
Agent Claude Code
Validate a submission's format and run mlebench grade. Catches errors before submission.
topprismdata/cultivating-ml-agent
Command Claude Code
Update the dev docs triple for the current task.
topprismdata/cultivating-ml-agent
Command Claude Code
Create dev docs triple (plan/context/tasks) for a multi-step task.
topprismdata/cultivating-ml-agent
Command Claude Code
Run the Grader agent on the current submission for a competition.
topprismdata/cultivating-ml-agent
Command Claude Code
Apply /meta-optimize suggestions after cross-model jury approval. Gates memory writes through external review.
topprismdata/cultivating-ml-agent
Command Claude Code
Analyze memory/ for staleness, contradictions, missing entries. Read-only.
topprismdata/cultivating-ml-agent
Command Claude Code
Get an independent second opinion from an external LLM (agy/gemini/codex/ollama) on a decision.
topprismdata/cultivating-ml-agent
Skill Claude CodeCodex
Correct implementation of adversarial validation for Kaggle competitions. Use when: (1) Selecting training samples that match test distribution, (2) Reducing synthetic data artifacts by filtering, (3) Preparing data subsets for better generalization. Covers train vs test classification, sample selection method, and…
topprismdata/cultivating-ml-agent
Skill Claude CodeCodex
Agent Nurture Framework: a systematic methodology for training AI agents from novice to expert through conversational knowledge crystallization. Use when: (1) designing an agent training pipeline, (2) consolidating fragmented skills into organized knowledge architecture, (3) integrating external learning resources…
topprismdata/cultivating-ml-agent
Skill Claude CodeCodex
Use when: (1) Starting a long-running experiment that may span multiple sessions/disconnects, (2) Resuming work after a break and needing to recover context, (3) Handing off to another agent or session, (4) You realize you've lost track of what was tried and why. Provides a structured 4-file session memory system that…
topprismdata/cultivating-ml-agent
Skill Claude CodeCodex
Use when encountering a new ML technique not covered by existing 43+ skills, when needing citations for a paper/report, when comparing recent (last 6 months) approaches to a known problem, or when the existing knowledge feels stale. Triggers on phrases like "latest paper on X", "SOTA in Y", "what does the literature…
topprismdata/cultivating-ml-agent
Skill Claude CodeCodex
AutoGluon-First Strategy: Always run AutoGluon bestquality preset as the first step in any tabular ML competition (5-15 min baseline). Validated 3/4 times vs manual ensembles on small/medium tabular datasets. Use when: (1) Starting any new tabular competition, (2) Need a strong baseline in 1M rows with limited RAM)…
topprismdata/cultivating-ml-agent
Skill Claude CodeCodex
AutoGluon preset selection strategy: when to use medium/good/high/bestquality, when EDA is unnecessary, and how to tune within a preset. Validated on s6e7 (AG highquality 600s → OOF=0.8739, LB=0.87458, gap=0.0007 — perfect alignment). Use when: (1) Deciding which AutoGluon preset to start with, (2) Wondering whether…
topprismdata/cultivating-ml-agent
Skill Claude CodeCodex
CatBoost-First Strategy: When manual GBDT work is needed, start with CatBoost (not LightGBM or XGBoost). CatBoost has native categorical feature handling, robust to overfitting, and consistently outperforms other GBDTs on small/medium tabular datasets. Use when: (1) AutoGluon is not available or too slow, (2) Need to…
topprismdata/cultivating-ml-agent
Skill Claude CodeCodex
Extract reusable knowledge from work sessions into new Claude Code skills. Use when: (1) /claudeception command to review session, (2) "save this as a skill" or "extract a skill", (3) "what did we learn?", (4) After non-obvious debugging, workarounds, trial-and-error discovery, or counterintuitive solutions. Do NOT…
topprismdata/cultivating-ml-agent
Skill Claude CodeCodex
Use when: (1) Entering a Kaggle Code Competition that requires notebooks with no internet access, (2) Need to fork a public baseline that depends on external artifact datasets (pre-trained models, feature matrices, wheels), (3) Your fork fails with "module not found" or "file not found" errors, (4) Need to identify…
topprismdata/cultivating-ml-agent
Skill Claude CodeCodex
Use when: (1) You need to rapidly iterate across MANY competing approaches in a single Kaggle competition (NeuroGolf-style: 7+ different public kernels forked in <2 hours), (2) You must decide which public dataset/kernel to spend your limited submission quota on, (3) Your highest-scoring submission might be a public…
topprismdata/cultivating-ml-agent
Skill Claude CodeCodex
Use when context window is getting crowded, when dealing with long training logs, or when preparing prompts with mixed-priority content (system / task / skills / examples). Triggers when assembling prompts >4000 chars, or when observing "Lost in the Middle" symptoms (model ignores mid-prompt content).
topprismdata/cultivating-ml-agent
Skill Claude CodeCodex
Use when: (1) a new submission scores worse than baseline and the reason is unclear, (2) multiple changes were made simultaneously (new model + new post-processing + new features), (3) need to isolate which component caused a regression, (4) CV improves but LB degrades, (5) comparing "smart" vs "simple" approaches…
topprismdata/cultivating-ml-agent
Skill Claude CodeCodex
Use when starting a new ML task that structurally resembles a known competition (recommendation ↔ retail, demand ↔ supply, churn ↔ fraud, segmentation ↔ classification). Triggers when your task feels "not novel" — there is likely a top solution you can borrow features from. Especially valuable at the start of a…
topprismdata/cultivating-ml-agent
Skill Claude CodeCodex
CV-LB Gap Acknowledgment: CV improvement does NOT equal LB improvement. This is one of the most important MLOps principles. Use when: (1) OOF score keeps improving but LB score plateaus or drops, (2) Spending days tuning hyperparameters without LB improvement, (3) Comparing models on CV only without LB validation, (4)…
topprismdata/cultivating-ml-agent
Skill Claude CodeCodex
Avoid applying domain knowledge constraints that hurt ML model performance. Use when: (1) Considering medical/physical/logical constraints on training data, (2) Adversarial validation AUC changes significantly after applying constraints (>0.10 shift), (3) CV score drops after adding "reasonable" domain rules, (4)…
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: