machine-learning
0
readiness-check
Classifies pre-run readiness (proceed/modify/skip) using recent load, recovery, and self-reported signals.
nadavyigal
data-ai
sorting
stars
current ordering strategy
query
all entries
refine the visible subset
machine-learning
0
ml-reviewer
WHEN: Machine Learning/Deep Learning code review, PyTorch/TensorFlow patterns, Model training optimization, MLOps checks WHAT: Model architecture review + Training patterns + Data pipeline checks + GPU optimization + Experiment tracking WHEN NOT: Data analysis only → python-data-reviewer, General Python → python-reviewer
physics91
data-ai
machine-learning
0
model-version-protocol
Model-trader version compatibility protocol: Embed version metadata in checkpoints, validate at load time. Trigger when: (1) training and live trading versions diverge, (2) models fail to load, (3) action interpretation issues.
smith6jt-cop
data-ai
machine-learning
0
hyperparam-sweep
Systematically search hyperparameter space. Use when tuning learning rate, batch size, or other hyperparameters.
rHedBull
data-ai
machine-learning
0
exploration-strategies
Master ε-greedy, UCB, curiosity-driven, RND, intrinsic motivation exploration
tachyon-beep
data-ai
machine-learning
0
debugtensorflow
Debug TensorFlow and Keras issues systematically. This skill helps diagnose and resolve machine learning problems including tensor shape mismatches, GPU/CUDA detection failures, out-of-memory errors, NaN/Inf values in loss functions, vanishing/exploding gradients, SavedModel loading errors, and data pipeline bottlenecks. Provides tf.debugging assertions, TensorBoard profiling, eager execution debugging, and version compatibility guidance.
SnakeO
data-ai
machine-learning
0
position-sizing-action-space
7-action space with position sizing (25/50/75%) + small account simulation. Trigger when: (1) model needs sizing decisions, (2) training for <$25K accounts, (3) upgrading obs_dim 5600->5900.
smith6jt-cop
data-ai
machine-learning
0
unsloth-lora
Configuring and optimizing 16-bit Low-Rank Adaptation (LoRA) and Rank-Stabilized LoRA (rsLoRA) for efficient LLM fine-tuning using triggers like lora, qlora, rslora, rank selection, lora_alpha, lora_dropout, and target_modules.
cuba6112
data-ai
machine-learning
0
policy-gradient-methods
Master REINFORCE, PPO, TRPO - direct policy optimization with trust regions
tachyon-beep
data-ai
machine-learning
0
benchmark-framework
Rigorous A/B/C testing framework for empirically evaluating reasoning patterns. Use when you need data-driven pattern selection, want to quantify trade-offs between patterns, or need to validate claims about which cognitive methodology performs best. Enables scientific measurement of quality, cost, and time trade-offs across ToT, BoT, SRC, HE, AR, DR, AT, RTR, and NDF patterns.
kimasplund
data-ai
machine-learning
0
production-eval-strategy
Strategies for evaluating agents in production - sampling, baselines, and regression detection
nexus-labs-automation
data-ai
machine-learning
0
torchserve
Model serving engine for PyTorch. Focuses on MAR packaging, custom handlers for preprocessing/inference, and management of multi-GPU worker scaling. (torchserve, mar-file, handler, basehandler, model-archiver, inference-api)
cuba6112
data-ai
machine-learning
0
regression-models
Bayesian regression models including linear, logistic, Poisson, negative binomial, and robust regression with Stan and JAGS implementations.
choxos
data-ai
machine-learning
0
account-aware-training
Add account state (P&L, win rate, drawdown) to RL observations + drawdown penalty in rewards. Trigger when: (1) model needs account awareness, (2) training should penalize drawdowns, (3) upgrading obs_dim 5300→5600.
smith6jt-cop
data-ai
machine-learning
0
model-architect
深度学习模型结构设计专家。当用户询问“模型设计”“网络结构”“模块划分”“数据流” “损失函数”等问题，或在训练问题中尚未明确模型结构时使用。
HuangTM23
data-ai
machine-learning
0
eval-recipes-runner
Run Microsoft's eval-recipes benchmarks to validate amplihack improvements against baseline agents. Activates when testing with eval-recipes, running evals, or benchmarking changes.
rysweet
data-ai
machine-learning
0
balls-mode
Decomposed reasoning with explicit confidence scoring. Use for complex decisions, debugging failures, and architectural choices where tracking uncertainty prevents wasted effort.
DammianMiller
data-ai
machine-learning
0
multi-timeframe-training
Train RL models across multiple timeframes with resampling. Trigger when: (1) multi-timeframe training, (2) resampling data, (3) creating 1Hour/4Hour models.
smith6jt-cop
data-ai
machine-learning
0
debugscikit-learn
Debug Scikit-learn issues systematically. Use when encountering model errors like NotFittedError, shape mismatches between train and test data, NaN/infinity value errors, pipeline configuration issues, convergence warnings from optimizers, cross-validation failures due to class imbalance, data leakage causing suspiciously high scores, or preprocessing errors with ColumnTransformer and feature alignment.
SnakeO
data-ai
machine-learning
0
load-anomaly-guard
Detects unsafe training load spikes (>20-30% week-over-week) and emits safety flags. Use in nightly background jobs or when reviewing weekly training volume with conservative adjustment recommendations.
nadavyigal
data-ai
machine-learning
0
atft-training
Run and monitor ATFT-GAT-FAN training loops, hyper-parameter sweeps, and safety modes on A100 GPUs.
wer-inc
data-ai
machine-learning
0
train-debug
Interactive diagnostic workflow for training problems. Use when training is failing, loss is stuck, gradients explode, NaN occurs, or convergence is poor.
rHedBull
data-ai