machine-learning
0
llm-ai-coding-agent
้ๅฐๆจกๅๆจ็ใ้็ๆๅ่ชฟ่ฉฆ้ฒ่กๆไฝณๅ
glennfriend
data-ai
sorting
์คํ
current ordering strategy
query
all entries
refine the visible subset
machine-learning
0
gradient-accumulation-deterministic
Implement gradient accumulation that produces bit-identical results to standard batching. Use when: comparing GA vs non-GA runs, debugging training reproducibility.
Erland366
data-ai
machine-learning
0
memory-write
Persist a decision or learning to Mother-Harness long-term memory
rcmiller01
data-ai
machine-learning
0
speckit-specify
Create or update the feature specification from a natural language feature description.
Obsidian-Owl
data-ai
machine-learning
0
experiment-logger
Log ML experiments with hyperparameters, metrics, and plots; human interprets results and plans next experiments
hmyuuu
data-ai
machine-learning
0
categorical-encoder
ะญะบัะฟะตัั categorical encoding. ะัะฟะพะปัะทัะน ะดะปั ML feature engineering, one-hot, target encoding ะธ embeddings.
dengineproblem
data-ai
machine-learning
0
machine-learning-engineer
Use when user needs ML model deployment, production serving infrastructure, optimization strategies, and real-time inference systems. Designs and implements scalable ML systems with focus on reliability and performance.
404kidwiz
data-ai
machine-learning
0
paper-replication
ๆทฑๅบฆๅญฆไน ่ฎบๆๅค็ฐ็skillใๅฏไปฅ่ฏปๅpdfๅนถ่งฃๆๅ ถไธญ็ๅพ็ใๅ ฌๅผใ่กจๆ ผ็ญๅ ๅฎน๏ผ็ถๅๅ่ไธ้ข็promptsใ่งฆๅ่ฏๅ ๆฌ"ๅธฎๆๅค็ฐ่ฟ็ฏ่ฎบๆ"ใ"่ฎบๆๅค็ฐ"ใ"ๅฎ็ฐ่ฟไธชๆจกๅ"๏ผๆๅฝ็จๆทๆไพๆทฑๅบฆๅญฆไน ่ฎบๆ้่ฆ่ฝฌๅไธบPyTorchไปฃ็ ๆถใ
bahayonghang
data-ai
machine-learning
0
calibration
Applies decision thresholds for high-confidence inputs or enforces conservative safety margins for low-confidence cases
do-ops885
data-ai
machine-learning
0
moai-lang-python
Python best practices with modern frameworks, AI/ML integration, and performance optimization for 2025
kivo360
data-ai
machine-learning
0
ground-truth-management
Comprehensive guide to creating, managing, and maintaining ground truth datasets for AI evaluation including annotation, quality control, and versioning
AmnadTaowsoam
data-ai
machine-learning
0
scaling-analysis
Run scaling experiments to understand model/data/compute relationships. Use when investigating scaling laws, compute-optimal training, or model size decisions.
rHedBull
data-ai
machine-learning
0
quant-resource-patterns
Follow these patterns when implementing quant domain resources like Dataset, Signal, Alpha, Portfolio, Strategy, Universe, Backtest, or MonitoringRun in OptAIC. Use for creating DB models, DTOs, services, and tests for trading-specific entities.
colingwuyu
data-ai
machine-learning
0
time-series-models
Bayesian time series models including AR, MA, ARMA, state-space models, and dynamic linear models in Stan and JAGS.
choxos
data-ai
machine-learning
0
production-api-tester
Live testing and validation of production research API for strategy optimization loops
mberto10
data-ai
machine-learning
0
feature-extraction
Extracts vector embeddings for fairness analysis using MobileNetV3 with FairDisCo disentanglement
do-ops885
data-ai
machine-learning
0
markov-regime-features
Debugging constant Markov regime features in RL observations - when HMM probabilities show uniform values instead of dynamic regime estimates
smith6jt-cop
data-ai
machine-learning
0
mlops-patterns
Follow these patterns when implementing MLOps features in OptAIC. Use for ML model definitions (5-component structure), model instances, training/inference pipelines, model registry, and monitoring. Covers signal models, macro regime models, relevance models, and signal combining/filtering models.
colingwuyu
data-ai
machine-learning
0
exps-logistic
Documentation for the logistic regression MI estimation experiment (exps_logistic)
TerryTong-Git
data-ai
machine-learning
0
network-architecture-sizing
PPO network architecture sizing for trading models. Trigger: (1) model files are unexpectedly small/large, (2) choosing hidden_dims for training, (3) balancing model capacity vs inference speed.
smith6jt-cop
data-ai
machine-learning
0
refactorscikit-learn
Refactor Scikit-learn and machine learning code to improve maintainability, reproducibility, and adherence to best practices. This skill transforms working ML code into production-ready pipelines that prevent data leakage and ensure reproducible results. It addresses preprocessing outside pipelines, missing random_state parameters, improper cross-validation, and custom transformers not following sklearn API conventions. Implements proper Pipeline and ColumnTransformer patterns, systematic hyperparameter tuning, and appropriate evaluation metrics.
SnakeO
data-ai
machine-learning
0
training-archive-gating
Mandatory training archive with model gating (APPROVED/REVIEW/DROP). Trigger when: (1) training run completes, (2) need to decide which models to deploy, (3) want historical training reference, (4) need checkpoint recommendations for overfitting.
smith6jt-cop
data-ai