majiayu000/claude-skill-registry - Page 34

l0

L0 regularization for neural network sparsification and intelligent sampling - used in survey calibration

label-studio-setup

Comprehensive guide for Label Studio setup and usage on local server for data labeling and annotation.

langevin-dynamics

Layer 5: SDE-Based Learning Analysis via Langevin Dynamics

learn-voice

Train RVC voice models from artist names. Full pipeline: YouTube search, download, stem separation, preprocessing, training, and model indexing. Builds a library of singing voices organized by category (voice/instrument).

leela-ai

Manufacturing Intelligence — Leela AI applies MOOLLM to industry

Source text: Undetermined

linear-solvers

Select and configure linear solvers for systems Ax=b in dense and sparse problems. Use when choosing direct vs iterative methods, diagnosing convergence issues, estimating conditioning, selecting preconditioners, or debugging stagnation in GMRES/CG/BiCGSTAB.

llm-fine-tuning

Fine-tune large language models efficiently using LoRA, QLoRA, and PEFT methods. Use for domain adaptation, instruction tuning, task-specific optimization, and parameter-efficient training of LLMs.

llm-fine-tuning

LoRA/QLoRA/PEFT fine-tuning workflows, dataset formatting, adapter merging, and eval loops. Covers Hugging Face TRL/PEFT patterns, chat template handling, and common training pitfalls.

llm-pretraining

Plan and execute large language model pretraining from data preparation to checkpoint management

longbridge-ml-strategy

Machine-learning prediction strategy framework via Longbridge Securities — walk-forward rolling training with feature engineering (MACD, RSI, Bollinger Band width, volume change rate) and a scikit-learn classifier (Random Forest / Gradient Boosting); retrains…

bio-epitranscriptomics-m6a-differential

Identify differential m6A methylation between conditions from MeRIP-seq. Use when comparing epitranscriptomic changes between treatment groups or cell states.

mediapipe-usage

Summarizes Google MediaPipe usage for web: Pose Landmarker with @mediapipe/tasks-vision, landmark indices, running modes, and patterns for real-time video. Use when working with MediaPipe, pose detection, body landmarks, or @mediapipe/tasks-vision.

metaxy

This skill should be used when the user asks to "define a feature", "create a BaseFeature class", "track feature versions", "set up metadata store", "field-level lineage", "FieldSpec", "FeatureDep", "run metaxy CLI", "metaxy migrations", or needs guidance on…

metaxy

This skill should be used when the user asks to "define a feature", "create a BaseFeature class", "track feature versions", "set up metadata store", "field-level dependencies", "FieldSpec", "FeatureDep", "run metaxy CLI", "metaxy migrations", or needs…

microimpute

ML-based variable imputation for survey data - used in policyengine-us-data to fill missing values

ml-antipattern-validator

Prevents 30+ critical AI/ML mistakes including data leakage, evaluation errors, training pitfalls, and deployment issues. Use when working with ML training, testing, model evaluation, or deployment.

ml-deployment-helper

Prepares ML models for production deployment with containerization, API creation, monitoring setup, and A/B testing. Activates for "deploy model", "production deployment", "model API", "containerize model", "docker ml", "serving ml model", "model monitoring",…

ml-engineer

Production machine learning systems and model serving infrastructure. Use when building ML pipelines, deploying models to production, implementing feature stores, or optimizing inference performance.

ml-engineer

Build production ML systems with PyTorch 2.x, TensorFlow, and modern ML frameworks. Implements model serving, feature engineering, A/B testing, and monitoring. Use PROACTIVELY for ML model deployment, inference optimization, or production ML infrastructure.

ml-experiment-lifecycle

Use when designing ML experiments, choosing evaluation metrics, tracking experiments, tuning hyperparameters, debugging training, ensuring reproducibility, or building ML pipelines. Covers W&B/MLflow integration, seed management, deterministic training, HPO…

ml-experiment-tracker

Guides ML experiment logging, versioning, and reproducibility using tools like MLflow, Weights & Biases, and DVC for systematic model development.

ml-expert

Implement machine learning solutions including model architectures, training pipelines, optimization strategies, and performance improvements. This skill spawns a specialist ML implementation agent...

ml-model-deployment

LLM and ML model serving with vLLM, TGI, Triton, and TorchServe. Covers quantization formats (GPTQ/AWQ/GGUF), batching strategies, latency optimization, and inference framework selection.

ml-pipeline

Coordinate ML-related analysis work by defining the problem, identifying required data, planning extraction, analyzing results, and producing recommendations or follow-up implementation tasks.

ml-pipeline

Coordinate ML-related analysis work by defining the problem, identifying required data, planning extraction, analyzing results, and producing recommendations or follow-up implementation tasks.

ml-pipeline

ML pipeline orchestrator — single entry point for ML-related tasks. Coordinates ML Engineer (analysis, modeling, recommendations), SRE Engineer (production data extraction), and Product Manager (task formulation). Domain context from CLAUDE.md. MVP flow:…

ml-pipeline-orchestration

ML pipeline design with Metaflow, Kubeflow, and ZenML including GPU steps, artifact tracking, and production patterns.

ml-pipeline-orchestrator

Orchestrates complete machine learning pipelines within SpecWeave increments. Activates when users request "ML pipeline", "train model", "build ML system", "end-to-end ML", "ML workflow", "model training pipeline", or similar. Guides users through data…

ml-researcher

ML research for RAN with reinforcement learning, causal inference, and cognitive consciousness integration. Use when researching ML algorithms for RAN optimization, implementing reinforcement learning agents, developing causal models, or enabling AI-driven…

ml-system-design

Use when designing end-to-end ML systems, choosing batch vs streaming inference, preventing training/serving skew, building data flywheels, or planning ML infrastructure scaling.

ml-system-design

End-to-end ML system design for production. Use when designing ML pipelines, feature stores, model training infrastructure, or serving systems. Covers the complete lifecycle from data ingestion to model deployment and monitoring.

mlflow

ML lifecycle management with MLflow. Track experiments, package models, manage registries, and deploy models. Use for ML operations, experiment tracking, and model deployment.

mlflow-patterns

ML experiment tracking, model registry, and deployment with MLflow for reproducible machine learning workflows.

mlops-advanced

Implement advanced MLOps practices for production ML systems. Use for: building CI/CD pipelines for ML models, implementing continuous training and monitoring, managing model registries and versioning, deploying with blue-green and canary strategies,…

mlops-dag-builder

Design DAG-based MLOps pipeline architectures with Airflow, Dagster, Kubeflow, or Prefect. Activates for DAG orchestration, workflow automation, pipeline design patterns, CI/CD for ML. Use for platform-agnostic MLOps infrastructure - NOT for SpecWeave…

mlops-engineer

ML infrastructure automation and production ML lifecycle management. Use when building ML pipelines, setting up experiment tracking, implementing CI/CD for models, or managing model deployments.

mlops

Implement MLOps practices for ML lifecycle management. Use for CI/CD pipelines, model versioning, experiment tracking, automated training, deployment automation, monitoring, and production ML workflows.

model-bias-fairness

Model Bias occurs when an AI system produces results that are systematically prejudiced against certain individuals or groups. Fairness is the practice of ensuring that the model's predictions do not

model-bias-and-fairness

Identifying, measuring, and mitigating algorithmic bias to ensure equitable outcomes in AI systems.

model-compression

Pruning, knowledge distillation, quantization-aware training, and edge deployment patterns for reducing model size and latency.