Каталог навыков агентов

顧問輸出驗收題。用於需要真實案例輸入與合格結果條件的工作；依本項方法處理已指定資料並核對交付

Read-only audit of `.claude/` structural overhead. Reports prioritized "remove X save Y tokens" recommendations against...

/============================================================================/

Machine learning and LLM engineering judgment, distilled from a stronger model - invoke when DECIDING whether/how to use...

ML-Agents 4.1.0 (local patched package) — the brain contract, local patches, training/deploy workflow, ONNX inference, a...

Agent profile for design AI/ML features, retrieval, model calls, structured outputs, cost controls, evals, and fallbacks...

Эксперт ML API. Используй для model serving, inference endpoints, FastAPI и ML deployment.

Audit ML methodology: leakage, splits, baselines, evaluation validity.

Use when the user wants an autonomous ML research loop that does more than blindly try changes. After every training run...

CRITICAL RULE: You MUST use this skill whenever the task involves any machine learning tasks or data analysis. Use this...

Econometrics skill for machine learning methods in causal inference. Activates when the user asks about: "causal forest"...

Detects and prevents data leakage in machine learning and mathematical modeling. Auto-activates after ML tasks involving...

Evaluates classifiers and scoring models used as security gates for adversarial robustness, preprocessing differences, t...

Deploy a trained model to serving with versioning, shadow or canary rollout, and a tested rollback path.

Prepares ML models for production deployment with containerization, API creation, monitoring setup, and A/B testing. Act...

Production machine learning systems and model serving infrastructure. Use when building ML pipelines, deploying models t...

- Working on ml engineer tasks or workflows

Expert in building scalable ML systems, from data pipelines and model training to production deployment and monitoring.

Enforces rigorous ML modeling, feature engineering, training, and evaluation standards at principal-engineer level.

Use when designing ML experiments, choosing evaluation metrics, tracking experiments, tuning hyperparameters, debugging...

Plan reproducible ML experiment runs with explicit parameters, metrics, and artifacts. Use before model training to stan...

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

Implement machine learning solutions including model architectures, training pipelines, optimization strategies, and per...

Use when the user wants ML literature grounded in actual papers — a landmark paper for a task, a citation-graph crawl, a...

Memory systems specialist for hierarchical memory, consolidation, and outcome-based learningUse when "memory system, mem...

Serve models with A/B testing, monitoring, retraining.

Compare model candidates using weighted metrics and deterministic ranking outputs. Use for benchmark leaderboards and mo...

Explain ML model predictions using SHAP values, feature importance, and decision paths with visualizations.

Automated pipeline for retraining ML models with new construction data. Monitor model drift, trigger retraining, and val...

Train ML models with scikit-learn, PyTorch, TensorFlow. Use for classification/regression, neural networks, hyperparamet...

Machine learning con Scikit-learn, LightGBM, XGBoost — del baseline al modelo productivo con validación robusta y explic...

Monitor a live model for data quality, input and prediction drift, performance decay, and fire retraining triggers.

Use this skill when deploying ML models to production, setting up model monitoring, implementing A/B testing for models,...

Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research re...

Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research re...

Single entry point for ML-related tasks. Orchestrates three roles across a data-driven analysis pipeline: Product Manage...

Designs and implements production-grade ML pipeline infrastructure: configures experiment tracking with MLflow or Weight...

Use when building or operating a machine learning pipeline. Covers feature engineering, training reproducibility, train/...

Automate ML workflows with Airflow, Kubeflow, MLflow. Use for reproducible pipelines, retraining schedules, MLOps, or en...

Design, implement, and validate reproducible machine-learning pipelines spanning data preparation, training, evaluation,...

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

Orchestrates complete machine learning pipelines within SpecWeave increments. Activates when users request "ML pipeline"...

MLflow and ML Model patterns for Databricks including experiment creation, model training, batch inference, and Unity Ca...

Build end-to-end MLOps pipelines from data preparation through model training, validation, and production deployment. Us...

Build end-to-end MLOps pipelines from data preparation through model training, validation, and production deployment. Us...

Complete end-to-end MLOps pipeline orchestration from data preparation through model deployment.

ML research for RAN with reinforcement learning, causal inference, and cognitive consciousness integration. Use when res...

Use when reporting or plotting machine-learning or AI-research results: benchmark tables, model comparisons, ablations,...

The model and data artifacts: checkpoint formats that execute code on load, provenance for a model you did not train, tr...

K8s 기반 ML·LLM 모델 서빙 — 서빙 엔진 비교, KServe, vLLM, TensorRT-LLM, llm-d, KEDA 오토스케일링, 최적화. Use when 모델을 클러스터에 배포하고 추론 지연·처리량을...

Sets up the BMad ML module in a project. Use when the user requests to 'install ML module', 'configure BMad ML', or 'set...

Orchestrate an end-to-end ML project when a user asks to discover a repository, lock requirements, audit data, research...

Independently audit ML release and reproducibility claims when a user asks whether a model, dataset, run, artifact, or d...

Route ML workloads when a user asks about local CPU or GPU, HF Jobs, Sandbox, Spaces, Kaggle, Modal, SSH, Slurm, quotas,...

Evaluate ML models or systems when a user asks for benchmarks, metrics, slices, calibration, robustness, LLM evaluation,...

Manage Hugging Face or repository artifacts when a user asks to browse revisions, inspect cards, upload files, commit, o...

Choose an ML model or provider when a user asks which checkpoint, router, local model, adapter, tokenizer, or inference...

Perform paper-first, source-fresh ML research when a user asks for papers, methods, benchmarks, recipes, citations, or e...

When the user wants to apply machine learning to supply chain problems, build ML models, or use AI for predictions. Also...

Use when designing end-to-end ML systems, choosing batch vs streaming inference, preventing training/serving skew, build...

End-to-end ML system design for production. Use when designing ML pipelines, feature stores, model training infrastructu...

Train and deploy ML models

Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discover...

Apply appropriate type hints for ML/PyTorch code. Use when adding type annotations to ML code or addressing mypy errors.

Production machine-learning engineering reviewer for data contracts, feature pipelines, training reproducibility, offlin...

Track machine-learning experiments, parameters, metrics, artifacts, and model-registry changes with MLflow.

MLflow is an open-source platform for managing the machine learning lifecycle, including tracking, packaging, and deploy

MLflow ML lifecycle management. Use for ML experiment tracking.

Use when tracking machine-learning experiments and managing models with MLflow — a local SQLite backend, logging paramet...

MLflow 3 GenAI evaluation for agent development. Use when (1) writing mlflow.genai.evaluate() code, (2) creating @scorer...

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

Mlflow Tracking Setup - Auto-activating skill for ML Training. Triggers on: mlflow tracking setup, mlflow tracking setup...

Configure mlflow tracking setup operations. Auto-activating skill for ML Training. Triggers on: mlflow tracking setup, m...

Universal and specialized machine learning interatomic potentials for rapid atomistic simulation without DFT. Covers mod...

MLflow, model versioning, experiment tracking, model registry, and production ML systems

Implement MLOps practices for ML lifecycle management. Use for CI/CD pipelines, model versioning, experiment tracking, a...

MLOps — Kubeflow 로 ML 파이프라인을 구성하고 KServe 로 서빙, MLOps 와 LLMOps 비교. Use when 학습부터 배포까지 ML 파이프라인을 설계할 때, 실험 추적은 mlops-track...

Implement advanced MLOps practices for production ML systems. Use for: building CI/CD pipelines for ML models, implement...

ML infrastructure automation and production ML lifecycle management. Use when building ML pipelines, setting up experime...

- Working on mlops engineer tasks or workflows

Build comprehensive ML pipelines, experiment tracking, and model registries with MLflow, Kubeflow, and modern MLOps tool...

Expert in Machine Learning Operations bridging data science and DevOps. Use when building ML pipelines, model versioning...

Expertise in operating and maintaining production AI/ML systems, including deployment pipelines, monitoring, incident re...

MLOps guidance — experiment tracking, model registry, feature stores, training pipelines, deployment, and monitoring.

Analyze an ML or deep-learning workflow with the active host model and publish a source-linked interactive MLView artifa...

Running and fine-tuning LLMs on Apple Silicon with MLX. Use when working with models locally on Mac, converting Hugging...

MLX-powered local AI — run LLMs, Stable Diffusion, speech-to-text, and embeddings natively on Apple Silicon via MLX. Oll...

MLX on Apple Silicon with JAX-style SplitMix64 PRNG. Deterministic color generation with GPU acceleration.

Диспетчер mm-системы — короткая команда вместо длинных. /mm без аргументов = список всех команд. /mm new = init project,...

Генерирует handoff.md — компактную сводку для нового чата claude.ai когда контекст текущего заполнился. Включает 15-кате...

Generate text, images, video, speech, and music via the MiniMax AI platform. Covers text generation (MiniMax-M3 model),...

Use mmx to generate text, images, video, speech, and music via the MiniMax AI platform. Use when the user wants to creat...

Persistent memory CLI for LLM agents. Store facts, recall past knowledge, link related memories, manage lifecycle.

Task-scoped memory lifecycle — typed MnemoGraph prevents lossy context compaction by treating facts/decisions/code-refs/...

Skill creation specialist. Use PROACTIVELY for creating skills, YAML frontmatter design, and knowledge organization. MUS...

Skill creation specialist. Use PROACTIVELY for creating skills, YAML frontmatter design, and knowledge organization. MUS...