Best MLOps skills for Claude Code, Codex and other agents.

Finds or validates a usable SageMaker execution role before deploying or training, so scripts do not try to create IAM roles they lack permission to create.

huggingface/skills

Comprehensive Python programming reference covering syntax, concurrency, networking, databases, ML/LLM development, and HPC.

crazyguitar/pysheeet

Sets up an isolated Python environment with a supported interpreter and current boto3 before any SageMaker deployment, training or AWS automation code runs.

huggingface/skills

Operates the Inspire ML platform through its local `inspire` CLI: picking account, workspace and resources, launching notebooks, jobs and services, then cleaning up.

realZillionX/InspireSkill

Deploys SageMaker endpoints with autoscaling, CloudWatch alarms and tags on by default, using scripts for real-time, scale-to-zero and async setups.

huggingface/skills

Designs ML pipeline infrastructure: experiment tracking with MLflow or Weights & Biases, Kubeflow and Airflow orchestration, Feast feature stores and model validation gates.

Jeffallan/claude-skills

Guides an agent through tracking ML experiments with W&B: run logging, config capture, hyperparameter sweeps, artifacts and a model registry.

Orchestra-Research/AI-Research-SKILLs

Analyze a full code repository and generate one resume-ready project description grounded in repository evidence.

Ssabby1/repo-to-resume-tailor

Deploys open models or custom weights from Model Garden to Agent Platform endpoints, checks deployment status and cleans up endpoints, confirming before any change.

google/skills

Builds and maintains templates/index.mcp.json for Comfy Cloud MCP tools.

Comfy-Org/workflow_templates

Runs ML training and batch jobs across clouds with SkyPilot, using spot instances, automatic region selection and managed recovery to cut GPU cost.

Orchestra-Research/AI-Research-SKILLs

Shows how to launch distributed Megatron-LM training on a SLURM cluster: sbatch skeleton, torch.distributed.run setup, CUDA_DEVICE_MAX_CONNECTIONS rules and failure diagnosis.

NVIDIA/Megatron-LM

Register a new AI model in DroidGear's model registry by fetching specs from models.dev.

Sunshow/droidgear

Add, change or verify a Nexus LLM model definition — the registry entry, the provider default, and proof the model id actually works against the live endpoint.

ProfSynapse/nexus

Declare the pipeline from data source to predictor as a skrub DataOps graph.

probabl-ai/skills

Sets up and maintains AzureML-ready Python projects as uv workspaces with devcontainers, a Makefile and job YAML, so local runs match cloud jobs and experiments stay reproducible.

Kilo-Org/kilo-marketplace

Guides an agent through designing an MLOps pipeline that covers data preparation, training, validation and deployment, with DAG orchestration and reference guides.

wshobson/agents

Covers logging and viewing training metrics, histograms, model graphs, embeddings and profiles with TensorBoard in PyTorch and TensorFlow projects.

Orchestra-Research/AI-Research-SKILLs

A skill your agent uses to generate well-branded interfaces and assets for beava (beava.dev, an open-source single-binary feature server for stream processing), either for production or throwaway…

beava-dev/beava

Evaluate one learner with skore.evaluate. An agent skill from probabl-ai/skills.

probabl-ai/skills

Guide to renting GPUs on Lambda Labs for ML training and inference: on-demand instances, 1-Click Clusters, SSH access, persistent filesystems and alternatives.

Orchestra-Research/AI-Research-SKILLs

Tracks ML experiments, versions models in the MLflow registry and covers deployment and reproducibility, with autologging for common frameworks.

Orchestra-Research/AI-Research-SKILLs

Shows how to log ML runs, configs, metrics and media with SwanLab and view them in cloud, local or self-hosted dashboards.

Orchestra-Research/AI-Research-SKILLs

how to use the edit command properly

omegaml/omegaml

Turns build, implement or design requests for ML pipelines into validated implementation plans grounded in a knowledge base or fetched framework documentation.

Leeroo-AI/superml

World-class ML engineering skill for productionizing ML models, MLOps, and building scalable ML systems.

davila7/claude-code-templates

Read-only audit of one persisted skore report: audit/NN<stem.py (jupytext percent), 1:1 with experiments/ and journal/.

probabl-ai/skills

Azure Machine Learning SDK v2 for Python. An agent skill from microsoft/skills.

microsoft/skills

ML engineering skill for productionizing models, building MLOps pipelines, and integrating LLMs.

alirezarezvani/claude-skills

Azure Weights & Biases SDK for .NET. An agent skill from microsoft/skills.

microsoft/skills

OCI Data Science service patterns including Jobs, Pipelines, Model Catalog, authentication, and the ADS SDK beyond AQUA.

oracle/accelerated-data-science

Data pipelines, feature stores, and embedding generation for AI/ML systems.

ancoleman/ai-design-components

Machine learning engineer expert for PyTorch, scikit-learn, model evaluation, and MLOps

RightNow-AI/openfang

Build, test, and debug Hermes Agent RL environments for Atropos training.

Tommy-yw/RunbookHermes

Establish model registry standards, governance controls, metadata schemas, approvals, and lifecycle policies for enterprise AI deployments.

sickn33/agentic-awesome-skills

Strategic guidance for operationalizing machine learning models from experimentation to production.

ancoleman/ai-design-components

Call model APIs through @prismshadow/mmsp (MMSP) — streaming text generation, image generation, speech synthesis, embeddings and the supported-model registry with one client.

Prism-Shadow/penguin-harness

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

aiskillstore/marketplace

Curate LLM training data: dedupe, filter, PII redaction. An agent skill from Luciole-Studio/Misaka-Agent.

Luciole-Studio/Misaka-Agent

Agent Platform Model Registry Management. An agent skill from google/skills.

google/skills

Copy skore reports between local, Hub, and MLflow with skore sync, and optionally switch the recorded upload destination.

probabl-ai/skills

Use during planning, implementation, PR review, or /qv-qip-triage when a change may affect public SDK API, native dependency, plugin contract, model registry contract, runtime, transport, storage…

tetherto/qvac

Neo4j Graph Data Science (GDS) embedded plugin via Python client or Cypher — covers graphdatascience client 2.x, GraphDataScience, gds.graph.project.native, gds.graph.project.cypher, snakecase…

neo4j-contrib/neo4j-skills

Curated download URLs and target directories, organized by family (Flux, WAN, LTX, Qwen, Z-Image, SD15/SDXL), for every model the comfyui-mcp skills reference, covering checkpoints, VAEs, text…

artokun/comfyui-mcp

Design and implement a complete ML pipeline for: $ARGUMENTS. An agent skill from aiskillstore/marketplace.

aiskillstore/marketplace

Shared review framework that every domain reviewer (pci, oracle, gov, edtech, healthcare, mlops, etc.) MUST follow.

avelikiy/great_cto

Read-only health check that a brand profile is production-ready: required fields, voice and audience completeness, guardrails, compliance-jurisdiction coverage, connector configuration and MCP…

indranilbanerjee/digital-marketing-pro

Speed up long-sequence transformer training and inference. An agent skill from Luciole-Studio/Misaka-Agent.

Luciole-Studio/Misaka-Agent