Machine Learning Agent Skills for Real ML Work
Machine learning skills help an AI agent carry out the steps of a data-mining process, from framing a prediction problem to monitoring a deployed model. Skills in this topic cover six sub-topics: problem framing (what prediction would change a decision, and what a dumb baseline scores), data (what the model is allowed to see, and what must be held out), training (fitting a model without fooling yourself on the training set), evaluation (numbers that would still hold on next week's data), deployment (getting predictions into the product), and monitoring (models rot; someone has to notice). Use the ranked list by finding the sub-topic that matches your current step, then pick a skill whose description addresses that step directly. The list is ordered by observed search demand, with direct matches first and a cap on any single publisher.
8 to start with21 top options
Start with these.
Machine learning follows a data-mining process: frame the problem, prepare data, train, evaluate, then deploy and watch drift.
These are the closest matches for this work. Start with the first one and open it to install.
- Rank 01View Agent SkillDirect
ml-pipeline-workflow
Builds end-to-end MLOps pipelines from data ingestion and preparation through model training, validation, deployment, and monitoring, with DAG orchestration patterns and reference guides.
10,692 · popularity - Rank 02View Agent SkillDirect
finetuning
OfficialFine-tune models on Microsoft Foundry using SFT (supervised), DPO (preference), or RFT (reinforcement with graders). Covers dataset preparation, training job submission, deployment, and evaluation. USE FOR: fine-tune, SFT, DPO, RFT, training data, grader, distillation, fine-tuned model, training job, large file upload, calibrate grader, deploy fine-tuned model, evaluate fine-tuned model. DO NOT USE FOR: general model deployment without fine-tuning (use deploy-model), agent creation (use agents), prompt optimization without training (use prompt-optimizer).
- Rank 03View Agent SkillDirect
azure-ai-ml-py
Official| Azure Machine Learning SDK v2 for Python. Use for ML workspaces, jobs, models, datasets, compute, and pipelines. Triggers: "azure-ai-ml", "MLClient", "workspace", "model registry", "training jobs", "datasets".
- Rank 04View Agent SkillDirect
agent-platform-eval-flywheel
Official>- Measures and improves the quality of AI models and agents on Google Cloud using the Eval Quality Flywheel methodology. Use when evaluating an agent or model, building an eval dataset, picking or writing evaluation metrics, analyzing failures, comparing results before and after a fix, or when guidance is needed on Agent Platform eval methodology — including dataset schema, LLM-as-judge scoring, and common failure causes. For fine-tuning, use agent-platform-tuning. For general production deployment, use agent-platform-deploy.
- Rank 05View Agent SkillDirect
bigquery-ai-ml
Official>- Leverages BigQuery's built-in machine learning and GenAI capabilities for advanced data analytics. Use when you need to write SQL queries that perform time-series forecasting, predict values, detect outliers or anomalies, find key drivers, perform semantic search or vector search, classify text, calculate similarity, summarize content, translate language, evaluate models, filter by semantic conditions, or leverage generative AI capabilities in BigQuery. Do not use for general BigQuery dataset, table, or job management requests.
- Rank 06View Agent SkillDirect
microsoft-foundry
OfficialBuild, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and resources end to end. USE FOR: azd ai agent, azd provision/deploy, hosted agent scaffold/develop/run/deploy/troubleshoot, prompt agent create, create agent, update agent, add tool to agent, invoke agent, agent.yaml, evaluate agent, batch eval, continuous eval, continuous monitoring, agent CI/CD, optimize prompt, improve prompt, prompt optimizer, optimize agent instructions, Agent Optimizer scaffold, dataset curation from traces, deploy model, model fine-tuning (SFT/DPO/RFT), Foundry project, RBAC, role assignment, permissions, quota, capacity, region, deployment failure, AI Services, create Foundry resource, knowledge index, customize deployment, onboard, availability, training-data, grader, distillation, large file upload. DO NOT USE FOR: Azure Functions, App Service, general Azure deploy (use azure-deploy), general Azure prep (use azure-prepare).
- Rank 07View Agent SkillDirect
agent-platform-model-registry
Official>- Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
- Rank 08View Agent SkillDirect
agent-platform-deploy
Official>- Deploy open models or custom weights from Model Garden to Agent Platform endpoints, check the status of an in-progress deployment operation, or clean up resources by undeploying models and deleting endpoints. Use when asked to actively deploy a model, list the Model Garden CATALOG of available models, check if a specific model is deployable (`gcloud ai model-garden models list-deployment-config`), query deployment cost, troubleshoot deployment errors (like quota limits), or undeploy/clean up endpoints. Also use when copying and deploying a 1P Tuned Model. Don't use for pure listing/discovery questions of the form "is X deployed?", "list my endpoints", or "which regions have models running?" — for those use `agent-platform-endpoint-management`. Don't use for public Vertex AI deployments (use the `vertex-deploy` skill) or for running model evaluations (use the `agent-platform-eval-flywheel` skill).
Explore 13 more Agent Skills
- Rank 09View Agent SkillPossible
google-cloud-solution-agentic-ai-data-science-workflow
Official>- Designs a tailored multi-product agentic data science architecture on Google Cloud that incorporates opinionated best practices. Use when architecting multi-product solutions for agent-based data analytics or ML workloads. Don't use for simple queries, non-agentic pipelines, general cloud reviews, or writing agent code.
Needs (stated): Network access
- Rank 10View Agent SkillPossible
ai-research-reproduction
NotableRigor Reproduce compatible skill slug for README-first deep learning repository reproduction. Use when the user wants an end-to-end, minimal-trustworthy flow that reads the repository first, selects the smallest documented inference or evaluation target, coordinates intake, setup, trusted execution, optional trusted training, optional repository analysis, and optional paper-gap resolution, enforces conservative patch rules, records evidence assumptions deviations and human decision points, and writes the standardized `repro_outputs/` bundle. Do not use for paper summary, generic environment se
310,973 · popularity - Rank 11View Agent SkillPossible
minimal-run-and-audit
NotableRigor Run skill for README-first deep learning repo reproduction. Use when the task is specifically to capture or normalize evidence from the selected smoke test or documented inference or evaluation command and write standardized `repro_outputs/` files, including patch notes when repository files changed. Do not use for training execution, initial repo intake, generic environment setup, paper lookup, target selection, hidden scientific-meaning changes, or end-to-end orchestration by itself.
450,032 · popularity - Rank 12View Agent SkillPossible
run-train
Rigor Train skill for deep learning research repositories. Use when a documented or selected training command should be run conservatively for startup verification, short-run verification, full kickoff, or resume, with command, config, seed, log, checkpoint, status, and metric evidence written to…
310,547 · popularity - Rank 13View Agent SkillPossible
explore-run
Rigor Improve / Rigor Explore run leaf skill for bounded exploratory evidence in deep learning research repositories. Use when the researcher explicitly authorizes exploratory runs such as small-subset validation, short-cycle guess-and-check, batch sweeps, idle-GPU search, or quick…
310,529 · popularity - Rank 14View Agent SkillPossible
analyze-project
Rigor Analyze / Rigor Audit read-only skill for deep learning research repositories. Use when the user wants to read and understand a repository, inspect model structure and training or inference entrypoints, review configs and insertion points, or flag suspicious implementation patterns without…
311,205 · popularity - Rank 15View Agent SkillPossible
safe-debug
Rigor Debug / Rigor Audit skill for deep learning research work. Use when the user pastes a traceback, terminal error, CUDA OOM, checkpoint load failure, shape mismatch, NaN loss symptom, or training failure and wants conservative diagnosis before any patching, with debug fixes clearly separated…
310,743 · popularity - Rank 16View Agent SkillPossible
repo-intake-and-plan
Rigor Intake helper for README-first deep learning repo reproduction. Use when the task is specifically to scan a repository, read the README and common project files, extract documented commands, classify inference, evaluation, and training candidates, and return the smallest trustworthy…
450,252 · popularity - Rank 17View Agent SkillPossible
env-and-assets-bootstrap
Rigor Setup skill for README-first deep learning repo reproduction. Use when the task is specifically to prepare a conservative conda-first environment, checkpoint and dataset path assumptions, cache location hints, and setup notes before any run on a README-documented repository. Do not use for…
450,087 · popularity - Rank 18View Agent SkillPossible
paper-context-resolver
Rigor Paper Context helper for README-first deep learning repo reproduction. Use only when the README and repository files leave a narrow reproduction-critical gap and the task is to resolve a specific paper detail such as dataset split, preprocessing, evaluation protocol, checkpoint mapping, or…
451,036 · popularity - Rank 19View Agent SkillPossible
azure-aigateway
OfficialConfigure Azure API Management as an AI Gateway for AI models, MCP tools, and agents. WHEN: semantic caching, token limit, content safety, load balancing, AI model governance, MCP rate limiting, jailbreak detection, add Azure OpenAI backend, add AI Foundry model, test AI gateway, LLM policies,…
544,026 · popularity - Rank 20View Agent SkillPossible
airunway-aks-setup
OfficialSet up AI Runway on AKS — from bare cluster to running model. Covers cluster verification, controller install, GPU assessment, provider setup, and first deployment. WHEN: \"setup AI Runway\", \"onboard AKS cluster\", \"install AI Runway\", \"airunway setup\", \"deploy model to AKS\", \"GPU…
337,927 · popularity - Rank 21View Agent SkillPossible
developing-genkit-js
Develop AI-powered applications using Genkit in Node.js/TypeScript. Use when the user asks about Genkit, AI agents, flows, or tools in JavaScript/TypeScript, or when encountering Genkit errors, validation issues, type errors, or API problems.
58,870 · popularity
What this topic covers
Each sub-topic groups Agent Skills for a specific situation.
- Problem
- What prediction would change a decision, and what a dumb baseline scores.
- Data
- What the model is allowed to see, and what must be held out.
- Training
- Fit a model without fooling yourself on the training set.
- Evaluation
- Numbers that would still hold on next week's data.
- Deployment
- Get predictions into the product.
- Monitoring
- Models rot; someone has to notice.
Frequently asked questions
- How is the ranked list ordered?
- The list is ranked by observed search demand. Direct matches to the topic appear first, and there is a cap on how many skills any single publisher can occupy.
- What does the machine learning topic cover?
- It covers the data-mining process: frame the problem, prepare data, train, evaluate, then deploy and watch drift. The sub-topics are problem, data, training, evaluation, deployment, and monitoring.
- Which sub-topic should I start with?
- Start with the sub-topic that matches your current step in the process. If you have not framed the prediction or established a dumb baseline, begin with problem; if you already have a model, look at evaluation, deployment, or monitoring.
How to install an Agent Skill
Start with the first skill on this page. Claude Code reads a SKILL.md once it is in the skills directory:
- Claude Code — copy the SKILL.md for ml-pipeline-workflow into ~/.claude/skills/ml-pipeline-workflow/ for yourself, or .claude/skills/ml-pipeline-workflow/ to share it with a project.
- From the registry — run npx skills add wshobson/agents@ml-pipeline-workflow.
- Or download ml-pipeline-workflow from its source and place that SKILL.md in the directory above.
How to choose Check the source and the skill’s own instructions before you install. Official and Notable describe where a skill comes from.