ML Experimentation — Agent Skill by Microsoft

From the author

Machine learning experimentation reference for model-experimentation conventions, experiment tracking and reproducibility, dataset and model abstractions, ML engagement fundamentals, and model-production readiness. Use when standing up ML experimentation infrastructure or assessing whether a trained model is ready for production.

— the description by Microsoft

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

This skill provides a structured reference for machine learning experimentation, focusing on reproducibility, environment management, and production readiness. It helps teams establish consistent conventions for repository structure, dataset and model abstractions, and evaluation flows. By grounding ML projects in established engineering playbooks, it ensures that experiments are comparable and that models are assessed against clear criteria before moving to production.

What it does

Provides conventions for virtual environment management and repository structure.
Outlines requirements for experiment tracking and reproducibility.
Defines dataset and model abstractions to ensure consistency.
Offers a checklist for assessing ML engagement fundamentals.
Provides a structured readiness review for moving models to production.
Clarifies ownership boundaries between experimentation, data operations, and other domains.

When to use it

When setting up infrastructure for a new machine learning project.
When establishing repository and environment conventions for an ML team.
When assessing whether a trained model meets the criteria for production deployment.
When needing to ensure experiments are repeatable and comparable across a team.
When evaluating the maturity of an ML engagement.

Advantages

Promotes consistent engineering practices across ML projects.
Improves reproducibility by standardizing environment and data tracking.
Provides a clear, structured path for production readiness assessments.
Helps teams balance rapid research exploration with operational requirements.
Reduces ambiguity in team roles and project lifecycle stages.

Usage examples

“How should we structure our ML repository to ensure reproducibility?”: The agent will provide guidance on folder structures, virtual environment configuration, and the necessity of tracking datasets, parameters, and code versions.
“Is our model ready for production?”: The agent will guide you through the ML Model Production Checklist, helping you evaluate readiness domains and make informed decisions based on your specific use case.

Install

Download the skill as a ZIP:
https://autogineer.com/agent-skills/microsoft/ml-experimentation/download

Unzip it into the cross-client skills folder of your project:

mkdir -p .agents/skills && unzip ml-experimentation.zip -d .agents/skills

Documentation by Microsoft

ML Experimentation Reference Pack

Goal

Ground machine learning experimentation in the Microsoft CSE engineering playbook so that environment setup, repository structure, experiment tracking, dataset and model abstractions, evaluation flow, and production-readiness review are applied consistently and attributed accurately.

This pack is machine learning specific. It assumes a model is being trained, tracked, evaluated, or assessed for production. General experiment framing, hypothesis formation, and vetting belong to experiment-design.

Inputs

The ML experimentation setup under discussion: environments, repository layout, tracking framework, or evaluation flow
The model under assessment and its training and evaluation history, when readiness is the question
Existing dataset versioning, parameter tracking, and environment capture practice
The engagement stage, since the production checklist has a lifecycle precondition

Reference index

Read only the reference that matches the active concern.

Reference	Read this when
model-experimentation.md	Standing up virtual environments, repository and notebook structure, experiment tracking and reproducibility, dataset and model abstractions, or evaluation flow
ml-checklists.md	Checking ML engagement fundamentals or assessing whether a trained model is ready to move toward production
provenance.md	Confirming what is upstream guidance, what is HVE Core derivation or repository convention, and where upstream is silent

Success criteria

Reproducibility keeps all four elements: dataset names and versions, parameters, code, and environment. Tracking a dataset name without its version is a labelling practice, not reproducibility.
Datasets and evaluation are defined consistently enough that experiments are comparable. A tracking framework alone does not deliver comparability.
Checklist section headings and readiness domains are preserved, and applicability caveats travel with them.
Experiment reproducibility stays distinct from pipeline replayability, which belongs to dataops, the DataOps skill for tier behavior, pipeline invariants, validation placement, tests, drift, and operational signals.

Constraints

Reproduce only the minimum text necessary for a specific technical point, and paraphrase everything else. Attribute every reference and describe accurately what each reference reproduces.
Preserve checklist section headings as structural identifiers and summarize what each section covers. Do not restore the upstream item lists or reconstruct either checklist locally; link readers to the upstream page for item wording.
Label repository conventions as substitutions rather than upstream recommendations. The uv environment convention is a repository substitution, not a playbook recommendation.
Do not convert a checklist into an unconditional gate. Upstream scopes the production checklist to teams that have already trained a model and permits use-case-specific decisions.

Ownership boundaries

Concern	Owner
Experiment framing, hypothesis formation, vetting criteria, and red flags	`experiment-design`
Pipeline mechanics, data tiering, replay semantics, and DS/MLOps test technique	`dataops`
Data validation, drift detection, and their asymmetric remediation	`dataops`
Ethical and Responsible AI review	`rai-planner`
Telemetry naming and data sensitivity classification	`telemetry-foundations` and `privacy-standards`

Stop rules

Stop and route to experiment-design, the general experiment selection, hypothesis, vetting, scope, and evaluation skill, when the request is about whether an experiment is worth running rather than how to run it.
Stop and state the lifecycle precondition when the production checklist is invoked for a model that has not been built or trained.
Stop and state the gap when upstream does not cover the request, such as a universal framework, tool, or metric choice made without project context.

Attribution

This pack declares CC-BY-4.0.

Both references derive from Microsoft CSE Code With Engineering Playbook documentation pages, which are licensed CC BY 4.0. Upstream guidance is summarized rather than reproduced; section headings and tool and file names are carried across as identifiers. The upstream project applies MIT through a separate LICENSE-CODE file to code samples only, which this pack does not reproduce. Each reference cites its own upstream URL, states that changes were made, and describes what it reproduces.

Explanatory framing, the lifecycle caveat, the readiness-domain grouping, the routing table, and the uv substitution are repository-original.

See provenance.md for the consolidated source map and derivation labels.

Files

ATTRIBUTION.mdAdded by AutoGineer987 B
LICENSEAdded by AutoGineer16.6 KiB
SKILL.md6.7 KiB
references/ml-checklists.md6.2 KiB
references/model-experimentation.md8.2 KiB
references/provenance.md6.1 KiB

Requirements and compatibility

Written for: GitHub Copilot, Claude Code

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Needs: Claude Code frontmatter

Security

No issues found by our static scan· No issues found

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Pytorch Lightning
K-Dense· Community
A framework for organizing PyTorch code to streamline neural network training, scaling, and experiment tracking.
Data and AIClaude CodeClaude appsOpenAI Codex+14 more
MITLow riskHas scriptsGitHub stars of the source repository56.4k
Aeon
K-Dense· Community
A scikit-learn compatible Python toolkit for comprehensive time series machine learning tasks.
Data and AIClaude CodeClaude appsOpenAI Codex+14 more
MITLow riskGitHub stars of the source repository56.4k
Umap Learn
K-Dense· Community
Integrate UMAP-learn for non-linear dimensionality reduction, visualization, and clustering preprocessing.
Data and AIClaude CodeClaude appsOpenAI Codex+14 more
MITLow riskGitHub stars of the source repository56.4k
Scikit Learn
K-Dense· Community
Comprehensive guidance for classical machine learning workflows using the scikit-learn Python library.
Data and AIClaude CodeClaude appsOpenAI Codex+14 more
MITLow riskHas scriptsGitHub stars of the source repository56.4k
Shap
K-Dense· Community
Explain and audit machine-learning model predictions using the SHAP framework for feature attribution and visualization.
Data and AIClaude CodeClaude appsOpenAI Codex+14 more
MITLow riskHas scriptsGitHub stars of the source repository56.4k
Pufferlib
K-Dense· Community
Version-aware guidance for PufferLib reinforcement learning environments, vectorization, policies, and training.
Data and AIClaude CodeClaude appsOpenAI Codex+14 more
MITLow riskHas scriptsGitHub stars of the source repository56.4k

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download ml-experimentation.zip