ml-experimentation — Claude Code skill: what it does, how to install
ml-experimentation is a Claude Code skill that applies Microsoft CSE practices to ML experiment tracking, reproducibility, and production readiness checks.
CC-BY-4.0 ★ 1,627 updated 2026-10-25
npx skills add microsoft/hve-core --skill ml-experimentation -a claude-codeWhat ml-experimentation does
This skill applies Microsoft CSE engineering practices to machine learning projects. It guides repository layout, notebook organization, parameter logging, and dataset abstractions. True reproducibility requires tracking four elements together: code, runtime environment, parameters, and dataset versions.
The reference enforces clear ownership boundaries across tasks. When asked whether an experiment is worth pursuing, it routes the question to experiment-design. Data pipeline mechanics and drift detection belong to dataops. The virtual environment setup using uv is a repository substitution rather than an upstream playbook requirement.
Evaluating production readiness carries a mandatory lifecycle precondition. If training has not finished yet, the readiness review stops immediately.
What it helps with
- track model parameters and dataset versions for reproducible runs
- structure repository layout and notebooks for ML experiments
- evaluate whether a trained model is ready for production
- separate experiment design from data pipeline operations
Example prompts for the agent
- Review our trained model against the production readiness checklist
- Help me set up repository structure and environment capture for ML experiments
- How should we track dataset versions and parameters to ensure reproducibility?
How to install ml-experimentation
1Skills CLI (Vercel)
npx skills add microsoft/hve-core --skill ml-experimentation -a claude-code2Manually: put the files in place
~/.claude/skills/ml-experimentation/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/ml-experimentation/
1Skills CLI (Vercel)
npx skills add microsoft/hve-core --skill ml-experimentation -a codex2Manually: put the files in place
.agents/skills/ml-experimentation/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add microsoft/hve-core --skill ml-experimentation -a cursor2Manually: put the files in place
.cursor/skills/ml-experimentation/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install microsoft/hve-core .github/skills/data-science-engineering/ml-experimentation2Manually: put the files in place
.github/skills/ml-experimentation/SKILL.md1Skills CLI (Vercel)
npx skills add microsoft/hve-core --skill ml-experimentation -a gemini-cli2Platform CLI
gemini skills install https://github.com/microsoft/hve-core --path .github/skills/data-science-engineering/ml-experimentationManually: put the files in place
.devin/skills/ml-experimentation/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about ml-experimentation
How to install ml-experimentation in Claude Code?
Run npx skills add microsoft/hve-core --skill ml-experimentation -a claude-code in your terminal.
What does ml-experimentation do?
It provides Microsoft CSE engineering guidelines for tracking ML experiments, managing dataset abstractions, and validating models before production deployment.
Can I use the production checklist before a model is trained?
No, the checklist requires an existing trained model. If the model has not been trained yet, the skill enforces its lifecycle stop rule.
Source text
SKILL.md · CC-BY-4.0
--- name: ml-experimentation description: "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." license: CC-BY-4.0 user-invocable: false metadata: authors: "Microsoft (Code With Engineering Playbook)" spec_version: "1.0" last_updated: "2026-08-02" content_based_on: "https://microsoft.github.io/code-with-engineering-playbook/ml-and-ai-projects/model-experimentation/; https://microsoft.github.io/code-with-engineering-playbook/ml-and-ai-projects/ml-fundamentals-checklist/; https://microsoft.github.io/code-with-engineering-playbook/ml-and-ai-projects/ml-model-checklist/" --- # 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](references/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](references/ml-checklists.md) | Checking ML engagement fundamentals or assessing whether a trained model is ready to move toward production | | [provenance.md](references/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](references/provenance.md) for the consolidated source map and derivation labels.
© microsoft · CC-BY-4.0 · microsoft/hve-core