ml-experimentation — скилл для Claude Code
Скилл ml-experimentation для Claude Code описывает инженерные практики Microsoft CSE и помогает выстроить воспроизводимый трекинг ML-экспериментов.
CC-BY-4.0 ★ 1 627 обновлён 2026-10-25
npx skills add microsoft/hve-core --skill ml-experimentation -a claude-codeЧто делает ml-experimentation
Скилл внедряет инженерные стандарты Microsoft CSE для машинного обучения. Он задаёт структуру репозитория и блокнотов, правила версионирования датасетов и логирования параметров. Воспроизводимость требует фиксации четырёх составляющих: кода, окружения, параметров и версии данных.
Внутри заложены правила разделения зон ответственности. Если вопрос касается ценности гипотезы, скилл перенаправляет в experiment-design. Механику пайплайнов и мониторинг дрейфа данных он отдаёт в dataops. Конвенция окружения на базе uv выбрана авторами репозитория и отсутствует в исходном плейбуке.
Проверка готовности к релизу имеет строгое условие жизненного цикла. Если модель ещё не обучена, применить производственный чек-лист не получится.
Какие задачи решает
- настроить воспроизводимый трекинг параметров и версий данных
- структурировать репозиторий и блокноты для ML-экспериментов
- проверить готовность обученной модели к переносу в прод
- разграничить задачи экспериментов и пайплайнов данных
Примеры запросов агенту
- Проверь готовность обученной модели к переносу в прод по чек-листу
- Как структурировать ML-репозиторий и зафиксировать версии датасетов для воспроизводимости?
- Помоги настроить трекинг экспериментов и окружение для обучения модели
Как установить ml-experimentation
1Через Skills CLI (Vercel)
npx skills add microsoft/hve-core --skill ml-experimentation -a claude-code2Вручную: положить файлы
~/.claude/skills/ml-experimentation/SKILL.mdПапка скилла целиком; для одного проекта — .claude/skills/ml-experimentation/
1Через Skills CLI (Vercel)
npx skills add microsoft/hve-core --skill ml-experimentation -a codex2Вручную: положить файлы
.agents/skills/ml-experimentation/SKILL.mdДля всех проектов — ~/.agents/skills/
1Через Skills CLI (Vercel)
npx skills add microsoft/hve-core --skill ml-experimentation -a cursor2Вручную: положить файлы
.cursor/skills/ml-experimentation/SKILL.mdCursor читает и .agents/skills/, и .claude/skills/
1GitHub CLI
gh skill install microsoft/hve-core .github/skills/data-science-engineering/ml-experimentation2Вручную: положить файлы
.github/skills/ml-experimentation/SKILL.md1Через Skills CLI (Vercel)
npx skills add microsoft/hve-core --skill ml-experimentation -a gemini-cli2Командой платформы
gemini skills install https://github.com/microsoft/hve-core --path .github/skills/data-science-engineering/ml-experimentationВручную: положить файлы
.devin/skills/ml-experimentation/SKILL.mdСтарый путь .windsurf/skills/ тоже читается
Claude.ai
Упакуйте папку в zip и загрузите в Settings → Capabilities → Skills
По шагам, с командами для каждой платформы: Как установить скилл в Claude Code: пять способов
Вопросы о ml-experimentation
Как установить ml-experimentation в Claude Code?
Выполните в терминале команду npx skills add microsoft/hve-core --skill ml-experimentation -a claude-code.
Что делает скилл ml-experimentation?
Он предоставляет инженерные рекомендации Microsoft CSE по организации экспериментов, абстракциям моделей и оценке готовности артефактов к продакшену.
Можно ли запустить производственный чек-лист до обучения модели?
Нет, у чек-листа готовности есть строгое условие жизненного цикла. Модель уже должна быть обучена, иначе скилл остановит выполнение.
Исходный текст
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