Skip to main content
skill CX Codex

dataops — Claude Code skill: what it does, how to install

Microsoft DataOps and DS/MLOps testing reference: where to validate data, how to write pipeline tests, and how to tell validation errors from drift.

CC-BY-4.0 ★ 1,627 updated 2026-10-25

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add microsoft/hve-core --skill dataops -a claude-code
Open on GitHub

What dataops does

The skill packages five Microsoft CSE Engineering Playbook references: data tier semantics (Bronze, Silver, Gold), Bronze-to-Silver validation placement rules, pipeline invariants (replay, idempotency, testability), pytest categories for DS/MLOps (data loading, transformations, model predictions, data validation), and the distinction between validation and drift detection. The agent reads only the reference needed for the current task — assigning a tier, placing validation, writing a test, or choosing observability metrics.

It generates code, assertions, and review guidance but does not run pipelines or write to telemetry. Each assertion ties back to a Microsoft source or is labelled as HVE Core derivation. The skill works without FFmpeg, Docker, or a Python environment — it is a text reference, not an executable tool.

Handles requests like 'place validation in Bronze → Silver pipeline', 'write pytest for model', 'distinguish drift from validation error'. It stops and routes metric naming to telemetry-foundations and data sensitivity classification to privacy-standards.

What it helps with

  • place data validation at the correct tier boundary
  • write pytest for pipelines, transformations or models
  • distinguish model drift from data validation errors
  • set replay and idempotency invariants for pipelines
  • validate synthetic-data generation contract before source access

Example prompts for the agent

  • Place validation in the Bronze to Silver pipeline and explain why not earlier
  • Write pytest for data loading and transformation in prepare_dataset.py
  • Tell apart model drift and validation error — which metrics and what to do in each case

How to install dataops

1Skills CLI (Vercel)

npx skills add microsoft/hve-core --skill dataops -a claude-code

2Manually: put the files in place

~/.claude/skills/dataops/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/dataops/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about dataops

How to install dataops in Claude Code?

Run npx skills add microsoft/hve-core --skill dataops -a claude-code, the skill will be available at ~/.claude/skills/dataops/SKILL.md.

What does the dataops skill do?

The skill holds Microsoft DataOps references: data tier semantics, Bronze-to-Silver validation placement, pipeline invariants, pytest categories for DS/MLOps, and the validation-versus-drift distinction.

How does data validation differ from drift detection?

Validation checks schema and constraint compliance at input, drift tracks distribution or model behavior change over time. Validation stops the pipeline, drift calls for retraining or tuning.

Source text

SKILL.md · CC-BY-4.0
---
name: dataops
description: "DataOps and DS/MLOps testing reference for data tiering, Bronze-to-Silver validation placement, pipeline invariants, pytest categories, and validation-versus-drift. Use when designing, reviewing, or generating data pipelines, transformation code, data validation, or data-science test suites."
license: CC-BY-4.0
user-invocable: false
metadata:
  authors: "Microsoft (Code With Engineering Playbook); Microsoft (planning synthesis)"
  spec_version: "1.0"
  last_updated: "2026-09-09"
  content_based_on: "https://microsoft.github.io/code-with-engineering-playbook/design/design-patterns/data-heavy-design-guidance/; https://microsoft.github.io/code-with-engineering-playbook/ml-and-ai-projects/testing-data-science-and-mlops-code/; https://microsoft.github.io/code-with-engineering-playbook/ml-and-ai-projects/ml-model-checklist/; https://microsoft.github.io/code-with-engineering-playbook/observability/ml-observability/"
---

# DataOps Reference Pack

## Goal

Ground pipeline and test generation in the Microsoft CSE engineering playbook so that data tier semantics, validation placement, recovery invariants, and DS/MLOps test technique are applied consistently and attributed accurately.

## Inputs

* The pipeline, transformation, validation, or test work under discussion
* The tier of each dataset involved, when the consuming workflow records one
* Existing test layout, package structure, and data-access boundaries
* A data classification produced elsewhere, when sensitivity matters

## Reference index

Read only the reference that matches the active concern.

| Reference                                                                                 | Read this when                                                                                                                                                     |
|-------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| [data-tiers-and-pipeline-invariants.md](references/data-tiers-and-pipeline-invariants.md) | Assigning tier meaning, placing validation, routing malformed records, or asserting replay, idempotency, testability, source-control, and configuration invariants |
| [testing-data-science-and-mlops.md](references/testing-data-science-and-mlops.md)         | Writing or reviewing tests for data loading, transformation, model load or predict, data validation, or model robustness                                           |
| [validation-drift-and-observability.md](references/validation-drift-and-observability.md) | Distinguishing data validation from drift detection, choosing remediation, or deciding which data and model signals matter                                         |
| [synthetic-data-operation-contract.md](references/synthetic-data-operation-contract.md)   | Validating synthetic-data preflight authority, field lineage, conditional subgroup evidence, result linkage, or guarded local replacement                          |
| [provenance.md](references/provenance.md)                                                 | Confirming what is upstream guidance, what is HVE Core derivation, and where upstream is silent                                                                    |

## Success criteria

* Tier language distinguishes the three upstream quality tiers from the additional storage areas.
* Validation is placed at the Bronze-to-Silver boundary, and the faithful-copy rationale with both replay purposes travels with that placement whether or not the request challenges it.
* Test guidance names the operation category, its technique, and where mocking stops.
* Validation and drift keep their distinct definitions and their distinct remediation paths.
* Every claim traces to an attributed upstream source or is labelled as HVE Core guidance.
* Synthetic-data generation stops before source access or writes unless its applicable
  `SYNTHETIC_DATA_OPERATION_V1` preflight passes deterministic validation.

## Constraints

* This skill generates code, assertions, and review guidance. It does not execute pipelines, transformation engines, or telemetry backends.
* 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.
* Label HVE Core derivations as such. Do not present a derived consequence or a repository convention as upstream guidance.
* Where upstream is silent, say so rather than inventing an upstream-sounding rule.

## Ownership boundaries

This skill decides *which* data and model signals matter. It does not own the vocabulary, the classification, or the surrounding workflow.

| Concern                                                                                      | Owner                   |
|----------------------------------------------------------------------------------------------|-------------------------|
| Metric names, instrument types, units, cardinality discipline, and the PII emission denylist | `telemetry-foundations` |
| Data sensitivity classification and DPIA thresholds                                          | `privacy-standards`     |
| Entity semantics, relationships, and which tier a dataset is recorded as                     | The calling workflow    |
| Feasibility assessment and go/no-go recommendation                                           | The calling workflow    |

No repository artifact currently owns the last two rows. When the caller supplies neither, state the gap rather than deciding tier assignment or feasibility here.

This skill never decides what is sensitive. It reads a classification produced elsewhere.

For synthetic-data operations, read
[synthetic-data-operation-contract.md](references/synthetic-data-operation-contract.md)
and validate records against
[synthetic-data-operation-v1.schema.json](assets/synthetic-data-operation-v1.schema.json).
The contract records qualified decisions by immutable reference; it does not store source
values or replace the authority of data, privacy, Responsible AI, fairness, or domain owners.

## Stop rules

* Stop and route metric naming, units, and cardinality to
  `telemetry-foundations`, the OpenTelemetry-aligned vocabulary and
  instrumentation skill. Route data sensitivity to `privacy-standards`, the
  privacy classification and DPIA-threshold reference.
* Stop and state the gap when the request depends on guidance the playbook does not provide, such as a drift threshold or an alerting policy.
* Stop and offer the correct placement when asked to validate before Bronze landing, rather than complying or refusing without an alternative.

## Attribution

This pack declares `CC-BY-4.0` because both bodies of content it holds carry that license.

Source pages are Microsoft CSE Code With Engineering Playbook documentation licensed CC BY 4.0. The upstream project applies MIT through a separate `LICENSE-CODE` file to code samples only, which this pack does not reproduce. The references derive from those documentation pages and have been changed: upstream guidance is paraphrased, and only identifiers and structural names are carried across as facts. `THIRD-PARTY-NOTICES` carries the attribution CC BY 4.0 requires and states that the content has been changed. Each reference cites its own upstream URL and states what it reproduces.

Content labelled as HVE Core derivation is repository-original material under CC BY 4.0. See [provenance.md](references/provenance.md) for the consolidated source map and derivation labels.

© microsoft · CC-BY-4.0 · microsoft/hve-core

Similar skills

All skills for Data and databases →

From the same set148

The whole set →
CVE Analyzer CVE Analyzer — a subagent for deep CVE analysis: checks if vulnerable code is reachable in the project and returns evidence-backed VEX status. CX Codex +1 ★ 1,627repo stars python-script python-script defines Python 3.11+ script standards for Claude Code, enforcing package workflows with uv, modern type syntax, and clean CLI structures. CX Codex +1 ★ 1,627repo stars hve-artifact-authoring The hve-artifact-authoring skill guides the creation and validation of HVE Core agents, prompts, instructions, and skills. Use it when preparing an artifact in the repository and checking it against project conventions. CX Codex +1 ★ 1,627repo stars vex-generation The vex-generation rule guides AI-assisted VEX triage with evidence requirements, confidence bands, and status constraints. Use it when an agent drafts vulnerability findings for human review. CX Codex +1 ★ 1,627repo stars session-log-canvas-update session-log-canvas-update diffs Copilot session event schemas against the canvas baseline. Keeps the Session Log canvas in sync across Copilot runtime updates. CX Codex +1 ★ 1,627repo stars Backlog Grooming Backlog Grooming reviews selected open GitHub issues against repository evidence and returns a maintainer report without changing those issues. CX Codex +1 ★ 1,627repo stars git-commit git-commit walks through confirming which paths to stage, then makes one local Conventional Commit, or just drafts a commit message for changes already staged. CX Codex +1 ★ 1,627repo stars ux-coaching ux-coaching guides UX practitioners through problem framing, design critique, and stakeholder advocacy by asking questions instead of giving ready-made answers. CX Codex +1 ★ 1,627repo stars

Project sponsors

Companies that keep this analytics open