Skip to main content
skill CX Codex

azure-custom-vision — Claude Code skill: what it does, install

azure-custom-vision — a skill that gives your agent a map of Azure AI Custom Vision docs: model export, prediction API, quotas, RBAC. Useful when you write training or deployment code.

CC-BY-4.0 169 installs ★ 818 updated 2026-10-25

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add MicrosoftDocs/Agent-Skills --skill azure-custom-vision -a claude-code
Open on GitHub

What azure-custom-vision does

The skill is a folder with a SKILL.md that indexes Custom Vision topics and points each one at a Microsoft Learn page. The agent scans the category table, then opens a line range of the file or a linked reference such as security.md. Only the section matching the question enters context.

Six categories sit inside: data collection and Smart Labeler, domain choice and migration off Custom Vision, tier limits and quotas, customer-managed keys with Azure RBAC, code patterns (SDK export, ONNX under Windows ML, TensorFlow in Python, classification and detection calls, Azure Storage), and deployment — copying projects between regions, exporting models for offline and mobile use.

Network access is mandatory. The preferred route is the mcp_microsoftdocs:microsoft_docs_fetch tool with from=learn-agent-skill; the fallback is fetch_webpage. Without either, the agent holds the index and nothing behind it. Scope stops at Custom Vision: Azure AI Vision, Azure Machine Learning and Foundry Local live in separate skills from the same repository.

What it helps with

  • pick a Custom Vision domain that fits your images
  • export a trained model to ONNX for Windows ML
  • work out training and prediction quotas for a pricing tier
  • wire Azure RBAC roles for a Custom Vision project
  • move a project to another Azure region

Example prompts for the agent

  • How do I export my Custom Vision model to ONNX and run it in Windows ML?
  • Check which training quotas apply to my Custom Vision tier
  • Set up RBAC so my service principal can train a Custom Vision project

How to install azure-custom-vision

1Skills CLI (Vercel)

npx skills add MicrosoftDocs/Agent-Skills --skill azure-custom-vision -a claude-code

2Manually: put the files in place

~/.claude/skills/azure-custom-vision/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/azure-custom-vision/

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

Questions about azure-custom-vision

How to install azure-custom-vision in Claude Code?

Run npx skills add MicrosoftDocs/Agent-Skills --skill azure-custom-vision -a claude-code. The skill file lands at ~/.claude/skills/azure-custom-vision/SKILL.md.

What does azure-custom-vision do?

It hands the agent an index of Custom Vision documentation with links to Microsoft Learn and fetches the matching page on demand. Coverage runs from data and domains to quotas, security, code and deployment.

What does the skill need to work?

Network access. The main route is the mcp_microsoftdocs MCP server and its microsoft_docs_fetch tool, with fetch_webpage as fallback. If that MCP server is missing, the skill suggests installing it.

Source text

SKILL.md · CC-BY-4.0
---
name: azure-custom-vision
description: Expert knowledge for Azure AI Custom Vision development including best practices, decision making, limits & quotas, security, integrations & coding patterns, and deployment. Use when exporting Custom Vision models, calling prediction APIs, using ONNX/TensorFlow, managing CMK/RBAC, or Smart Labeler, and other Azure AI Custom Vision related development tasks. Not for Azure AI Vision (use azure-ai-vision), Azure AI services (use microsoft-foundry-tools), Azure Machine Learning (use azure-machine-learning), Azure AI Foundry Local (use microsoft-foundry-local).
compatibility: Requires network access. Uses mcp_microsoftdocs:microsoft_docs_fetch or fetch_webpage to retrieve documentation.
metadata:
  generated_at: "2026-06-21"
  generator: "docs2skills/1.0.0"
---
# Azure AI Custom Vision Skill

This skill provides expert guidance for Azure AI Custom Vision. Covers best practices, decision making, limits & quotas, security, integrations & coding patterns, and deployment. It combines local quick-reference content with remote documentation fetching capabilities.

## How to Use This Skill

> **IMPORTANT for Agent**: Use the **Category Index** below to locate relevant sections. For categories with line ranges (e.g., `L35-L120`), use `read_file` with the specified lines. For categories with file links (e.g., `[security.md](security.md)`), use `read_file` on the linked reference file

> **IMPORTANT for Agent**: If `metadata.generated_at` is more than 3 months old, suggest the user pull the latest version from the repository. If `mcp_microsoftdocs` tools are not available, suggest the user install it: [Installation Guide](https://github.com/MicrosoftDocs/mcp/blob/main/README.md)

This skill requires **network access** to fetch documentation content:
- **Preferred**: Use `mcp_microsoftdocs:microsoft_docs_fetch` with query string `from=learn-agent-skill`. Returns Markdown.
- **Fallback**: Use `fetch_webpage` with query string `from=learn-agent-skill&accept=text/markdown`. Returns Markdown.

## Category Index

| Category | Lines | Description |
|----------|-------|-------------|
| Best Practices | L34-L39 | Improving Custom Vision model quality with better data collection/labeling strategies and using Smart Labeler to speed and automate image annotation |
| Decision Making | L40-L45 | Guidance on selecting the best Custom Vision domain for your scenario and planning migrations from Custom Vision to other Azure or third‑party vision services. |
| Limits & Quotas | L46-L50 | Details on Custom Vision usage limits per pricing tier, including training/prediction quotas, project and image caps, and how limits affect model training and deployment. |
| Security | L51-L57 | Managing Custom Vision security: encryption with customer-managed keys, secure data handling/export/deletion, and configuring Azure RBAC roles and permissions. |
| Integrations & Coding Patterns | L58-L68 | Using Custom Vision models and APIs in apps: exporting via SDK, running ONNX/TensorFlow in Windows ML/Python, calling classification/detection APIs, and integrating with Azure Storage. |
| Deployment | L69-L73 | Deploying Custom Vision models: copying/backing up projects across regions and exporting models for offline, edge, and mobile (TensorFlow, ONNX, iOS/Android) use. |

### Best Practices
| Topic | URL |
|-------|-----|
| Apply Custom Vision data strategies to improve models | https://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/getting-started-improving-your-classifier |
| Speed up Custom Vision labeling with Smart Labeler | https://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/suggested-tags |

### Decision Making
| Topic | URL |
|-------|-----|
| Plan migration from Custom Vision to alternative services | https://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/migration-options |
| Choose the right Custom Vision domain for your project | https://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/select-domain |

### Limits & Quotas
| Topic | URL |
|-------|-----|
| Review Custom Vision limits and quotas by tier | https://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/limits-and-quotas |

### Security
| Topic | URL |
|-------|-----|
| Configure customer-managed keys for Custom Vision encryption | https://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/encrypt-data-at-rest |
| View, export, and delete Custom Vision data securely | https://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/export-delete-data |
| Configure Azure RBAC roles for Custom Vision projects | https://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/role-based-access-control |

### Integrations & Coding Patterns
| Topic | URL |
|-------|-----|
| Integrate Custom Vision ONNX models with Windows ML apps | https://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/custom-vision-onnx-windows-ml |
| Run exported Custom Vision TensorFlow models in Python | https://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/export-model-python |
| Export Custom Vision models programmatically with SDK | https://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/export-programmatically |
| Use Custom Vision SDK for image classification | https://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/quickstarts/image-classification |
| Call Custom Vision object detection APIs with SDK | https://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/quickstarts/object-detection |
| Integrate Custom Vision with Azure Storage queues and blobs | https://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/storage-integration |
| Use Custom Vision prediction API to test images | https://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/use-prediction-api |

### Deployment
| Topic | URL |
|-------|-----|
| Copy and back up Custom Vision projects across regions | https://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/copy-move-projects |
| Export Custom Vision models for offline and mobile use | https://learn.microsoft.com/en-us/azure/ai-services/custom-vision-service/export-your-model |

© MicrosoftDocs · CC-BY-4.0 · MicrosoftDocs/Agent-Skills

Similar skills

All skills for AI and ML →
azure-ai-vision-imageanalysis-py Microsoft The azure-ai-vision-imageanalysis-py skill guides Python work with Azure AI Vision Image Analysis, from OCR and object detection to captions and smart crops. Use it when building image-understanding features. CX Codex +1 2installs azure-ai-vision-imageanalysis-java Microsoft azure-ai-vision-imageanalysis-java — a skill for the Azure AI Vision SDK for Java. It feeds the agent ready code for captions, OCR, object detection, tagging and smart cropping. CX Codex +1 ★ 3,232repo stars senior-computer-vision Alireza Rezvani senior-computer-vision is a Claude Code skill for computer vision work, from object detection and image segmentation to model deployment. It applies to training pipelines and inference tuning. CX Codex +1 1,152installs azure-infra-engineer VoltAgent The azure-infra-engineer subagent reviews and changes Azure infrastructure with security, reliability, and rollback in mind. Delegate work on resources, networking, identity, or automation. CX Codex ★ 6,505repo stars azure-role-selector official github The azure-role-selector skill selects an Azure role with the least privilege needed for an identity and shows how to assign it. Use it when Azure access needs a careful RBAC match. CX Codex +1 9,399installs iam-audit briiirussell iam-audit audits cloud and identity provider access, designs least-privilege role models, and structures SSO migrations. Detects privilege creep without making live changes. CX Codex +1 450installs

From the same set144

The whole set →
azure-chaos-studio Skill for Azure Chaos Studio setup: experiments, workspaces, AKS agents, Private Link, and migration from classic experiments. CX Codex +1 170installs azure-redhat-openshift A skill for Claude Code, Codex, Cursor and other IDEs providing expert guidance on Azure Red Hat OpenShift. Covers cluster sizing, network topology, identity configuration, and integration with Azure services. CX Codex +1 169installs azure-cloud-hsm Technical skill for Azure Cloud HSM to handle authentication, networking, audit logs, and PKCS#11 keys. Helps diagnose cluster sync issues and verify capacity limits. CX Codex +1 169installs azure-service-connector This skill guides Azure Service Connector work, from wiring Azure compute to Redis and databases to troubleshooting security and deployment issues. CX Codex +1 169installs azure-operator-nexus Azure Operator Nexus reference for AI agents. Guides deployment, bare-metal troubleshooting, network fabric setup, and cluster upgrades. CX Codex +1 169installs azure-network-function-manager Guides Azure Network Function Manager work around prerequisites, identities, permissions, and secure access to network functions. CX Codex +1 169installs azure-attestation Reference skill for Azure Attestation work: error troubleshooting, claim-rule policies, SGX and TPM baselines, private endpoints. Keeps the agent on Microsoft's own docs. CX Codex +1 169installs azure-business-process-tracking Agent reference for Azure Business Process Tracking, focused on deployment: builds, tests and CI/CD pipelines. CX Codex +1 168installs

Project sponsors

Companies that keep this analytics open