Is the Azure AI Vision skill free?

Yes. The skill itself is free from MicrosoftDocs/Agent-Skills. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Azure AI Vision SkillProof Score?

8.4/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 4/5.

How do I install Azure AI Vision?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Azure AI Vision with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Azure AI Vision

Routes Azure AI Vision dev questions to authoritative Microsoft Learn docs and fetches them

by MicrosoftDocs · MicrosoftDocs/Agent-Skills

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.4/10
Tested: Jul 21, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 4ac587e

Fetched SKILL.md (HTTP 200) at skills/azure-ai-vision/SKILL.md; it is a single self-contained file, no local reference files. Verified the internal Category Index line ranges (L33-39, L57-60) point to real URL tables and spot-checked 3 external Learn URLs (migration-options, call-analyze-image-40, install-containers) all HTTP 200; no security smells. For output, I ran the skill's routing on an Image Analysis 4.0 object-detection limits question: my from-memory baseline invented a ~100-object cap and 50x50px/20MB/format limits, while the skill-routed Learn page returned the exact documented limitations (5%-of-image threshold, closely-arranged objects, no brand differentiation) plus the real objectsResult JSON schema and had no such cap, correcting two fabrications. Docs docked 1 point: it claims "local quick-reference content" but the body is essentially just a curated URL index.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 7/10
Docs & honesty 4/5

What Azure AI Vision does

A documentation-index skill for Azure AI Vision development (Image Analysis, Read OCR containers, smart-crop thumbnails, background removal, multimodal embeddings, live video frame analysis). It maps a question to the correct Microsoft Learn page under a Category Index (Decision Making, Limits and Quotas, Configuration, Integrations and Coding Patterns, Deployment) and fetches it via the microsoftdocs MCP or a web-fetch fallback. Triggers when working with Azure AI Vision APIs, SDKs, OCR containers, or deployment, and explicitly defers Custom Vision, Video Indexer, Document Intelligence, and Immersive Reader to their own skills.

How to install Azure AI Vision

git clone --depth 1 https://github.com/MicrosoftDocs/Agent-Skills.git /tmp/azure-ai-vision-src
mkdir -p ~/.claude/skills
cp -R /tmp/azure-ai-vision-src/skills/azure-ai-vision ~/.claude/skills/azure-ai-vision
# Self-contained: one SKILL.md, no local reference files or scripts.
# Runtime needs network access. Preferred fetch path is the microsoftdocs MCP
# (mcp_microsoftdocs:microsoft_docs_fetch); install: https://github.com/MicrosoftDocs/mcp
# Fallback is any web-fetch tool with query string from=learn-agent-skill&accept=text/markdown.

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Azure AI Vision

/azure-ai-vision Routes Azure AI Vision dev questions to authoritative Microsoft Learn docs and fetches them

It also activates on plain-language prompts like these:

Extract text from this image using Read OCR
Generate a smart-crop thumbnail for this photo
Analyze video frames with Azure AI Vision

Frequently asked questions

Is the Azure AI Vision skill free?: Yes. The skill itself is free from MicrosoftDocs/Agent-Skills. SkillProof publishes the install command and an independent test verdict at no cost.
Does Azure AI Vision work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 21, 2026. Verdict: Tested · Works. Fetched SKILL.md (HTTP 200) at skills/azure-ai-vision/SKILL.md; it is a single self-contained file, no local reference files. Verified the internal Category Index line ranges (L33-39, L57-60) point to real URL tables and spot-checked 3 external Learn URLs (migration-options, call-analyze-image-40, install-containers) all HTTP 200; no security smells. For output, I ran the skill's routing on an Image Analysis 4.0 object-detection limits question: my from-memory baseline invented a ~100-object cap and 50x50px/20MB/format limits, while the skill-routed Learn page returned the exact documented limitations (5%-of-image threshold, closely-arranged objects, no brand differentiation) plus the real objectsResult JSON schema and had no such cap, correcting two fabrications. Docs docked 1 point: it claims "local quick-reference content" but the body is essentially just a curated URL index.
What is the Azure AI Vision SkillProof Score?: 8.4/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 4/5.
How do I install Azure AI Vision?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Azure AI Vision with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.