Kipt

Your prompts and skills, one keystroke away.

Explore

Azure storage skill: Blob, Files, Queues, Tables and Data Lake for coding agents

The Azure storage skill teaches coding agents Blob, Files, Queue, Table and Data Lake storage, access tiers and redundancy. How to install and use it.

By the Kipt team · Updated 26 October 2026

Source: microsoft/azure-skills · Maintainer: Microsoft · License: MIT · Checked: 26 October 2026

What is the Azure storage skill?

The Azure storage skill is Microsoft's reference card for Azure Storage, written for coding agents. It tells the agent which of the five storage services fits a job, how to list and move blobs through the Azure MCP Server or the Azure CLI, how access tiers and redundancy options differ, and which SDK package to use in each language.

Its description opens: "Azure Storage Services including Blob Storage, File Shares, Queue Storage, Table Storage, and Data Lake." It goes on to say it "Answers questions about storage access tiers (hot, cool, cold, archive), when to use each tier, and tier comparison."

The skill ships in microsoft/azure-skills, the Azure Skills Plugin. The README lists it under "Work across data, AI, identity, and platform services" and says the repo is synced automatically from microsoft/GitHub-Copilot-for-Azure. The SKILL.md frontmatter lists version 1.2.2 and author Microsoft.

As of 26 October 2026, its skills.sh page listed about 566,400 installs (snapshot, 26 October 2026).

What does it do?

The SKILL.md is short, about 5 KB, and works as a lookup table rather than a step-by-step workflow.

Pick the service. It maps each service to a use and a CLI group:

Service The skill says to use it for CLI
Blob Storage Objects, files, backups, static content az storage blob
File Shares SMB file shares, lift-and-shift az storage file
Queue Storage Async messaging, task queues az storage queue
Table Storage NoSQL key-value (it adds "consider Cosmos DB") az storage table
Data Lake Big data analytics, hierarchical namespace az storage fs

Use MCP first. The section is titled "MCP Server (Preferred)". When Azure MCP is enabled, the agent calls the azure__storage tool with five commands: list storage accounts, list containers, list blobs, download a blob and upload a blob. If MCP is off, the skill tells the agent: "In Copilot CLI or Claude Code, ask the user to run /mcp and enable Azure MCP".

Fall back to the CLI. Without MCP, the same five jobs map to Azure CLI commands:

az storage account list --output table
az storage container list --account-name ACCOUNT --output table
az storage blob list --account-name ACCOUNT --container-name CONTAINER --output table
az storage blob download --account-name ACCOUNT --container-name CONTAINER --name BLOB --file LOCAL_PATH
az storage blob upload --account-name ACCOUNT --container-name CONTAINER --name BLOB --file LOCAL_PATH

Explain tiers and redundancy. The skill's tables give Standard versus Premium accounts, the four blob access tiers with their day thresholds (cool 30+ days, cold 90+, archive 180+, with rehydration needed for archive), and durability for LRS (11 nines), ZRS (12 nines), GRS and GZRS (16 nines each). Those figures line up with the minimum storage periods and durability numbers on Microsoft's own pages on access tiers and storage redundancy.

Point to SDKs. A references/ folder holds short quick starts for Blob (Python, TypeScript, Java, Rust), Queue and File Shares (Python, TypeScript), Data Lake (Python) and Tables (Python, Java), plus sdk-usage.md, which lists package names and install commands for .NET, Java, JavaScript, Python, Go and Rust.

Steer auth toward managed identity. Every quick start except Rust uses DefaultAzureCredential and labels it for local development (the Rust one uses DeveloperToolsCredential for development). The shared auth-best-practices.md puts it plainly: "Use managed identities and Azure RBAC in production. Reserve DefaultAzureCredential for local development only." It gives per-language patterns that switch to ManagedIdentityCredential outside development.

How do you install the Azure storage skill?

The repo README documents several routes. The full plugin is the better fit here, because the skill's preferred path runs through the Azure MCP Server that the plugin wires in.

Claude Code: the Azure Skills Plugin. Run inside Claude Code:

/plugin install azure@claude-plugins-official

Or run /plugin and search for "azure". Update later with /plugin update azure@claude-plugins-official. See Claude Code plugins and Claude Code MCP.

GitHub Copilot CLI:

/plugin marketplace add microsoft/azure-skills
/plugin install azure@azure-skills

Codex, Cursor and Gemini CLI. For Codex, the README says to run codex plugin marketplace add microsoft/azure-skills, then install azure from /plugins. For Cursor, use the Cursor Marketplace or Settings, then Plugins. For Gemini CLI, run gemini extensions install https://github.com/microsoft/azure-skills. See Codex skills and Cursor skills.

Skill only. The command on skills.sh copies just this folder:

npx skills add https://github.com/microsoft/azure-skills --skill azure-storage

Prerequisites, per the README: an Azure account or subscription, Node.js 18 or later on your PATH for npx, and the Azure CLI signed in with az login. The README also documents service principal sign-in through AZURE_TENANT_ID, AZURE_CLIENT_ID and AZURE_CLIENT_SECRET.

How do you use it?

Ask about storage in plain language. The skill is model-invoked, so the agent loads it when your request matches its trigger list, which includes "upload files", "download blobs", "storage accounts" and "storage tier comparison".

Example prompts (suggestions; the first is from the README's prompt list):

  • List my Azure storage accounts.
  • Which access tier should I use for log files we read twice a year? Explain the trade-offs.
  • Upload ./dist to the web container in account mysiteprod and list what landed there.
  • Add Blob Storage to this Python API with azure-storage-blob. Use managed identity in production.
  • Should this app use Table Storage or Cosmos DB for user settings?

For a question about tiers or redundancy, expect an answer drawn from the skill's tables. For listing or moving data, expect MCP tool calls, or az storage commands if MCP is off.

Tips and limits

From the repo, Microsoft Learn and skills.sh, not from testing:

  • It can write data. Uploads go through storage_blob_put or az storage blob upload. Check the account and container names before you approve a write.
  • It's a reference, not a provisioner. It doesn't create storage accounts or write infrastructure code. For new resources in an azd project, the README's build workflow uses azure-prepare.
  • Tier costs are relative only. The tables say "Higher storage, lower access" and so on, with no prices. Check Azure's pricing pages for real numbers.
  • Smart tier isn't covered. Microsoft's access tiers page now describes a smart tier that moves data between hot, cool and cold based on usage. The skill's table lists only hot, cool, cold and archive.
  • Treat blob content as untrusted. On skills.sh, Gen Agent Trust Hub rated the skill Pass (Safe) on 6 October 2026, but noted that blobs the agent downloads could carry hidden instructions and that the skill has no rule about ignoring them. Socket rated it Pass on 6 October 2026 and Snyk Pass on 7 October 2026.
  • Telemetry. The README says to set AZURE_MCP_COLLECT_TELEMETRY=false to turn off Azure MCP telemetry.

The MIT License lets you copy and change the skill as long as you keep Microsoft's copyright and license notices.

Save it in your Kipt library

An edited copy is useful if your team has rules the stock skill doesn't know, such as a default region, naming scheme, or "never use account keys". In Kipt, open Skills and paste the skill's GitHub folder link into the import box, or drop the folder or a .zip. The copy carries the skill files only, not the plugin's MCP setup. Skills in your private GitHub repo install into Claude Code or Codex with one command:

npx skills add https://github.com/<you>/<repo>.git --all -g

Kipt is not affiliated with Microsoft.

Similar skills

Questions

What is the Azure storage skill?

azure-storage is an Agent Skill in Microsoft's microsoft/azure-skills repo. It gives a coding agent a reference for Blob Storage, File Shares, Queue Storage, Table Storage and Data Lake, plus blob access tiers, redundancy options and SDK quick starts in several languages.

How do I install the Azure storage skill in Claude Code?

Run /plugin install azure@claude-plugins-official inside Claude Code to get the Azure Skills Plugin, which bundles this skill with the Azure MCP Server. For the skill files alone, run npx skills add https://github.com/microsoft/azure-skills --skill azure-storage.

Does the Azure storage skill need the Azure MCP Server?

No, but it prefers it. With Azure MCP enabled, the agent lists accounts, containers and blobs and uploads or downloads blobs through MCP tools. Without it, the skill falls back to az storage commands in the Azure CLI, so you need the CLI installed and signed in.

Can the Azure storage skill upload or change data?

Yes. Its MCP tool list includes a blob upload command and its CLI fallback includes az storage blob upload, so an agent can write to a container your account can reach. Review those steps before you approve them, especially against production storage accounts.

Which storage services does the skill not cover?

Its description says not to use it for SQL databases, for Cosmos DB (it points to azure-prepare) or for messaging with Event Hubs or Service Bus (it points to azure-messaging). It covers Blob, Files, Queue, Table and Data Lake storage.

More in Skill directory

All guides

Keep your prompts and skills in one place, in your own GitHub. Install every skill with one command.

Get started

Kipt is an independent product, not affiliated with or endorsed by Anthropic, OpenAI, Cursor or GitHub. Claude, ChatGPT, Codex, Cursor and GitHub are trademarks of their owners.