azure-open-datasets — Claude Code skill: Azure Open Datasets limits
A reference skill for Azure Open Datasets limits: throttling on non-Spark downloads, quota ceilings and retry handling, pulled from Microsoft Learn docs.
CC-BY-4.0 161 installs ★ 818 updated 2026-10-25
npx skills add MicrosoftDocs/Agent-Skills --skill azure-open-datasets -a claude-codeWhat azure-open-datasets does
The skill hands the agent a reference on Azure Open Datasets limits and quotas: download caps outside Spark, how throttling behaves, where retries fit. A small local index maps each category to line ranges, so the agent reads just that slice of the file.
Docs come from the network. Preferred call is mcp_microsoftdocs:microsoft_docs_fetch with from=learn-agent-skill; the fallback is fetch_webpage with accept=text/markdown. No network, or neither tool available, and only the local stub remains. The skill also tells you to install mcp_microsoftdocs when the tools are missing and to pull a fresh copy once metadata.generated_at is older than 3 months.
Scope stays narrow: download limits and quotas only. Azure Data Explorer, Synapse, Databricks and Machine Learning each have their own skill in the same repo, and this one does not cover them.
What it helps with
- trace why a non-Spark dataset download stalls under throttling
- pick a retry strategy that fits the quota
- jump straight to the official limits section
- keep Open Datasets quota questions apart from Synapse or Databricks ones
Example prompts for the agent
- Downloads of a non-Spark Azure Open Datasets table keep getting throttled. Pull the official limits and suggest a retry plan.
- Find the Microsoft Learn section on Azure Open Datasets quotas and summarize it.
- My export script keeps hitting rate limits. What do the docs say about working around them?
How to install azure-open-datasets
1Skills CLI (Vercel)
npx skills add MicrosoftDocs/Agent-Skills --skill azure-open-datasets -a claude-code2Manually: put the files in place
~/.claude/skills/azure-open-datasets/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/azure-open-datasets/
1Skills CLI (Vercel)
npx skills add MicrosoftDocs/Agent-Skills --skill azure-open-datasets -a codex2Manually: put the files in place
.agents/skills/azure-open-datasets/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add MicrosoftDocs/Agent-Skills --skill azure-open-datasets -a cursor2Manually: put the files in place
.cursor/skills/azure-open-datasets/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install MicrosoftDocs/Agent-Skills skills/azure-open-datasets2Manually: put the files in place
.github/skills/azure-open-datasets/SKILL.md1Skills CLI (Vercel)
npx skills add MicrosoftDocs/Agent-Skills --skill azure-open-datasets -a gemini-cli2Platform CLI
gemini skills install https://github.com/MicrosoftDocs/Agent-Skills --path skills/azure-open-datasetsManually: put the files in place
.devin/skills/azure-open-datasets/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add MicrosoftDocs/Agent-Skills --skill azure-open-datasets -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about azure-open-datasets
How do I install azure-open-datasets in Claude Code?
Run npx skills add MicrosoftDocs/Agent-Skills --skill azure-open-datasets -a claude-code. The skill file lands at ~/.claude/skills/azure-open-datasets/SKILL.md.
What does azure-open-datasets do?
It gives the agent guidance on Azure Open Datasets limits and quotas: throttling during non-Spark downloads, retries, ways around rate limits. A local index points at the Microsoft Learn sections.
What does the skill need to work?
Network access plus a doc-fetching tool: mcp_microsoftdocs:microsoft_docs_fetch or fetch_webpage. Without them only the local part runs.
Source text
SKILL.md · CC-BY-4.0
--- name: azure-open-datasets description: Expert knowledge for Azure Open Datasets development including limits & quotas. Use when handling non-Spark dataset downloads, throttling behavior, quota limits, retry logic, or rate-limit workarounds, and other Azure Open Datasets related development tasks. Not for Azure Data Explorer (use azure-data-explorer), Azure Synapse Analytics (use azure-synapse-analytics), Azure Databricks (use azure-databricks), Azure Machine Learning (use azure-machine-learning). compatibility: Requires network access. Uses mcp_microsoftdocs:microsoft_docs_fetch or fetch_webpage to retrieve documentation. metadata: generated_at: "2026-07-26" generator: "docs2skills/1.0.0" --- # Azure Open Datasets Skill This skill provides expert guidance for Azure Open Datasets. Covers limits & quotas. 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 | |----------|-------|-------------| | Limits & Quotas | L29-L32 | Managing and troubleshooting non-Spark download limits for Azure Open Datasets, including throttling behavior, quotas, and strategies to avoid or handle rate limits | ### Limits & Quotas | Topic | URL | |-------|-----| | Handle Azure Open Datasets non-Spark download limits | https://learn.microsoft.com/en-us/azure/open-datasets/samples |
© MicrosoftDocs · CC-BY-4.0 · MicrosoftDocs/Agent-Skills