Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
practicalswan avatar

Microsoft Development

  • 13 installs
  • 7 repo stars
  • Updated August 2, 2026
  • practicalswan/agent-skills

microsoft-development is a Claude Code skill for ai & agent building.

About

microsoft-development is a Claude Code skill for ai & agent building. It helps solo builders move faster with AI-assisted development.

  • microsoft-development
  • AI & Agent Building
  • AI-coding skill

Microsoft Development by the numbers

  • 13 all-time installs (skills.sh)
  • Ranked #11,409 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
  • Data as of Aug 4, 2026 (Skillselion catalog sync)
npx skills add https://github.com/practicalswan/agent-skills --skill microsoft-development

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs13
repo stars7
Last updatedAugust 2, 2026
Repositorypracticalswan/agent-skills

How do I helps with ai & agent building tasks.?

Helps with ai & agent building tasks.

Who is it for?

Best when you're working on ai & agent building and need structured help with microsoft development.

Skip if: Teams with no ai & agent building needs, or anyone wanting a generic chat assistant without this specific workflow.

When should I use this skill?

When you need to helps with ai & agent building tasks., or when microsoft-development is a claude code skill for ai & agent building.

What you get

Structured output aligned to microsoft-development: microsoft-development, AI & Agent Building.

Files

SKILL.mdMarkdownGitHub ↗

Microsoft Development

Optimized for current Microsoft Graph, Entra ID, PowerShell 7.x, and Microsoft 365 integration workflows.

Use this skill when the answer should come from Microsoft documentation rather than memory or third-party summaries.

  • Leverage native parallel subagent dispatch and 200k+ context windows where available.

Current MCP Reality

Microsoft's Learn Docs MCP server is publicly documented and currently exposes these core tools:

  • microsoft_docs_search
  • microsoft_docs_fetch
  • microsoft_docs_extract_code_examples
  • microsoft_docs_search_by_product

Microsoft's getting-started docs also describe installation through npx -y @microsoft/learn-docs-mcp.

Activation Conditions

Use symptom -> action triggers: when one matches, apply this skill and verify with the protocol below.

  • Verifying Azure SDK usage, limits, or configuration
  • Looking up .NET, Graph, Windows, or Microsoft 365 APIs
  • Pulling official code examples before implementation
  • Checking product-specific guidance for Azure, Power BI, or Power Platform

Recommended Workflow

1. Search first with microsoft_docs_search. 2. Narrow by product with microsoft_docs_search_by_product when results are broad. 3. Fetch the relevant page with microsoft_docs_fetch for details. 4. Extract code examples with microsoft_docs_extract_code_examples if the user needs working snippets. 5. Prefer official code and limits over recollection.

Query Patterns

  • "Azure Container Apps scale rules"
  • "BlobClient UploadAsync Azure.Storage.Blobs"
  • product="power-bi" query="row level security dax"
  • product="microsoft-graph" query="send mail application permissions"

Guardrails

  • Use Microsoft Learn MCP for Microsoft-specific answers before browsing elsewhere.
  • Treat package versions, quotas, and service capabilities as time-sensitive.
  • If Learn MCP is unavailable in the current client, use the included scripts and references as local fallbacks, then browse official docs.

Anti-Patterns

  • Changing infrastructure before inspecting the current state: Cloud drift and hidden dependencies make blind edits risky.
  • Hardcoding credentials or environment assumptions: Rollouts stop being reproducible and secrets become harder to rotate.
  • Skipping rollback, observability, or validation planning: You only notice the missing safeguards after the deployment is already live.

Verification Protocol

Before claiming "skill applied successfully":

1. Pass/fail: The Microsoft Development implementation names the target runtime, framework version, and affected files. 2. Pass/fail: Build, lint, test, or equivalent local validation is run for the changed surface. 3. Pass/fail: Edge cases for errors, dependency drift, and environment differences are addressed or explicitly out of scope. 4. Pressure-test scenario: Apply the workflow to a change that passes happy-path tests but fails one boundary condition. 5. Success metric: Zero untested success claims; every implementation claim maps to a command or artifact.

Before and After Example

# Before
az deployment group create `
  --resource-group app-rg `
  --template-file main.bicep

# After
$deploymentName = "api-$(Get-Date -Format yyyyMMddHHmmss)"
az deployment group create `
  --name $deploymentName `
  --resource-group app-rg `
  --template-file main.bicep `
  --parameters environment=prod `
  --what-if

Moves from an opaque deployment command to a traceable and reviewable workflow with named deployments, explicit parameters, and a preflight diff.

Common Pitfalls

  • Treating vendor examples as drop-in production code: Official snippets usually prove an API, not your project’s retry, logging, or auth requirements.
  • Skipping service-specific limits and permissions review: Azure and Microsoft 365 failures often come from quotas or scopes rather than syntax.
  • Relying on memory instead of current docs: Microsoft SDK behavior and surface area change often enough that stale recall is risky.

References & Resources

Documentation

  • Azure Services Quick Reference - Common Azure services, SDK packages, and decision points
  • .NET Patterns - Practical .NET design and dependency-injection patterns
  • Microsoft Learn MCP - Current tool names, install command, and query workflow

Scripts

  • Azure Health Check - Validate Azure login and inspect common resource health in a resource group

Examples

  • Azure Function API Example - Example serverless API workflow tied back to official Microsoft docs

<!-- PORTABILITY:START -->

Cross-Client Portability

This skill is written to stay usable across GitHub Copilot, Claude Code, Codex, and Gemini CLI.

  • GitHub Copilot: keep the folder in a Copilot-visible skill or plugin path, or wrap the workflow as project instructions if the host does not support portable skill folders directly.
  • Claude Code: keep the folder in a local skills directory or a compatible plugin or marketplace source.
  • Codex: install or sync the folder into $CODEX_HOME/skills/<skill-name> and restart Codex after major changes.
  • Gemini CLI: this repository generates a project command named /skills:microsoft-development from this skill. Rebuild commands with python scripts/export-gemini-skill.py microsoft-development and then run /commands reload inside Gemini CLI.

<!-- PORTABILITY:END -->

<!-- MCP:START -->

MCP Availability And Fallback

Preferred MCP Server: Microsoft Learn Docs MCP

  • Fallback prompt: "Use the Microsoft Development skill without MCP. Rely on the local SKILL.md, bundled references or scripts, and manual verification. Show the exact commands, evidence, and final checks you used before concluding."
  • Use Microsoft Learn in a browser and local SDK or CLI documentation when the docs MCP server is unavailable.
  • Verify generated commands or samples with the native toolchain (dotnet, az, PowerShell, etc.) before shipping them.

<!-- MCP:END -->

Related Skills

  • azure-integrations: Use it when the workflow also needs Azure deployment and infrastructure automation.
  • powerbi-modeling: Use it when the workflow also needs Power BI semantic model design and DAX work.
  • sql-development: Use it when the workflow also needs SQL query, schema, and performance tuning work.
  • documentation-authoring: Use it when the workflow also needs drafting structured technical or product documents.

Related skills

FAQ

What does microsoft-development do?

microsoft-development is a Claude Code skill for ai & agent building.

When should I use microsoft-development?

When you need to helps with ai & agent building tasks., or when microsoft-development is a claude code skill for ai & agent building.

What are the main capabilities?

microsoft-development; AI & Agent Building; AI-coding skill.

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.