Microsoft Agent Framework
Implement Microsoft Agent Framework agents and workflows in .NET or Python with correct packages, async patterns, and sample-aligned architecture.
Overview
microsoft-agent-framework is an agent skill for the Build phase that teaches solo builders how to install and structure Microsoft Agent Framework projects in .NET and Python using official samples and idiomatic async, DI
Install
npx skills add https://github.com/github/awesome-copilot --skill microsoft-agent-frameworkWhat is this skill?
- Dual-language reference for .NET (Microsoft.Agents.AI) and Python (agent-framework) with official repo and sample links
- .NET guidance covers async/await, dependency injection, hosting, authentication, and idiomatic middleware
- Python guidance emphasizes modern async, explicit APIs, and type hints in dynamic agent code
- Points builders to upstream dotnet/python sample trees before adopting new APIs or workflow patterns
- Authoritative dotnet and python sample trees linked from SKILL.md
Adoption & trust: 1.6k installs on skills.sh; 34.6k GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
You want Microsoft-hosted agents in .NET or Python but lack a concise map from packages and repos to async, DI, middleware, and workflow patterns that match the framework’s current samples.
Who is it for?
Indie builders adding multi-step agents or workflows to an existing .NET or Python product using Microsoft Agent Framework.
Skip if: Teams only wiring OpenAI/Anthropic SDKs without Agent Framework, or non-Microsoft stacks where this reference adds no install or hosting guidance.
When should I use this skill?
Target project is C#/.NET or Python and you are implementing or extending Microsoft Agent Framework agents, workflows, hosting, or middleware.
What do I get? / Deliverables
You get stack-specific install paths, authoritative sample links, and implementation norms so your agent services register, authenticate, and run workflows the way Agent Framework expects.
- Package install commands (dotnet add / pip install)
- Architecture aligned with official Agent Framework samples
Recommended Skills
Journey fit
Canonical shelf is Build because the skill is authoritative implementation guidance for agent runtime, orchestration, and hosting—not distribution or compliance. Agent-tooling is the best fit for framework installation, middleware, context providers, and workflow execution patterns.
How it compares
Framework implementation reference for Microsoft’s agent runtime—not a generic prompt pack or an MCP server catalog entry.
Common Questions / FAQ
Who is microsoft-agent-framework for?
Solo and small-team developers shipping agent features in C#/.NET or Python who standardize on Microsoft Agent Framework rather than ad-hoc LLM scripts.
When should I use microsoft-agent-framework?
During Build agent-tooling when scaffolding agents, workflows, middleware, or hosting; also when refactoring async agent code before Ship review if you are on the Microsoft stack.
Is microsoft-agent-framework safe to install?
Treat it as documentation-style guidance; review the Security Audits panel on this Prism page and vet any network-facing agent auth you add in your own repo.
SKILL.md
READMESKILL.md - Microsoft Agent Framework
# Microsoft Agent Framework for .NET Use this reference when the target project is written in C# or another .NET language. ## Authoritative sources - Repository: <https://github.com/microsoft/agent-framework/tree/main/dotnet> - Samples: <https://github.com/microsoft/agent-framework/tree/main/dotnet/samples> ## Installation For new projects, install the package with: ```bash dotnet add package Microsoft.Agents.AI ``` ## .NET-specific guidance - Use `async`/`await` patterns consistently for agent operations and workflow execution. - Follow .NET type-safety and dependency-injection conventions. - Keep service registration, configuration, and authentication aligned with standard .NET hosting patterns. - Use middleware, context providers, and orchestration components idiomatically within the .NET application model. - Check the latest .NET samples before introducing new APIs or workflow patterns. # Microsoft Agent Framework for Python Use this reference when the target project is written in Python. ## Authoritative sources - Repository: <https://github.com/microsoft/agent-framework/tree/main/python> - Samples: <https://github.com/microsoft/agent-framework/tree/main/python/samples> ## Installation For new projects, install the package with: ```bash pip install agent-framework ``` ## Python-specific guidance - Use modern async patterns throughout agent and workflow operations. - Add type hints and keep APIs explicit even in dynamic code. - Follow standard Python packaging and environment practices for dependencies and tooling. - Use middleware, context providers, and orchestration patterns in ways that fit the Python application structure. - Check the latest Python samples before introducing new APIs or workflow patterns. --- name: microsoft-agent-framework description: 'Create, update, refactor, explain, or review Microsoft Agent Framework solutions using shared guidance plus language-specific references for .NET and Python.' --- # Microsoft Agent Framework Use this skill when working with applications, agents, workflows, or migrations built on Microsoft Agent Framework. Microsoft Agent Framework is the unified successor to Semantic Kernel and AutoGen, combining their strengths with new capabilities. Because it is still in public preview and changes quickly, always ground implementation advice in the latest official documentation and samples rather than relying on stale knowledge. ## Determine the target language first Choose the language workflow before making recommendations or code changes: 1. Use the **.NET** workflow when the repository contains `.cs`, `.csproj`, `.sln`, `.slnx`, or other .NET project files, or when the user explicitly asks for C# or .NET guidance. Follow [references/dotnet.md](references/dotnet.md). 2. Use the **Python** workflow when the repository contains `.py`, `pyproject.toml`, `requirements.txt`, or the user explicitly asks for Python guidance. Follow [references/python.md](references/python.md). 3. If the repository contains both ecosystems, match the language used by the files being edited or the user's stated target. 4. If the language is ambiguous, inspect the current workspace first and then choose the closest language-specific reference. ## Always consult live documentation - Read the Microsoft Agent Framework overview first: <https://learn.microsoft.com/agent-framework/overview/agent-framework-overview> - Prefer official docs and samples for the current API surface. - Use the Microsoft Docs MCP tooling when available to fetch up-to-date framework guidance and examples. - Treat older Semantic Kernel or AutoGen patterns as migration inputs, not as the default implementation model. ## Shared guidance When working with Microsoft Agent Framework in any language: - Use async patterns for agent and workflow operations. - Implement explicit error handling and logging. - Prefer strong typing, clear interfaces, and maintainable composition patterns. - Use `DefaultAzureCredentia