agent-framework-builder-python
Use this skill when building, modifying, reviewing, evaluating, integrating, or hosting Python applications with Microsoft Agent Framework. Use it for Agent Framework agents, harness agents, workflows, orchestrations, declarative definitions, tools, sessions, middleware, evaluation, observability, integrations, or hosting, even when the user has not yet chosen the correct framework pattern.
How do I install this agent skill?
npx skills add https://github.com/microsoft/agent-framework --skill agent-framework-builder-pythonIs this agent skill safe to install?
- Gen Agent Trust Hubpass
This skill provides architectural guidance for building Python applications using the Microsoft Agent Framework. It incorporates several security-conscious design patterns, including explicit tool approval modes, guidance on managing sensitive session data, and recommendations for sandboxing autonomous operations. The skill references official Microsoft documentation and repositories, aligning with standard development practices for this ecosystem.
- Socketpass
No alerts
- Snykpass
Risk: LOW · No issues
What does this agent skill do?
Agent Framework builder for Python
Use this skill as the entry point for Python Agent Framework application work. Choose the smallest framework pattern that preserves the required behavior, load only the relevant references, and validate against current APIs instead of relying on remembered preview-era syntax.
Workflow
- Inspect the existing project, Python version, dependency manager, and installed Agent Framework packages.
- Choose the simplest matching path from the table below.
- Resolve design questions only when they materially change the implementation.
- Read only the linked reference for the selected path.
- Implement the smallest coherent change and run the narrowest validation that exercises it.
Core abstractions
- A chat client implements the model-facing
SupportsChatGetResponseprotocol. It sends messages and options to a model provider and returns chat responses or streaming updates. - An agent implements the
SupportsAgentRunprotocol. The standardAgentimplementation combines a chat client with instructions, tools, middleware, context providers, and session handling behind onerun(...)interface. - A harness agent is a regular
Agentassembled bycreate_harness_agent. It adds an opinionated set of context providers and middleware; it does not introduce a separate agent abstraction. - A workflow coordinates explicit execution paths. Graph workflows and most orchestration builders can use multiple
SupportsAgentRunimplementations or executors.HandoffBuilderis the exception: its participants must be concreteAgentinstances.
User interface options
- DevUI is a local development, testing, and debugging tool for interacting with agents and workflows. Never run or deploy DevUI as a production application host.
- AG-UI is the application-facing protocol integration for connecting an agent or workflow to an AG-UI-compatible
frontend. Use the
agent-framework-ag-uipackage when the product needs streaming UI events, tool interactions, shared state, interrupts, or resume behavior.
Choose the build path
| Path | Choose it when | Details |
|---|---|---|
| Plain agent | One model-driven actor owns the task and tools, sessions, context, and middleware are sufficient. | Plain agents |
| Harness agent | The product needs an operating loop with todos, modes, memory, approvals, skills, optional file access, background agents, shell, compaction, or repeated execution. | Harness agents |
| Workflow or orchestration | Explicit stages, routing, parallelism, multiple participants, checkpointing, human input, or intermediate outputs are central to correctness. | Workflows |
| Declarative definition | YAML or JSON should be the source of truth for a supported agent or workflow. | Declarative definitions |
| Evaluation | Expected outputs, tool calls, failed runs, or quality regressions are the main concern. | Evaluation |
| Observability | The task is diagnosing or monitoring runtime behavior with traces, logs, and metrics. | Observability |
| Extensibility | The application needs a custom provider, ContextProvider, or middleware component. | Extensibility |
| Integration | The task is choosing or wiring a provider, protocol, memory store, tool service, UI, or platform extension. | Integrations |
| Hosting and deployment | Working Agent Framework code needs a process host, protocol endpoint, identity contract, or deployment shape. | Hosting and deployment |
Defaults
- Agent Framework requires Python 3.11 or later. Prefer the latest supported Python release or the previous release (N-1), unless a required dependency has a narrower compatibility range.
- Install the narrow Agent Framework distribution needed by the application instead of defaulting to the
agent-frameworkmeta-package. - Agent Framework does not automatically read
.envfiles. If the project uses one, callload_dotenv()explicitly or use the selected API's documentedenv_file_pathor equivalent initialization option.
Current documentation lookup
This skill and its references guide high-level development choices; they are not product documentation. Use them for selection criteria, trade-offs, and constraints that materially change a choice. Microsoft Learn is the documentation source for implementing the selected approach.
For provider matrices, package maturity, hosted tools, deployment details, or unfamiliar APIs, consult current sources before generating code. Use public docstrings or API reference pages for signatures and option details, and use Learn or maintained samples for end-to-end procedures. Do not copy those details into this skill or its references.
When the coding agent supports MCP, configure the Microsoft Learn MCP Server as a Streamable HTTP server:
https://learn.microsoft.com/api/mcp
See Microsoft Learn MCP Server setup for client configuration. The endpoint is for MCP clients and returns an error when opened directly in a browser.
- Search Microsoft Learn with
microsoft_docs_search. - Fetch the relevant page with
microsoft_docs_fetch. - Use
microsoft_code_sample_searchwhen a current implementation example is needed. - If Learn MCP is unavailable and a trusted
mslearnCLI is already installed, use the equivalent command:
| MCP tool | Preinstalled CLI |
|---|---|
microsoft_docs_search(query="...") | mslearn search "..." |
microsoft_docs_fetch(url="...") | mslearn fetch "..." |
microsoft_code_sample_search(query="...", language="python") | mslearn code-search "..." --language python |
Do not fetch and execute an unpinned CLI package during a coding session. Use the official Microsoft Learn MCP/CLI setup to install or update it intentionally.
Canonical starting points:
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/microsoft/agent-framework/agent-framework-builder-python">View agent-framework-builder-python on skillZs</a>