python-development
Workflow guidance for developing Python code in the Agent Framework repository. Use this when writing or modifying Python source files under python/.
- License 许可
- MIT
- 最近更新
- 2026-11-14
- Stars
- ★ 1.5w
- Forks
- 2.6k
01 前言 Front Matter
- name
- python-development
- description
- Workflow guidance for developing Python code in the Agent Framework repository. Use this when writing or modifying Python source files under python/.
02 资源文件 10
- 参考文档steps/step-00-scope.md5.6 KB
- 参考文档steps/step-pass1-ia.md5.3 KB
- 参考文档steps/step-pass2-states.md5.5 KB
- 参考文档steps/step-pass3-journey.md5.2 KB
- 参考文档steps/step-pass4-ai-slop.md6.7 KB
- 参考文档steps/step-pass5-design-sys.md5.9 KB
- 参考文档steps/step-pass6-a11y.md6.3 KB
- 参考文档steps/step-pass7-gaps.md6.4 KB
- 参考文档steps/step-report.md6.8 KB
- 参考文档workflow.md2.0 KB
03 SKILL.md 正文
Python Development Workflow
The canonical engineering rules are in
python/CODING_STANDARD.md. Read and apply that
document before changing Python source. Do not create or maintain a competing
copy of the standards in this skill.
Before Editing
- Read
python/AGENTS.mdand the nearest packageAGENTS.md. - Identify whether the change affects package source, tests, samples, public exports, package governance, or more than one of those surfaces.
- Read the task-specific skill when applicable:
python-testingfor test design, integration markers, and test commands.python-code-qualityfor formatting, linting, and type checking.python-package-managementfor package creation, dependencies, public lazy exports, and package lifecycle.python-feature-lifecyclefor staged API decorators and promotion.
Implementing Changes
- Follow established patterns in the owning package unless they conflict with
python/CODING_STANDARD.md. - Keep the common public path import-light and review public API changes for compatibility and ergonomics.
- Update source, typing surfaces, tests, samples, and documentation together when they represent the same contract.
- For root
agent_frameworkexport changes, follow the synchronized runtime,__all__, and.pyiworkflow inpython-package-management. - Do not broaden a change into unrelated cleanup solely because nearby code predates the current standard.
Validation
Run the smallest relevant commands from python/. Use
python-code-quality and python-testing to select package-scoped syntax,
typing, and test commands before escalating to broader checks.
When a convention, command, or workflow changes, update the canonical document or owning task-specific skill rather than duplicating the new guidance here.
04 同仓库更多 Skills
draft-release-notes
Create or rewrite Agent Framework release notes from a generated GitHub release log. Use when preparing Python or .NET release notes, filtering mixed-language changelogs, deduplicating changes, preserving inline contributor credits, or documenting breaking-change migrations from pull requests. Requires the user to provide the generated GitHub log, language, and release version before work begins.
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.
agent-framework-builder-dotnet
Use this skill when building, modifying, reviewing, evaluating, integrating, or hosting .NET (C#) 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.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and `azd ai agent run`) and after deploying it to an Azure AI Foundry project with `azd`. Use this when asked to validate a hosted agent sample.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded project_endpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
support-style
Contoso Outdoors customer-support tone and formatting guidelines.