team-charters

作者: microsoft

为多智能体编码团队提供角色章程(使命、所有权、核心原则、质量标准)。每个章程定义了角色的使命、所有权……

npx skills add https://github.com/microsoft/github-copilot-modernization --skill team-charters

Team Charters

Defines the mission, ownership, core principles, quality bar, and (for most roles) communication rules for each role in a multi-agent coding team. Each charter is a reference file under references/.

Available Roles

RoleMissionCharter
architectOwn the technical blueprint: how the system is built, how it should be rebuilt, whether the implementation follows the design, and build verification (smoke test)references/architect.md
backendOwn the server-side implementation: build the logic that powers the productreferences/backend.md
dbaOwn the data layer: make sure data is modeled correctly, stored safely, and migrates reliablyreferences/dba.md
devopsOwn CI/CD pipelines, deployment automation, and operational infrastructurereferences/devops.md
frontendOwn the client-side implementation: build what the user sees and interacts withreferences/frontend.md
pmOwn the product definition: what features exist, what needs to be built, and whether the delivered result matchesreferences/pm.md
securityAudit and verify security posture — find vulnerabilities and escalate, do NOT fix themreferences/security.md
teamleadOwn the execution blueprint and quality gates: constitution, implementation plans, testing strategies, task breakdowns, and gate verdictsreferences/teamlead.md
testerOwn runtime-validation execution: verify that the system works correctly by executing the approved testing strategy through integration and end-to-end testingreferences/tester.md
uxOwn user experience design: how users interact with the system, what they see, and how information is organizedreferences/ux.md

Usage

To look up a specific role's charter, read references/<role>.md. Each charter contains:

  1. Mission — one-line purpose statement
  2. You Own — ownership scope for the role
  3. Core Principle — boundary constraints and what the role must NOT do
  4. Quality Bar — minimum standards the role must meet
  5. Communication (most roles) — when and whom to notify or escalate to

Key Design Principles

  • WHAT vs HOW: PM defines WHAT (features, acceptance criteria). Architect defines HOW (design, patterns, contracts).
  • Validation planning vs validation execution: teamlead owns testing strategy and conformance review; tester owns runtime-validation execution only.
  • Read-only roles: PM, architect, security, ux produce documentation only — no source code. Teamlead focuses on planning and quality gates.
  • Tester never modifies production code — escalates bugs to the responsible role.
  • Ownership boundaries are strict — if work crosses into another role's territory, delegate via notify/escalate.

来自 microsoft 的更多技能

oss-growth
microsoft
OSS增长黑客角色
agent-framework-azure-ai-py
microsoft
使用Microsoft Agent Framework Python SDK(agent-framework-azure-ai)构建Azure AI Foundry代理。在创建使用AzureAIAgentsProvider的持久化代理、使用托管工具(代码解释器、文件搜索、网络搜索)、集成MCP服务器、管理对话线程或实现流式响应时使用。涵盖函数工具、结构化输出和多工具代理。
development
airunway-aks-setup
microsoft
在AKS上设置AI Runway——从裸集群到运行模型。涵盖集群验证、控制器安装、GPU评估、提供商设置和首次部署。适用场景:“设置AI Runway”、“接入AKS集群”、“安装AI Runway”、“airunway设置”、“将模型部署到AKS”、“在AKS上进行GPU推理”、“在AKS上配置KAITO”、“在AKS上运行LLM”、“在AKS上使用vLLM”、“在AKS上设置模型服务”、“AI Runway控制器”。
devops
appinsights-instrumentation
microsoft
使用Azure Application Insights对Web应用进行插桩的指南。提供遥测模式、SDK设置和配置参考。适用场景:如何对应用进行插桩、App Insights SDK、遥测模式、什么是App Insights、Application Insights指南、插桩示例、APM最佳实践。
devops
applicationinsights-web-ts
microsoft
使用Application Insights JavaScript SDK(@microsoft/applicationinsights-web)为浏览器/Web应用添加检测。用于真实用户监控(RUM)——页面视图、点击、AJAX/fetch依赖项、异常、自定义事件,以及与后端OpenTelemetry追踪关联的浏览器端GenAI代理追踪。涵盖SDK加载器脚本和npm设置、框架扩展(React、React Native、Angular)、点击分析、遥测初始化器,以及从浏览器发出的代理/工具/模型跨度所遵循的OTel GenAI语义约定。
devops
azure-ai-anomalydetector-java
microsoft
使用适用于 Java 的 Azure AI 异常检测器 SDK 构建异常检测应用程序。在实现单变量/多变量异常检测、时间序列分析或 AI 驱动的监控时使用。
development
azure-ai-language-conversations-py
microsoft
使用azure-ai-language-conversations Python SDK实现对话语言理解(CLU)。当使用ConversationAnalysisClient分析对话意图和实体、构建NLP功能或将语言理解集成到应用程序中时使用。
development
azure-ai-ml-py
microsoft
Azure Machine Learning SDK v2 for Python。用于机器学习工作区、作业、模型、数据集、计算资源和管道。 触发词:“azure-ai-ml”、“MLClient”、“工作区”、“模型注册表”、“训练作业”、“数据集”。
development