Help us improve
Share bugs, ideas, or general feedback.
From ms-copilot-platform
Use when the user asks about the Microsoft Frontier Agent Platform architecture, how platform components fit together, solution architecture design, component selection, integration patterns, or the 10-layer platform model (Copilot UI, Agent Store, hosting, intelligence, protocols, MCP servers, connectors, data platform, systems of record, Agent Control System).
npx claudepluginhub bmarcurella/claude-marketplace --plugin ms-copilot-platformHow this skill is triggered — by the user, by Claude, or both
Slash command
/ms-copilot-platform:platform-architectureThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
This skill provides comprehensive knowledge of the Microsoft Frontier Agent Platform — the full
Provides UI/UX resources: 50+ styles, color palettes, font pairings, guidelines, charts for web/mobile across React, Next.js, Vue, Svelte, Tailwind, React Native, Flutter. Aids planning, building, reviewing interfaces.
Fetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.
Explores codebases via GitNexus: discover repos, query execution flows, trace processes, inspect symbol callers/callees, and review architecture.
Share bugs, ideas, or general feedback.
This skill provides comprehensive knowledge of the Microsoft Frontier Agent Platform — the full stack that powers AI agents across the Microsoft ecosystem. The platform has 10 interconnected layers, and understanding how they fit together is essential for designing effective agent solutions.
The Frontier Agent Platform is organized into these interconnected layers. Consult
references/platform-layers.md for detailed descriptions of each component.
The development side spans a spectrum from no-code to full pro-code:
When helping design a solution architecture:
Identify the scenario, user personas, data sources, integration points, compliance needs, and
scale expectations. Use references/requirements-template.md for a structured intake.
For each requirement, identify which platform layer(s) are involved. A typical agent solution
touches 4-6 layers. Consult references/platform-layers.md for component capabilities.
Choose specific components within each layer. Common patterns include:
| Pattern | Components | Best For |
|---|---|---|
| Simple Q&A Agent | Copilot UI → Agent Builder → SharePoint | Document retrieval, FAQ |
| Business Process Agent | Copilot UI → Copilot Studio → Power Automate → D365 | Workflow automation |
| Pro-Code Agent | Copilot UI → Agents SDK → Foundry → Azure AI | Custom orchestration |
| Multi-Agent System | Copilot UI → Custom Engine → A2A → Multiple Agents | Complex workflows |
| Data Intelligence Agent | Copilot UI → Fabric IQ → Microsoft Fabric → Dataverse | Analytics, BI |
Map how components communicate. Key integration protocols:
For every architecture, address:
Generate visual architecture diagrams using Mermaid or draw.io format.
Use references/diagram-templates.md for reusable architecture diagram patterns.
Always verify architecture details against current documentation. Use microsoft_docs_search
and microsoft_docs_fetch to:
references/platform-layers.md — Detailed breakdown of all 10 platform layers with every componentreferences/requirements-template.md — Structured requirements gathering templatereferences/diagram-templates.md — Reusable Mermaid architecture diagram templatesreferences/integration-patterns.md — Common integration patterns between layers