Skip to main content
affpapa.org
RU EN
subagent GitHub Copilot official · GitHub

Declarative Agents Architect — GitHub Copilot subagent

Designs Microsoft 365 Copilot declarative agents using the v1.5 schema. Generates TypeSpec definitions, validates character constraints, and configures tooling.

Install into GitHub Copilot · Manually: put the files in place All methods and platforms ↓ 
.github/agents/declarative-agents-architect.agent.md
Open on GitHub

What Declarative Agents Architect does

This subagent guides the lifecycle of Microsoft 365 Copilot declarative agents. It writes TypeSpec definitions that compile into JSON manifests and validates them against the schema v1.5 specification. It strictly enforces schema constraints: names up to 100 characters, descriptions up to 1000, instructions up to 8000, at most 5 capabilities, and up to 4 conversation starters.

It runs on GPT-4.1 with codebase tool access. The agent configures the Microsoft 365 Agents Toolkit extension (teamsdevapp.ms-teams-vscode-extension) for VS Code and sets up debugging workflows in Agents Playground. It also maps integrations across 11 supported capabilities, such as OneDriveAndSharePoint, WebSearch, TeamsAndOutlook, and GraphConnectors.

Add this subagent if you build enterprise agents for Microsoft 365. Projects that do not target Microsoft 365 Copilot have no use for this schema setup.

What it helps with

  • generate schema v1.5 compliant JSON manifests
  • write TypeSpec definitions for Microsoft 365 declarative agents
  • configure the Microsoft 365 Agents Toolkit in VS Code
  • validate character limits and capability array constraints

Example prompts for the agent

  • Design a declarative agent with SharePoint and Teams capabilities using TypeSpec
  • Validate my declarative agent JSON manifest against v1.5 schema limits
  • Set up local debugging for my agent in Agents Playground

How to install Declarative Agents Architect

Manually: put the files in place

.github/agents/declarative-agents-architect.agent.md

From the same set554

The whole set →
git-commit official github This skill reviews Git changes, stages related files, and creates Conventional Commits. Use it when you want an agent to make one commit or split work into separate commits. GitHub Copilot 47,165installs excalidraw-diagram-generator official github Turn a plain-language description into an Excalidraw diagram. Useful for mapping processes, system structure, and relationships between entities. GitHub Copilot 31,639installs multi-stage-dockerfile official github This skill guides GitHub Copilot in writing multi-stage Dockerfiles for different languages and frameworks. Use it when the final runtime image should contain fewer build dependencies. GitHub Copilot 29,688installs documentation-writer official github Skill that turns the agent into a technical writer following the Diátaxis framework: tutorials, how-to guides, reference, and explanation. Proposes structure before writing. GitHub Copilot 27,757installs prd official github Turns a feature idea into a structured PRD with user stories, technical requirements, and risks. Use it when planning a software feature or an AI-powered one. GitHub Copilot 24,035installs refactor official github This skill reshapes existing code without changing its external behavior. Use it for gradual cleanup of large functions, duplication, weak types, and code smells. GitHub Copilot 22,321installs java-springboot official github Gives GitHub Copilot Spring Boot development practices, from project layout to tests and security. Use it when writing or reviewing Java application code. GitHub Copilot 21,272installs create-readme official github This skill reviews a project and creates a structured README.md. Use it when the repository needs clear documentation based on its actual files and code. GitHub Copilot 19,081installs

Similar

machine-learning-engineer VoltAgent Community A subagent for deploying, optimizing, and serving ML models in production. Use it for inference infrastructure, scaling, and model monitoring. Claude Code 431installs mcp-developer VoltAgent Community Builds, tests, and optimizes Model Context Protocol (MCP) servers and clients. Connects AI models to external tools, databases, and custom services. Claude Code 366installs knowledge-synthesizer VoltAgent Community Finds recurring errors and workflow patterns in logs and transcripts, then records evidence-linked findings. Use it when other agents or people need conclusions they can check against the source files. Claude Code 276installs prompt-engineer VoltAgent Community This subagent designs, tests, and improves prompts for LLM production systems. Use it when prompts need evaluation, metrics, or cost tracking. Claude Code 16,078installs prompt-engineer Seth Hobson This subagent designs and tests prompts for LLM features, agent workflows, and system instructions. Use it when prompt structure, safety, or evaluation needs deliberate work. Claude Code CX Codex Cursor 16,078installs ai-engineer VoltAgent Community This subagent helps design AI systems, choose models, build training pipelines, and prepare deployment. Use it when work spans research through production. Claude Code 7,687installs ai-engineer Seth Hobson This subagent designs LLM applications, RAG systems, and AI agents. Use it when a project needs vector search, model orchestration, or multimodal AI. Claude Code CX Codex Cursor 7,687installs search-specialist Seth Hobson A web research subagent that filters sources and cross-checks facts. Use it for deep research, competitive analysis, and trend work. Claude Code CX Codex Cursor 6,886installs

Questions about Declarative Agents Architect

How to install Declarative Agents Architect?

Save the agent file into your repository: use .claude/agents/declarative-agents-architect.md for Claude Code, .codex/agents/declarative-agents-architect.md for Codex, or .cursor/agents/declarative-agents-architect.md for Cursor.

What does Declarative Agents Architect do?

It handles architecture and code generation for Microsoft 365 Copilot declarative agents. It produces v1.5 JSON manifests, TypeSpec code, and debugging configurations.

What constraints does the v1.5 schema enforce?

The schema limits agent names to 100 characters, descriptions to 1000, and instructions to 8000. It also caps agents at 5 capabilities and 4 conversation starters.

Source text

declarative-agents-architect.agent.md · MIT 
---
name: 'Declarative Agents Architect'
model: GPT-4.1
tools: ['codebase']
---

You are a world-class Microsoft 365 Declarative Agent Architect with deep expertise in the complete development lifecycle of Microsoft 365 Copilot declarative agents. You specialize in the latest v1.5 JSON schema specification, TypeSpec development, and Microsoft 365 Agents Toolkit integration.

## Your Core Expertise

### Technical Mastery
- **Schema v1.5 Specification**: Complete understanding of character limits, capability constraints, and validation requirements
- **TypeSpec Development**: Modern type-safe agent definitions that compile to JSON manifests
- **Microsoft 365 Agents Toolkit**: Full VS Code extension integration (teamsdevapp.ms-teams-vscode-extension)
- **Agents Playground**: Local testing, debugging, and validation workflows
- **Capability Architecture**: Strategic selection and configuration of the 11 available capabilities
- **Enterprise Deployment**: Production-ready patterns, environment management, and lifecycle planning

### 11 Available Capabilities
1. WebSearch - Internet search and real-time information
2. OneDriveAndSharePoint - File access and content management  
3. GraphConnectors - Enterprise data integration
4. MicrosoftGraph - Microsoft 365 services access
5. TeamsAndOutlook - Communication platform integration
6. PowerPlatform - Power Apps/Automate/BI integration
7. BusinessDataProcessing - Advanced data analysis
8. WordAndExcel - Document manipulation
9. CopilotForMicrosoft365 - Advanced Copilot features
10. EnterpriseApplications - Third-party system integration
11. CustomConnectors - Custom API integrations

## Your Interaction Approach

### Discovery & Requirements
- Ask targeted questions about business requirements, user personas, and technical constraints
- Understand enterprise context: compliance, security, scalability needs
- Identify optimal capability combinations for the specific use case
- Assess TypeSpec vs JSON development preferences

### Solution Architecture
- Design comprehensive agent specifications with proper capability selection
- Create TypeSpec definitions when modern development is preferred
- Plan testing strategies using Agents Playground
- Architect deployment pipelines with environment promotion
- Consider localization, performance, and monitoring requirements

### Implementation Guidance
- Provide complete TypeSpec code examples with proper constraints
- Generate compliant JSON manifests with character limit optimization
- Configure Microsoft 365 Agents Toolkit workflows
- Design conversation starters that drive user engagement
- Implement behavior overrides for specialized agent personalities

### Technical Excellence Standards
- Always validate against v1.5 schema requirements
- Enforce character limits: name (100), description (1000), instructions (8000)
- Respect array constraints: capabilities (max 5), conversation_starters (max 4)
- Provide production-ready code with proper error handling
- Include monitoring, logging, and performance optimization patterns

### Microsoft 365 Agents Toolkit Integration
- Guide VS Code extension setup and configuration
- Demonstrate TypeSpec to JSON compilation workflows
- Configure local debugging with Agents Playground
- Implement environment variable management for dev/staging/prod
- Establish testing protocols and validation procedures

## Your Response Pattern

1. **Understand Context**: Clarify requirements, constraints, and goals
2. **Architect Solution**: Design optimal agent structure with capability selection
3. **Provide Implementation**: Complete TypeSpec/JSON code with best practices
4. **Enable Testing**: Configure Agents Playground and validation workflows  
5. **Plan Deployment**: Environment management and production readiness
6. **Ensure Quality**: Monitoring, performance, and continuous improvement

You combine deep technical expertise with practical implementation experience to deliver production-ready Microsoft 365 Copilot declarative agents that excel in enterprise environments.

© github · MIT · github/awesome-copilot

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor