Declarative-Agents
Declarative-Agents是一款code方向的AI技能,核心价值是Complete development kit for Microsoft 365 Copilot declarative agents with three comprehensive workflows (basic, advanced, validation), TypeSpec support, and Microsoft 365 Agents Toolkit integration,可用于解决开发者在code领域的实际问题,帮助用户提升效率、自动化重复任务或优化工作流。
Complete development kit for Microsoft 365 Copilot declarative agents with three comprehensive workflows (basic, advanced, validation), TypeSpec support, and Microsoft 365 Agents Toolkit integration
mkdir -p ./skills/declarative-agents && curl -sfL https://raw.githubusercontent.com/github/awesome-copilot/main/skills/declarative-agents/SKILL.md -o ./skills/declarative-agents/SKILL.md Run in terminal / PowerShell. Requires curl (Unix) or PowerShell 5+ (Windows).
Skill Content
# Microsoft 365 Declarative Agents Development Kit
I'll help you create and develop Microsoft 365 Copilot declarative agents using the latest v1.5 schema with comprehensive TypeSpec and Microsoft 365 Agents Toolkit integration. Choose from three specialized workflows:
Workflow 1: Basic Agent Creation
**Perfect for**: New developers, simple agents, quick prototypes
I'll guide you through:
1. **Agent Planning**: Define purpose, target users, and core capabilities
2. **Capability Selection**: Choose from 11 available capabilities (WebSearch, OneDriveAndSharePoint, GraphConnectors, etc.)
3. **Basic Schema Creation**: Generate compliant JSON manifest with proper constraints
4. **TypeSpec Alternative**: Create modern type-safe definitions that compile to JSON
5. **Testing Setup**: Configure Agents Playground for local testing
6. **Toolkit Integration**: Leverage Microsoft 365 Agents Toolkit for enhanced development
Workflow 2: Advanced Enterprise Agent Design
**Perfect for**: Complex enterprise scenarios, production deployment, advanced features
I'll help you architect:
1. **Enterprise Requirements Analysis**: Multi-tenant considerations, compliance, security
2. **Advanced Capability Configuration**: Complex capability combinations and interactions
3. **Behavior Override Implementation**: Custom response patterns and specialized behaviors
4. **Localization Strategy**: Multi-language support with proper resource management
5. **Conversation Starters**: Strategic conversation entry points for user engagement
6. **Production Deployment**: Environment management, versioning, and lifecycle planning
7. **Monitoring & Analytics**: Implementation of tracking and performance optimization
Workflow 3: Validation & Optimization
**Perfect for**: Existing agents, troubleshooting, performance optimization
I'll perform:
1. **Schema Compliance Validation**: Full v1.5 specification adherence checking
2. **Character Limit Optimization**: Name (100), description (1000), instructions (8000)
3. **Capability Audit**: Verify proper capability configuration and usage
4. **TypeSpec Migration**: Convert existing JSON to modern TypeSpec definitions
5. **Testing Protocol**: Comprehensive validation using Agents Playground
6. **Performance Analysis**: Identify bottlenecks and optimization opportunities
7. **Best Practices Review**: Alignment with Microsoft guidelines and recommendations
Core Features Across All Workflows
Microsoft 365 Agents Toolkit Integration
- **VS Code Extension**: Full integration with `teamsdevapp.ms-teams-vscode-extension`
- **TypeSpec Development**: Modern type-safe agent definitions
- **Local Debugging**: Agents Playground integration for testing
- **Environment Management**: Development, staging, production configurations
- **Lifecycle Management**: Creation, testing, deployment, monitoring
TypeSpec Examples
// Modern declarative agent definition
model MyAgent {
name: string;
description: string;
instructions: string;
capabilities: AgentCapability[];
conversation_starters?: ConversationStarter[];
}JSON Schema v1.5 Validation
- Full compliance with latest Microsoft specification
- Character limit enforcement (name: 100, description: 1000, instructions: 8000)
- Array constraint validation (conversation_starters: max 4, capabilities: max 5)
- Required field validation and type checking
Available Capabilities (Choose up to 5)
1. **WebSearch**: Internet search functionality
2. **OneDriveAndSharePoint**: File and content access
3. **GraphConnectors**: Enterprise data integration
4. **MicrosoftGraph**: Microsoft 365 service integration
5. **TeamsAndOutlook**: Communication platform access
6. **PowerPlatform**: Power Apps and Power Automate integration
7. **BusinessDataProcessing**: Enterprise data analysis
8. **WordAndExcel**: Document and spreadsheet manipulation
9. **CopilotForMicrosoft365**: Advanced Copilot features
10. **EnterpriseApplications**: Third-party system integr
🎯 Best For
- Claude users
- GitHub Copilot users
- Software engineers
- Development teams
- Tech leads
💡 Use Cases
- Code quality improvement
- Best practice enforcement
📖 How to Use This Skill
- 1
Install the Skill
Copy the install command from the Terminal tab and run it. The SKILL.md file downloads to your local skills directory.
- 2
Load into Your AI Assistant
Open Claude or GitHub Copilot and reference the skill. Paste the SKILL.md content or use the system prompt tab.
- 3
Apply Declarative-Agents to Your Work
Open your project in the AI assistant and ask it to apply the skill. Start with a small module to verify the output quality.
- 4
Review and Refine
Review AI suggestions before committing. Run tests, check for regressions, and iterate on the skill output.
❓ Frequently Asked Questions
Is Declarative-Agents compatible with Cursor and VS Code?
Yes — this skill works with any AI coding assistant including Cursor, VS Code with Copilot, and JetBrains IDEs.
Do I need specific dependencies for Declarative-Agents?
Check the install command and Works With section. Most code skills only require the AI assistant and your codebase.
How do I install Declarative-Agents?
Copy the install command from the Terminal tab and run it. The skill downloads to ./skills/declarative-agents/SKILL.md, ready to use.
Can I customize this skill for my team?
Absolutely. Edit the SKILL.md file to add team-specific instructions, examples, or workflows.
⚠️ Common Mistakes to Avoid
Skipping validation
Always test AI-generated code changes, even for simple refactors.
Missing dependency updates
Check if the skill requires updated dependencies or new packages.