Skip to content

borghei/Claude-Skills / engineering/agent-designer

agent-designer

Verified

Designs multi-agent system architectures with orchestration patterns, tool schemas, and performance evaluation. Use when building AI agent systems, designing agent workflows, creating tool schemas, or evaluating agent performance.

assets/sample_system_requirements.json

View on GitHub
{
  "goal": "Build a comprehensive research and analysis platform that can gather information from multiple sources, analyze data, and generate detailed reports",
  "description": "The system needs to handle complex research tasks involving web searches, data analysis, document processing, and collaborative report generation. It should be able to coordinate multiple specialists working in parallel while maintaining quality control and ensuring comprehensive coverage of research topics.",
  "tasks": [
    "Conduct multi-source web research on specified topics",
    "Analyze and synthesize information from various sources",
    "Perform data processing and statistical analysis",
    "Generate visualizations and charts from data",
    "Create comprehensive written reports",
    "Fact-check and validate information accuracy",
    "Coordinate parallel research streams",
    "Handle real-time information updates",
    "Manage research project timelines",
    "Provide interactive research assistance"
  ],
  "constraints": {
    "max_response_time": 30000,
    "budget_per_task": 1.0,
    "quality_threshold": 0.9,
    "concurrent_tasks": 10,
    "data_retention_days": 90,
    "security_level": "standard",
    "compliance_requirements": ["GDPR", "data_minimization"]
  },
  "team_size": 6,
  "performance_requirements": {
    "high_throughput": true,
    "fault_tolerance": true,
    "low_latency": false,
    "scalability": "medium",
    "availability": 0.99
  },
  "safety_requirements": [
    "Input validation and sanitization",
    "Output content filtering",
    "Rate limiting for external APIs",
    "Error handling and graceful degradation",
    "Human oversight for critical decisions",
    "Audit logging for all operations"
  ],
  "integration_requirements": [
    "REST API endpoints for external systems",
    "Webhook support for real-time updates",
    "Database integration for data persistence",
    "File storage for documents and media",
    "Email notifications for important events",
    "Dashboard for monitoring and control"
  ],
  "scale_requirements": {
    "initial_users": 50,
    "peak_concurrent_users": 200,
    "data_volume_gb": 100,
    "requests_per_hour": 1000,
    "geographic_regions": ["US", "EU"],
    "growth_projection": "50% per year"
  }
}
brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).Stars: 322kUpdated Claude CodeCodexVerifiedInstall
brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).Stars: 198kUpdated Claude CodeCodexVerifiedInstall