multi-agent-rolesProvides standardized, role-based AI agents for multi-agent systems with clear responsibilities across strategy, creative, technical, and management domains.
Install via ClawdBot CLI:
clawdbot install xiulipan/multi-agent-rolesThis skill provides a comprehensive framework for designing professional multi-agent systems. It includes standardized role definitions for various AI applications and workflows.
A well-designed multi-agent system requires:
{
"agents": {
"list": [
{
"id": "marketing_strategist",
"workspace": "/workspaces/marketing-agency/strategist",
"agentDir": "/agents/marketing-strategist",
"config": {
"role": "Strategic Planner",
"expertise": "marketing strategy, brand positioning",
"responsibilities": [
"Develop overall marketing strategy",
"Define campaign objectives",
"Allocate marketing budget"
]
}
},
{
"id": "content_creator",
"workspace": "/workspaces/marketing-agency/content",
"agentDir": "/agents/content-creator",
"config": {
"role": "Content Strategist",
"expertise": "content planning, copywriting",
"responsibilities": [
"Create content calendars",
"Write marketing copy",
"Manage social media content"
]
}
},
{
"id": "graphic_designer",
"workspace": "/workspaces/marketing-agency/design",
"agentDir": "/agents/graphic-designer",
"config": {
"role": "Creative Director",
"expertise": "visual design, branding",
"responsibilities": [
"Create visual assets",
"Maintain brand consistency",
"Design marketing materials"
]
}
},
{
"id": "analytics_specialist",
"workspace": "/workspaces/marketing-agency/analytics",
"agentDir": "/agents/analytics-specialist",
"config": {
"role": "Data Analyst",
"expertise": "marketing analytics, performance tracking",
"responsibilities": [
"Track campaign performance",
"Analyze user behavior",
"Generate performance reports"
]
}
}
]
},
"bindings": [
{
"agentId": "marketing_strategist",
"match": { "channel": "any", "peer": { "kind": "direct" } }
},
{
"agentId": "content_creator",
"match": { "channel": "any", "text": { "contains": ["content", "copy", "writing"] } }
},
{
"agentId": "graphic_designer",
"match": { "channel": "any", "text": { "contains": ["design", "visual", "logo"] } }
},
{
"agentId": "analytics_specialist",
"match": { "channel": "any", "text": { "contains": ["analytics", "report", "metrics"] } }
}
]
}
{
"agents": {
"list": [
{
"id": "technical_architect",
"workspace": "/workspaces/dev-team/architecture",
"agentDir": "/agents/technical-architect",
"config": {
"role": "Technical Architect",
"expertise": "system design, architecture patterns",
"responsibilities": [
"Design system architecture",
"Make technical decisions",
"Review code architecture"
]
}
},
{
"id": "frontend_developer",
"workspace": "/workspaces/dev-team/frontend",
"agentDir": "/agents/frontend-developer",
"config": {
"role": "Full-Stack Developer",
"expertise": "React, JavaScript, UI design",
"responsibilities": [
"Develop user interfaces",
"Implement frontend functionality",
"Optimize performance"
]
}
},
{
"id": "backend_developer",
"workspace": "/workspaces/dev-team/backend",
"agentDir": "/agents/backend-developer",
"config": {
"role": "Full-Stack Developer",
"expertise": "Node.js, Python, databases",
"responsibilities": [
"Develop APIs",
"Design database schema",
"Implement business logic"
]
}
},
{
"id": "qa_engineer",
"workspace": "/workspaces/dev-team/qa",
"agentDir": "/agents/qa-engineer",
"config": {
"role": "QA Engineer",
"expertise": "testing, automation, debugging",
"responsibilities": [
"Write test cases",
"Run test automation",
"Identify and report bugs"
]
}
}
]
},
"bindings": [
{
"agentId": "technical_architect",
"match": { "text": { "contains": ["architecture", "design", "technical"] } }
},
{
"agentId": "frontend_developer",
"match": { "text": { "contains": ["frontend", "UI", "React"] } }
},
{
"agentId": "backend_developer",
"match": { "text": { "contains": ["API", "database", "Node.js"] } }
},
{
"agentId": "qa_engineer",
"match": { "text": { "contains": ["test", "QA", "bug"] } }
}
]
}
Use this framework to evaluate and refine your multi-agent roles:
Professional multi-agent role design requires careful planning and continuous refinement. By defining clear roles with complementary skills and effective communication patterns, you can create robust, scalable multi-agent systems that drive innovation and efficiency.
The examples and frameworks provided here serve as a starting point for designing your own multi-agent systems. Remember to adapt these principles to your specific domain and requirements.
Generated Mar 1, 2026
A marketing agency uses Strategic Planner, Content Strategist, and Creative Director agents to design and execute campaigns. The Strategic Planner sets goals and budgets, the Content Strategist creates content calendars and copy, and the Creative Director ensures visual consistency and brand alignment.
A tech startup employs Technical Architect, Full-Stack Developer, and QA Engineer agents to build and test applications. The Technical Architect designs scalable architecture, the Full-Stack Developer implements front-end and back-end code, and the QA Engineer ensures quality through testing and bug reporting.
A consulting firm utilizes Process Optimization Specialist, Data Analyst, and Project Manager agents to improve client operations. The Process Optimization Specialist analyzes workflows, the Data Analyst identifies trends and insights, and the Project Manager coordinates implementation and tracks progress.
An e-commerce company deploys Customer Support Manager, Data Analyst, and Risk Manager agents to handle inquiries and mitigate issues. The Customer Support Manager manages operations and resolves complex cases, the Data Analyst analyzes support performance, and the Risk Manager identifies and addresses potential service risks.
A product design firm leverages UX Designer, Creative Director, and Strategic Planner agents to develop and launch new products. The UX Designer conducts user research and creates prototypes, the Creative Director defines brand identity, and the Strategic Planner sets market strategy and objectives.
Offer the multi-agent system as a cloud-based SaaS platform where businesses subscribe to access predefined agent roles and workflows. Revenue is generated through monthly or annual subscription fees based on the number of agents and features used.
Provide consulting and implementation services to tailor the multi-agent system for specific client needs, such as integrating with existing tools or developing custom roles. Revenue comes from project-based fees and ongoing support contracts.
Partner with marketing, consulting, or tech agencies to embed the multi-agent system into their service offerings, enabling them to deliver enhanced solutions to clients. Revenue is generated through licensing fees or revenue-sharing agreements with partners.
💬 Integration Tip
Start by integrating one or two core agent roles into existing workflows to test collaboration, then scale up based on performance and feedback.
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Search and analyze your own session logs (older/parent conversations) using jq.
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Vibe-coding ready.
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection