{ "schemaVersion": "1.0", "item": { "slug": "agent-designer", "name": "agent-designer", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/alirezarezvani/agent-designer", "canonicalUrl": "https://clawhub.ai/alirezarezvani/agent-designer", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/agent-designer", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agent-designer", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "README.md", "SKILL.md", "agent_evaluator.py", "agent_planner.py", "assets/sample_execution_logs.json", "assets/sample_system_requirements.json" ], "primaryDoc": "SKILL.md", "quickSetup": [ "Download the package from Yavira.", "Extract the archive and review SKILL.md first.", "Import or place the package into your OpenClaw setup." ], "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run." } ] }, "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-30T16:55:25.780Z", "expiresAt": "2026-05-07T16:55:25.780Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network", "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null }, "scope": "source", "summary": "Source download looks usable.", "detail": "Yavira can redirect you to the upstream package for this source.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/agent-designer" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] }, "downloadPageUrl": "https://openagent3.xyz/downloads/agent-designer", "agentPageUrl": "https://openagent3.xyz/skills/agent-designer/agent", "manifestUrl": "https://openagent3.xyz/skills/agent-designer/agent.json", "briefUrl": "https://openagent3.xyz/skills/agent-designer/agent.md" }, "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "Agent Designer - Multi-Agent System Architecture", "body": "Tier: POWERFUL\nCategory: Engineering\nTags: AI agents, architecture, system design, orchestration, multi-agent systems" }, { "title": "Overview", "body": "Agent Designer is a comprehensive toolkit for designing, architecting, and evaluating multi-agent systems. It provides structured approaches to agent architecture patterns, tool design principles, communication strategies, and performance evaluation frameworks for building robust, scalable AI agent systems." }, { "title": "1. Agent Architecture Patterns", "body": "Single Agent Pattern\n\nUse Case: Simple, focused tasks with clear boundaries\nPros: Minimal complexity, easy debugging, predictable behavior\nCons: Limited scalability, single point of failure\nImplementation: Direct user-agent interaction with comprehensive tool access\n\nSupervisor Pattern\n\nUse Case: Hierarchical task decomposition with centralized control\nArchitecture: One supervisor agent coordinating multiple specialist agents\nPros: Clear command structure, centralized decision making\nCons: Supervisor bottleneck, complex coordination logic\nImplementation: Supervisor receives tasks, delegates to specialists, aggregates results\n\nSwarm Pattern\n\nUse Case: Distributed problem solving with peer-to-peer collaboration\nArchitecture: Multiple autonomous agents with shared objectives\nPros: High parallelism, fault tolerance, emergent intelligence\nCons: Complex coordination, potential conflicts, harder to predict\nImplementation: Agent discovery, consensus mechanisms, distributed task allocation\n\nHierarchical Pattern\n\nUse Case: Complex systems with multiple organizational layers\nArchitecture: Tree structure with managers and workers at different levels\nPros: Natural organizational mapping, clear responsibilities\nCons: Communication overhead, potential bottlenecks at each level\nImplementation: Multi-level delegation with feedback loops\n\nPipeline Pattern\n\nUse Case: Sequential processing with specialized stages\nArchitecture: Agents arranged in processing pipeline\nPros: Clear data flow, specialized optimization per stage\nCons: Sequential bottlenecks, rigid processing order\nImplementation: Message queues between stages, state handoffs" }, { "title": "2. Agent Role Definition", "body": "Role Specification Framework\n\nIdentity: Name, purpose statement, core competencies\nResponsibilities: Primary tasks, decision boundaries, success criteria\nCapabilities: Required tools, knowledge domains, processing limits\nInterfaces: Input/output formats, communication protocols\nConstraints: Security boundaries, resource limits, operational guidelines\n\nCommon Agent Archetypes\n\nCoordinator Agent\n\nOrchestrates multi-agent workflows\nMakes high-level decisions and resource allocation\nMonitors system health and performance\nHandles escalations and conflict resolution\n\nSpecialist Agent\n\nDeep expertise in specific domain (code, data, research)\nOptimized tools and knowledge for specialized tasks\nHigh-quality output within narrow scope\nClear handoff protocols for out-of-scope requests\n\nInterface Agent\n\nHandles external interactions (users, APIs, systems)\nProtocol translation and format conversion\nAuthentication and authorization management\nUser experience optimization\n\nMonitor Agent\n\nSystem health monitoring and alerting\nPerformance metrics collection and analysis\nAnomaly detection and reporting\nCompliance and audit trail maintenance" }, { "title": "3. Tool Design Principles", "body": "Schema Design\n\nInput Validation: Strong typing, required vs optional parameters\nOutput Consistency: Standardized response formats, error handling\nDocumentation: Clear descriptions, usage examples, edge cases\nVersioning: Backward compatibility, migration paths\n\nError Handling Patterns\n\nGraceful Degradation: Partial functionality when dependencies fail\nRetry Logic: Exponential backoff, circuit breakers, max attempts\nError Propagation: Structured error responses, error classification\nRecovery Strategies: Fallback methods, alternative approaches\n\nIdempotency Requirements\n\nSafe Operations: Read operations with no side effects\nIdempotent Writes: Same operation can be safely repeated\nState Management: Version tracking, conflict resolution\nAtomicity: All-or-nothing operation completion" }, { "title": "4. Communication Patterns", "body": "Message Passing\n\nAsynchronous Messaging: Decoupled agents, message queues\nMessage Format: Structured payloads with metadata\nDelivery Guarantees: At-least-once, exactly-once semantics\nRouting: Direct messaging, publish-subscribe, broadcast\n\nShared State\n\nState Stores: Centralized data repositories\nConsistency Models: Strong, eventual, weak consistency\nAccess Patterns: Read-heavy, write-heavy, mixed workloads\nConflict Resolution: Last-writer-wins, merge strategies\n\nEvent-Driven Architecture\n\nEvent Sourcing: Immutable event logs, state reconstruction\nEvent Types: Domain events, system events, integration events\nEvent Processing: Real-time, batch, stream processing\nEvent Schema: Versioned event formats, backward compatibility" }, { "title": "5. Guardrails and Safety", "body": "Input Validation\n\nSchema Enforcement: Required fields, type checking, format validation\nContent Filtering: Harmful content detection, PII scrubbing\nRate Limiting: Request throttling, resource quotas\nAuthentication: Identity verification, authorization checks\n\nOutput Filtering\n\nContent Moderation: Harmful content removal, quality checks\nConsistency Validation: Logic checks, constraint verification\nFormatting: Standardized output formats, clean presentation\nAudit Logging: Decision trails, compliance records\n\nHuman-in-the-Loop\n\nApproval Workflows: Critical decision checkpoints\nEscalation Triggers: Confidence thresholds, risk assessment\nOverride Mechanisms: Human judgment precedence\nFeedback Loops: Human corrections improve system behavior" }, { "title": "6. Evaluation Frameworks", "body": "Task Completion Metrics\n\nSuccess Rate: Percentage of tasks completed successfully\nPartial Completion: Progress measurement for complex tasks\nTask Classification: Success criteria by task type\nFailure Analysis: Root cause identification and categorization\n\nQuality Assessment\n\nOutput Quality: Accuracy, relevance, completeness measures\nConsistency: Response variability across similar inputs\nCoherence: Logical flow and internal consistency\nUser Satisfaction: Feedback scores, usage patterns\n\nCost Analysis\n\nToken Usage: Input/output token consumption per task\nAPI Costs: External service usage and charges\nCompute Resources: CPU, memory, storage utilization\nTime-to-Value: Cost per successful task completion\n\nLatency Distribution\n\nResponse Time: End-to-end task completion time\nProcessing Stages: Bottleneck identification per stage\nQueue Times: Wait times in processing pipelines\nResource Contention: Impact of concurrent operations" }, { "title": "7. Orchestration Strategies", "body": "Centralized Orchestration\n\nWorkflow Engine: Central coordinator manages all agents\nState Management: Centralized workflow state tracking\nDecision Logic: Complex routing and branching rules\nMonitoring: Comprehensive visibility into all operations\n\nDecentralized Orchestration\n\nPeer-to-Peer: Agents coordinate directly with each other\nService Discovery: Dynamic agent registration and lookup\nConsensus Protocols: Distributed decision making\nFault Tolerance: No single point of failure\n\nHybrid Approaches\n\nDomain Boundaries: Centralized within domains, federated across\nHierarchical Coordination: Multiple orchestration levels\nContext-Dependent: Strategy selection based on task type\nLoad Balancing: Distribute coordination responsibility" }, { "title": "8. Memory Patterns", "body": "Short-Term Memory\n\nContext Windows: Working memory for current tasks\nSession State: Temporary data for ongoing interactions\nCache Management: Performance optimization strategies\nMemory Pressure: Handling capacity constraints\n\nLong-Term Memory\n\nPersistent Storage: Durable data across sessions\nKnowledge Base: Accumulated domain knowledge\nExperience Replay: Learning from past interactions\nMemory Consolidation: Transferring from short to long-term\n\nShared Memory\n\nCollaborative Knowledge: Shared learning across agents\nSynchronization: Consistency maintenance strategies\nAccess Control: Permission-based memory access\nMemory Partitioning: Isolation between agent groups" }, { "title": "9. Scaling Considerations", "body": "Horizontal Scaling\n\nAgent Replication: Multiple instances of same agent type\nLoad Distribution: Request routing across agent instances\nResource Pooling: Shared compute and storage resources\nGeographic Distribution: Multi-region deployments\n\nVertical Scaling\n\nCapability Enhancement: More powerful individual agents\nTool Expansion: Broader tool access per agent\nContext Expansion: Larger working memory capacity\nProcessing Power: Higher throughput per agent\n\nPerformance Optimization\n\nCaching Strategies: Response caching, tool result caching\nParallel Processing: Concurrent task execution\nResource Optimization: Efficient resource utilization\nBottleneck Elimination: Systematic performance tuning" }, { "title": "10. Failure Handling", "body": "Retry Mechanisms\n\nExponential Backoff: Increasing delays between retries\nJitter: Random delay variation to prevent thundering herd\nMaximum Attempts: Bounded retry behavior\nRetry Conditions: Transient vs permanent failure classification\n\nFallback Strategies\n\nGraceful Degradation: Reduced functionality when systems fail\nAlternative Approaches: Different methods for same goals\nDefault Responses: Safe fallback behaviors\nUser Communication: Clear failure messaging\n\nCircuit Breakers\n\nFailure Detection: Monitoring failure rates and response times\nState Management: Open, closed, half-open circuit states\nRecovery Testing: Gradual return to normal operation\nCascading Failure Prevention: Protecting upstream systems" }, { "title": "Architecture Decision Process", "body": "Requirements Analysis: Understand system goals, constraints, scale\nPattern Selection: Choose appropriate architecture pattern\nAgent Design: Define roles, responsibilities, interfaces\nTool Architecture: Design tool schemas and error handling\nCommunication Design: Select message patterns and protocols\nSafety Implementation: Build guardrails and validation\nEvaluation Planning: Define success metrics and monitoring\nDeployment Strategy: Plan scaling and failure handling" }, { "title": "Quality Assurance", "body": "Testing Strategy: Unit, integration, and system testing approaches\nMonitoring: Real-time system health and performance tracking\nDocumentation: Architecture documentation and runbooks\nSecurity Review: Threat modeling and security assessments" }, { "title": "Continuous Improvement", "body": "Performance Monitoring: Ongoing system performance analysis\nUser Feedback: Incorporating user experience improvements\nA/B Testing: Controlled experiments for system improvements\nKnowledge Base Updates: Continuous learning and adaptation\n\nThis skill provides the foundation for designing robust, scalable multi-agent systems that can handle complex tasks while maintaining safety, reliability, and performance at scale." } ], "body": "Agent Designer - Multi-Agent System Architecture\n\nTier: POWERFUL\nCategory: Engineering\nTags: AI agents, architecture, system design, orchestration, multi-agent systems\n\nOverview\n\nAgent Designer is a comprehensive toolkit for designing, architecting, and evaluating multi-agent systems. It provides structured approaches to agent architecture patterns, tool design principles, communication strategies, and performance evaluation frameworks for building robust, scalable AI agent systems.\n\nCore Capabilities\n1. Agent Architecture Patterns\nSingle Agent Pattern\nUse Case: Simple, focused tasks with clear boundaries\nPros: Minimal complexity, easy debugging, predictable behavior\nCons: Limited scalability, single point of failure\nImplementation: Direct user-agent interaction with comprehensive tool access\nSupervisor Pattern\nUse Case: Hierarchical task decomposition with centralized control\nArchitecture: One supervisor agent coordinating multiple specialist agents\nPros: Clear command structure, centralized decision making\nCons: Supervisor bottleneck, complex coordination logic\nImplementation: Supervisor receives tasks, delegates to specialists, aggregates results\nSwarm Pattern\nUse Case: Distributed problem solving with peer-to-peer collaboration\nArchitecture: Multiple autonomous agents with shared objectives\nPros: High parallelism, fault tolerance, emergent intelligence\nCons: Complex coordination, potential conflicts, harder to predict\nImplementation: Agent discovery, consensus mechanisms, distributed task allocation\nHierarchical Pattern\nUse Case: Complex systems with multiple organizational layers\nArchitecture: Tree structure with managers and workers at different levels\nPros: Natural organizational mapping, clear responsibilities\nCons: Communication overhead, potential bottlenecks at each level\nImplementation: Multi-level delegation with feedback loops\nPipeline Pattern\nUse Case: Sequential processing with specialized stages\nArchitecture: Agents arranged in processing pipeline\nPros: Clear data flow, specialized optimization per stage\nCons: Sequential bottlenecks, rigid processing order\nImplementation: Message queues between stages, state handoffs\n2. Agent Role Definition\nRole Specification Framework\nIdentity: Name, purpose statement, core competencies\nResponsibilities: Primary tasks, decision boundaries, success criteria\nCapabilities: Required tools, knowledge domains, processing limits\nInterfaces: Input/output formats, communication protocols\nConstraints: Security boundaries, resource limits, operational guidelines\nCommon Agent Archetypes\n\nCoordinator Agent\n\nOrchestrates multi-agent workflows\nMakes high-level decisions and resource allocation\nMonitors system health and performance\nHandles escalations and conflict resolution\n\nSpecialist Agent\n\nDeep expertise in specific domain (code, data, research)\nOptimized tools and knowledge for specialized tasks\nHigh-quality output within narrow scope\nClear handoff protocols for out-of-scope requests\n\nInterface Agent\n\nHandles external interactions (users, APIs, systems)\nProtocol translation and format conversion\nAuthentication and authorization management\nUser experience optimization\n\nMonitor Agent\n\nSystem health monitoring and alerting\nPerformance metrics collection and analysis\nAnomaly detection and reporting\nCompliance and audit trail maintenance\n3. Tool Design Principles\nSchema Design\nInput Validation: Strong typing, required vs optional parameters\nOutput Consistency: Standardized response formats, error handling\nDocumentation: Clear descriptions, usage examples, edge cases\nVersioning: Backward compatibility, migration paths\nError Handling Patterns\nGraceful Degradation: Partial functionality when dependencies fail\nRetry Logic: Exponential backoff, circuit breakers, max attempts\nError Propagation: Structured error responses, error classification\nRecovery Strategies: Fallback methods, alternative approaches\nIdempotency Requirements\nSafe Operations: Read operations with no side effects\nIdempotent Writes: Same operation can be safely repeated\nState Management: Version tracking, conflict resolution\nAtomicity: All-or-nothing operation completion\n4. Communication Patterns\nMessage Passing\nAsynchronous Messaging: Decoupled agents, message queues\nMessage Format: Structured payloads with metadata\nDelivery Guarantees: At-least-once, exactly-once semantics\nRouting: Direct messaging, publish-subscribe, broadcast\nShared State\nState Stores: Centralized data repositories\nConsistency Models: Strong, eventual, weak consistency\nAccess Patterns: Read-heavy, write-heavy, mixed workloads\nConflict Resolution: Last-writer-wins, merge strategies\nEvent-Driven Architecture\nEvent Sourcing: Immutable event logs, state reconstruction\nEvent Types: Domain events, system events, integration events\nEvent Processing: Real-time, batch, stream processing\nEvent Schema: Versioned event formats, backward compatibility\n5. Guardrails and Safety\nInput Validation\nSchema Enforcement: Required fields, type checking, format validation\nContent Filtering: Harmful content detection, PII scrubbing\nRate Limiting: Request throttling, resource quotas\nAuthentication: Identity verification, authorization checks\nOutput Filtering\nContent Moderation: Harmful content removal, quality checks\nConsistency Validation: Logic checks, constraint verification\nFormatting: Standardized output formats, clean presentation\nAudit Logging: Decision trails, compliance records\nHuman-in-the-Loop\nApproval Workflows: Critical decision checkpoints\nEscalation Triggers: Confidence thresholds, risk assessment\nOverride Mechanisms: Human judgment precedence\nFeedback Loops: Human corrections improve system behavior\n6. Evaluation Frameworks\nTask Completion Metrics\nSuccess Rate: Percentage of tasks completed successfully\nPartial Completion: Progress measurement for complex tasks\nTask Classification: Success criteria by task type\nFailure Analysis: Root cause identification and categorization\nQuality Assessment\nOutput Quality: Accuracy, relevance, completeness measures\nConsistency: Response variability across similar inputs\nCoherence: Logical flow and internal consistency\nUser Satisfaction: Feedback scores, usage patterns\nCost Analysis\nToken Usage: Input/output token consumption per task\nAPI Costs: External service usage and charges\nCompute Resources: CPU, memory, storage utilization\nTime-to-Value: Cost per successful task completion\nLatency Distribution\nResponse Time: End-to-end task completion time\nProcessing Stages: Bottleneck identification per stage\nQueue Times: Wait times in processing pipelines\nResource Contention: Impact of concurrent operations\n7. Orchestration Strategies\nCentralized Orchestration\nWorkflow Engine: Central coordinator manages all agents\nState Management: Centralized workflow state tracking\nDecision Logic: Complex routing and branching rules\nMonitoring: Comprehensive visibility into all operations\nDecentralized Orchestration\nPeer-to-Peer: Agents coordinate directly with each other\nService Discovery: Dynamic agent registration and lookup\nConsensus Protocols: Distributed decision making\nFault Tolerance: No single point of failure\nHybrid Approaches\nDomain Boundaries: Centralized within domains, federated across\nHierarchical Coordination: Multiple orchestration levels\nContext-Dependent: Strategy selection based on task type\nLoad Balancing: Distribute coordination responsibility\n8. Memory Patterns\nShort-Term Memory\nContext Windows: Working memory for current tasks\nSession State: Temporary data for ongoing interactions\nCache Management: Performance optimization strategies\nMemory Pressure: Handling capacity constraints\nLong-Term Memory\nPersistent Storage: Durable data across sessions\nKnowledge Base: Accumulated domain knowledge\nExperience Replay: Learning from past interactions\nMemory Consolidation: Transferring from short to long-term\nShared Memory\nCollaborative Knowledge: Shared learning across agents\nSynchronization: Consistency maintenance strategies\nAccess Control: Permission-based memory access\nMemory Partitioning: Isolation between agent groups\n9. Scaling Considerations\nHorizontal Scaling\nAgent Replication: Multiple instances of same agent type\nLoad Distribution: Request routing across agent instances\nResource Pooling: Shared compute and storage resources\nGeographic Distribution: Multi-region deployments\nVertical Scaling\nCapability Enhancement: More powerful individual agents\nTool Expansion: Broader tool access per agent\nContext Expansion: Larger working memory capacity\nProcessing Power: Higher throughput per agent\nPerformance Optimization\nCaching Strategies: Response caching, tool result caching\nParallel Processing: Concurrent task execution\nResource Optimization: Efficient resource utilization\nBottleneck Elimination: Systematic performance tuning\n10. Failure Handling\nRetry Mechanisms\nExponential Backoff: Increasing delays between retries\nJitter: Random delay variation to prevent thundering herd\nMaximum Attempts: Bounded retry behavior\nRetry Conditions: Transient vs permanent failure classification\nFallback Strategies\nGraceful Degradation: Reduced functionality when systems fail\nAlternative Approaches: Different methods for same goals\nDefault Responses: Safe fallback behaviors\nUser Communication: Clear failure messaging\nCircuit Breakers\nFailure Detection: Monitoring failure rates and response times\nState Management: Open, closed, half-open circuit states\nRecovery Testing: Gradual return to normal operation\nCascading Failure Prevention: Protecting upstream systems\nImplementation Guidelines\nArchitecture Decision Process\nRequirements Analysis: Understand system goals, constraints, scale\nPattern Selection: Choose appropriate architecture pattern\nAgent Design: Define roles, responsibilities, interfaces\nTool Architecture: Design tool schemas and error handling\nCommunication Design: Select message patterns and protocols\nSafety Implementation: Build guardrails and validation\nEvaluation Planning: Define success metrics and monitoring\nDeployment Strategy: Plan scaling and failure handling\nQuality Assurance\nTesting Strategy: Unit, integration, and system testing approaches\nMonitoring: Real-time system health and performance tracking\nDocumentation: Architecture documentation and runbooks\nSecurity Review: Threat modeling and security assessments\nContinuous Improvement\nPerformance Monitoring: Ongoing system performance analysis\nUser Feedback: Incorporating user experience improvements\nA/B Testing: Controlled experiments for system improvements\nKnowledge Base Updates: Continuous learning and adaptation\n\nThis skill provides the foundation for designing robust, scalable multi-agent systems that can handle complex tasks while maintaining safety, reliability, and performance at scale." }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/alirezarezvani/agent-designer", "publisherUrl": "https://clawhub.ai/alirezarezvani/agent-designer", "owner": "alirezarezvani", "version": "2.1.1", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/agent-designer", "downloadUrl": "https://openagent3.xyz/downloads/agent-designer", "agentUrl": "https://openagent3.xyz/skills/agent-designer/agent", "manifestUrl": "https://openagent3.xyz/skills/agent-designer/agent.json", "briefUrl": "https://openagent3.xyz/skills/agent-designer/agent.md" } }