{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"github-othmaneblial--awesome-openclaw-examples","slug":"othmaneblial--awesome-openclaw-examples","name":"awesome-openclaw-examples","type":"repo","url":"https://othmaneblial.github.io/awesome-openclaw-examples","page_url":"https://unfragile.ai/othmaneblial--awesome-openclaw-examples","categories":["automation"],"tags":["ai-agents","ai-automation","awesome-list","clawhub","developer-tools","llm","openai","openclaw","openclaw-plugin","openclaw-skills","productivity","self-hosted","workflow-automation"],"pricing":{"model":"open_source","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"github-othmaneblial--awesome-openclaw-examples__cap_0","uri":"capability://planning.reasoning.real.world.openclaw.agent.example.curation.and.documentation","name":"real-world openclaw agent example curation and documentation","description":"Curates and documents 100+ tested, production-ready OpenClaw agent implementations across diverse use cases (automation, chatbots, workflows). Each example includes runnable scripts, prompt templates, performance KPIs, and sample outputs, enabling developers to understand agent patterns through concrete, executable reference implementations rather than abstract documentation.","intents":["I need to see how other developers have built OpenClaw agents for my specific use case","I want to understand best practices for structuring OpenClaw skills and workflows","I need working code examples I can adapt for my own agent implementation","I want to benchmark expected performance and outputs for similar agent tasks"],"best_for":["developers building their first OpenClaw agents","teams evaluating OpenClaw as an agent framework","engineers migrating from other agent frameworks to OpenClaw","builders prototyping multi-skill workflows"],"limitations":["Examples are static snapshots — may not reflect latest OpenClaw API changes","Limited to use cases covered in the 100 examples; niche workflows may lack reference implementations","No interactive playground or live execution environment; examples require local setup","Documentation quality and depth varies across examples depending on contributor effort"],"requires":["OpenClaw framework installed and configured","ClawHub account or self-hosted ClawHub instance for skill access","Python 3.8+ or Node.js 14+ depending on example language","API credentials for external services used in examples (OpenAI, etc.)"],"input_types":["example metadata (use case category, skill requirements)","prompt templates (text)","configuration files (YAML/JSON)"],"output_types":["executable agent scripts (Python/Shell)","sample agent outputs (text, structured data)","performance metrics and KPIs (JSON)","documentation and implementation guides (Markdown)"],"categories":["planning-reasoning","developer-tools"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-othmaneblial--awesome-openclaw-examples__cap_1","uri":"capability://tool.use.integration.clawhub.skill.discovery.and.integration.pattern.documentation","name":"clawhub skill discovery and integration pattern documentation","description":"Documents how to discover, select, and compose ClawHub skills within OpenClaw agents through 100+ examples that demonstrate skill chaining, parameter passing, and error handling patterns. Examples show concrete integration points between agent orchestration logic and skill execution, enabling developers to understand the skill-to-agent binding architecture.","intents":["I need to understand which ClawHub skills are available and how to use them in my agent","I want to see examples of skill composition — how to chain multiple skills together","I need to understand how to pass data between skills and handle skill failures","I want to learn the patterns for custom skill development within OpenClaw"],"best_for":["developers new to the ClawHub skill ecosystem","teams building multi-skill agents requiring complex orchestration","engineers extending OpenClaw with custom skills","builders evaluating skill coverage for their use case"],"limitations":["Examples may use deprecated or outdated ClawHub skills if not actively maintained","Skill availability varies by ClawHub instance; self-hosted instances may have different skill sets","No automated skill compatibility checking — developers must manually verify skill versions","Examples don't cover advanced skill composition patterns like conditional branching or dynamic skill selection"],"requires":["ClawHub instance (cloud or self-hosted) with skill registry access","OpenClaw agent framework configured with ClawHub connector","Understanding of skill schema and parameter types","API credentials for skills requiring external service authentication"],"input_types":["skill names and parameter schemas (structured metadata)","agent input data (text, structured objects)","skill configuration (JSON/YAML)"],"output_types":["skill execution results (varies by skill type)","agent output combining multiple skill results (text, structured data)","execution logs and error traces (text)"],"categories":["tool-use-integration","planning-reasoning"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-othmaneblial--awesome-openclaw-examples__cap_2","uri":"capability://text.generation.language.agent.prompt.engineering.and.template.library","name":"agent prompt engineering and template library","description":"Provides 100+ tested prompt templates and engineering patterns for OpenClaw agents, including system prompts, task decomposition patterns, few-shot examples, and output formatting instructions. Each example includes the actual prompts used, enabling developers to understand how to structure agent instructions for different task types and skill combinations.","intents":["I need effective system prompts for my OpenClaw agent","I want to see how to structure prompts for multi-step task decomposition","I need examples of few-shot prompting for specific agent behaviors","I want to understand how to guide agents to use specific skills effectively"],"best_for":["prompt engineers optimizing agent behavior","developers new to agent-based LLM applications","teams building domain-specific agents","builders fine-tuning agent outputs for specific formats or constraints"],"limitations":["Prompts are optimized for specific LLM models (likely GPT-4/3.5); effectiveness varies with different model backends","Prompt engineering is empirical — examples may not transfer directly to different domains or skill sets","No automated prompt optimization or A/B testing framework included","Limited guidance on prompt versioning and iteration strategies"],"requires":["OpenClaw agent framework","LLM API access (OpenAI or compatible provider)","Understanding of prompt engineering fundamentals","Familiarity with the specific skills being used in examples"],"input_types":["task descriptions (text)","skill definitions and capabilities (structured metadata)","example inputs and desired outputs (text, structured data)"],"output_types":["system prompts (text)","task decomposition instructions (text)","output formatting templates (text, JSON schema)","few-shot examples (text)"],"categories":["text-generation-language","planning-reasoning"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-othmaneblial--awesome-openclaw-examples__cap_3","uri":"capability://automation.workflow.agent.workflow.automation.use.case.library","name":"agent workflow automation use case library","description":"Catalogs 100+ real-world automation workflows implemented with OpenClaw agents, spanning domains like customer service, content generation, data processing, and business process automation. Each use case includes the complete workflow definition, skill composition, and performance metrics, enabling developers to understand how agents solve specific business problems.","intents":["I need to understand what types of workflows OpenClaw agents can automate","I want to see how other teams have solved similar business problems with agents","I need to estimate performance and cost for automating my specific workflow","I want to understand the skill and infrastructure requirements for my use case"],"best_for":["business teams evaluating agent automation for their workflows","developers building agents for specific industries or domains","teams migrating from traditional automation tools to agent-based approaches","builders estimating ROI and resource requirements for agent projects"],"limitations":["Use cases are domain-specific; applicability to different industries varies","Performance metrics may not reflect real-world conditions in different environments or at different scales","Examples assume specific skill availability; custom skill development may be required for some workflows","No guidance on change management or organizational adoption of agent-based workflows"],"requires":["OpenClaw framework and ClawHub skills matching the use case","Understanding of the specific business domain and workflow","Infrastructure to run agents (cloud or self-hosted)","API credentials for external services integrated in the workflow"],"input_types":["workflow input data (varies by use case: text, structured data, files)","workflow configuration (YAML/JSON)","skill parameters and settings (structured data)"],"output_types":["workflow results (varies by use case: text, structured data, files)","execution logs and audit trails (text, JSON)","performance metrics and KPIs (JSON, CSV)","cost and resource utilization reports (structured data)"],"categories":["automation-workflow","planning-reasoning"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-othmaneblial--awesome-openclaw-examples__cap_4","uri":"capability://data.processing.analysis.agent.performance.benchmarking.and.kpi.tracking","name":"agent performance benchmarking and kpi tracking","description":"Includes performance metrics, KPIs, and benchmarking data for 100+ agent implementations, documenting execution time, cost per task, success rates, and skill utilization patterns. Enables developers to understand performance characteristics of different agent architectures and skill compositions, supporting capacity planning and optimization decisions.","intents":["I need to understand the performance characteristics of OpenClaw agents for my use case","I want to benchmark my agent's performance against similar implementations","I need to estimate costs and resource requirements for scaling my agent","I want to identify performance bottlenecks and optimization opportunities"],"best_for":["teams optimizing agent performance and cost","developers planning infrastructure for agent deployment","builders evaluating agent frameworks based on performance characteristics","engineers conducting capacity planning for agent systems"],"limitations":["Performance metrics are historical snapshots; actual performance varies with LLM model versions, skill implementations, and infrastructure","Benchmarks may not reflect performance under production load or with different data distributions","Limited guidance on performance optimization strategies or tuning parameters","Cost estimates depend on specific LLM pricing and skill implementations; may not reflect current pricing"],"requires":["OpenClaw framework with performance monitoring enabled","LLM API access with usage tracking","Infrastructure to run agents and collect metrics","Understanding of relevant KPIs for your use case"],"input_types":["agent execution logs (text, JSON)","LLM API usage data (structured data)","skill execution traces (structured data)","task input and output data (varies by use case)"],"output_types":["performance metrics (JSON, CSV)","KPI reports (text, structured data)","cost analysis and projections (structured data)","performance comparison charts and visualizations (data for charting)"],"categories":["data-processing-analysis","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-othmaneblial--awesome-openclaw-examples__cap_5","uri":"capability://automation.workflow.self.hosted.agent.deployment.and.configuration.examples","name":"self-hosted agent deployment and configuration examples","description":"Demonstrates self-hosted deployment patterns for OpenClaw agents, including containerization, infrastructure setup, skill registry configuration, and operational considerations. Examples show how to deploy agents on-premises or in private cloud environments, with documentation of configuration options, scaling strategies, and monitoring setup.","intents":["I need to deploy OpenClaw agents in my own infrastructure","I want to understand the operational requirements for running agents at scale","I need to configure a self-hosted ClawHub instance for my organization","I want to understand security and compliance considerations for agent deployment"],"best_for":["enterprises deploying agents in regulated environments","teams requiring on-premises or private cloud deployment","developers building self-hosted agent platforms","builders managing multi-tenant agent infrastructure"],"limitations":["Deployment examples may be specific to certain cloud providers or infrastructure platforms","Limited guidance on high-availability and disaster recovery configurations","No automated deployment or infrastructure-as-code templates provided","Operational monitoring and alerting setup is not comprehensively documented"],"requires":["Container runtime (Docker) or Kubernetes cluster","Infrastructure to host OpenClaw and ClawHub (cloud VM, on-premises server, or Kubernetes)","Database for agent state and skill registry (PostgreSQL or compatible)","Network configuration and security setup (firewalls, TLS, authentication)"],"input_types":["deployment configuration files (YAML, JSON)","infrastructure specifications (CPU, memory, storage requirements)","skill registry configuration (structured data)","security and compliance requirements (text, structured data)"],"output_types":["deployment scripts and configurations (Shell, YAML)","infrastructure documentation (Markdown, diagrams)","operational runbooks (text)","monitoring and alerting configurations (YAML, JSON)"],"categories":["automation-workflow","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-othmaneblial--awesome-openclaw-examples__cap_6","uri":"capability://planning.reasoning.multi.agent.coordination.and.workflow.orchestration.patterns","name":"multi-agent coordination and workflow orchestration patterns","description":"Documents patterns for coordinating multiple OpenClaw agents within larger workflows, including agent-to-agent communication, state sharing, task delegation, and result aggregation. Examples demonstrate how to structure complex automation scenarios where multiple agents work together, with patterns for synchronization, error handling, and result validation.","intents":["I need to coordinate multiple agents working on different parts of a workflow","I want to understand how to pass results between agents","I need patterns for handling failures and retries in multi-agent workflows","I want to see examples of agents delegating tasks to other agents"],"best_for":["teams building complex, multi-stage automation workflows","developers implementing agent hierarchies or specialized agent teams","builders creating agent-based business process automation","engineers designing fault-tolerant agent systems"],"limitations":["Multi-agent coordination adds complexity; examples may not cover all edge cases","State management between agents requires external persistence; no built-in solution provided","Limited guidance on deadlock prevention or circular dependency handling","Scalability of multi-agent patterns is not comprehensively documented"],"requires":["OpenClaw framework with multi-agent support","External state store or message queue for agent coordination (Redis, RabbitMQ, etc.)","Workflow orchestration layer (could be custom or third-party)","Monitoring and debugging tools for multi-agent workflows"],"input_types":["workflow definitions with agent tasks (YAML, JSON)","agent input data and task specifications (structured data)","state and context shared between agents (structured data)","error and retry policies (structured data)"],"output_types":["aggregated results from multiple agents (structured data)","workflow execution logs and traces (text, JSON)","state snapshots and checkpoints (structured data)","error reports and recovery actions (text, structured data)"],"categories":["planning-reasoning","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-othmaneblial--awesome-openclaw-examples__cap_7","uri":"capability://automation.workflow.agent.testing.and.validation.framework.examples","name":"agent testing and validation framework examples","description":"Demonstrates testing strategies for OpenClaw agents, including unit testing individual skills, integration testing skill compositions, and end-to-end testing of complete workflows. Examples show how to validate agent outputs, test error handling, and ensure deterministic behavior where needed, with patterns for test data generation and result validation.","intents":["I need to test my OpenClaw agent before deploying to production","I want to validate that my agent produces correct outputs for different inputs","I need to test error handling and recovery in my agent","I want to ensure my agent's behavior is consistent and predictable"],"best_for":["developers building production-grade agents","teams implementing CI/CD pipelines for agent code","builders ensuring quality and reliability of agent systems","engineers validating agent behavior across different configurations"],"limitations":["Testing LLM-based agents is inherently non-deterministic; examples may not cover all failure modes","No built-in test framework provided; examples use standard testing tools","Limited guidance on testing agents with external API dependencies","Performance testing and load testing patterns are not comprehensively documented"],"requires":["OpenClaw framework with test support","Testing framework (pytest, Jest, or similar)","Test data and fixtures for your specific use case","Mock implementations of external services for isolated testing"],"input_types":["test cases and scenarios (structured data, text)","test data and fixtures (varies by use case)","expected outputs and validation rules (structured data)","error scenarios and edge cases (text, structured data)"],"output_types":["test results and coverage reports (text, JSON)","validation reports (text, structured data)","error logs and failure analysis (text, JSON)","performance test results (structured data)"],"categories":["automation-workflow","code-generation-editing"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":35,"verified":false,"data_access_risk":"high","permissions":["OpenClaw framework installed and configured","ClawHub account or self-hosted ClawHub instance for skill access","Python 3.8+ or Node.js 14+ depending on example language","API credentials for external services used in examples (OpenAI, etc.)","ClawHub instance (cloud or self-hosted) with skill registry access","OpenClaw agent framework configured with ClawHub connector","Understanding of skill schema and parameter types","API credentials for skills requiring external service authentication","OpenClaw agent framework","LLM API access (OpenAI or compatible provider)"],"failure_modes":["Examples are static snapshots — may not reflect latest OpenClaw API changes","Limited to use cases covered in the 100 examples; niche workflows may lack reference implementations","No interactive playground or live execution environment; examples require local setup","Documentation quality and depth varies across examples depending on contributor effort","Examples may use deprecated or outdated ClawHub skills if not actively maintained","Skill availability varies by ClawHub instance; self-hosted instances may have different skill sets","No automated skill compatibility checking — developers must manually verify skill versions","Examples don't cover advanced skill composition patterns like conditional branching or dynamic skill selection","Prompts are optimized for specific LLM models (likely GPT-4/3.5); effectiveness varies with different model backends","Prompt engineering is empirical — examples may not transfer directly to different domains or skill sets","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.20934936232440401,"quality":0.41,"ecosystem":0.6000000000000001,"match_graph":0.25,"freshness":0.75,"weights":{"adoption":0.3,"quality":0.2,"ecosystem":0.15,"match_graph":0.3,"freshness":0.05}},"observed_outcomes":{"matches":0,"success_rate":0,"avg_confidence":0,"top_intents":[],"last_matched_at":null},"maintenance":{"status":"active","updated_at":"2026-05-24T12:16:22.063Z","last_scraped_at":"2026-05-03T13:59:57.743Z","last_commit":"2026-04-05T16:42:16Z"},"community":{"stars":110,"forks":17,"weekly_downloads":null,"model_downloads":null,"model_likes":null}},"distribution":{"claim_url":"https://unfragile.ai/submit?claim=othmaneblial--awesome-openclaw-examples","compare_url":"https://unfragile.ai/compare?artifact=othmaneblial--awesome-openclaw-examples"}},"signature":"Afa6OdOgiZrhLThi7pBQ1dd4SwmAV6mIcUg5SD495XmVeY6E/75zgQP890pgEY/YLGN55RgmxQ5IVuCnBUeCCQ==","signedAt":"2026-06-20T11:59:56.329Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/othmaneblial--awesome-openclaw-examples","artifact":"https://unfragile.ai/othmaneblial--awesome-openclaw-examples","verify":"https://unfragile.ai/api/v1/verify?slug=othmaneblial--awesome-openclaw-examples","publicKey":"https://unfragile.ai/api/v1/trust-passport-public-key","spec":"https://unfragile.ai/trust","schema":"https://unfragile.ai/schema.json","docs":"https://unfragile.ai/docs"}}