JSON-driven multi-agent development framework for intelligent CLI orchestration. Enables operations teams to automate workflows using Claude, Codex, or Qwen agents. Connects to existing CLI tools and workflows for streamlined development and execution.
git clone https://github.com/catlog22/Claude-Code-Workflow.gitWORKFLOW_GUIDE.md
[{"step":1,"action":"Define your workflow requirements","details":"Identify the CLI tools you need to orchestrate (e.g., docker, kubectl, git), the agents required for each step, and the conditions for success/failure. Use the prompt template to structure your requirements."},{"step":2,"action":"Generate the JSON workflow config","details":"Use the prompt template in your AI assistant (Claude/ChatGPT) to generate a complete JSON configuration. Replace [PLACEHOLDERS] with your specific parameters, tools, and agents. Validate the output structure matches your needs."},{"step":3,"action":"Test the workflow in a sandbox environment","details":"Run the workflow in a non-production environment using tools like Claude Code or a similar CLI agent framework. Start with dry-run modes or test commands to verify each agent's behavior before full execution."},{"step":4,"action":"Integrate with your CI/CD pipeline","details":"Embed the JSON workflow config in your CI/CD pipeline (e.g., GitHub Actions, GitLab CI, Jenkins). Configure triggers (e.g., on PR merge, schedule) and notifications (e.g., Slack, email) for workflow results."},{"step":5,"action":"Monitor and iterate","details":"Track workflow execution metrics (e.g., success rate, execution time) and agent performance. Use the report generator to log results and identify bottlenecks or failures. Refine agent prompts and tools based on feedback."}]
Quickly fix configuration issues using the lite workflow.
Conduct multi-perspective analysis on security vulnerabilities with collaborative CLI tools.
Implement test-driven development workflows for new features.
Automate the integration of payment gateways through structured planning.
No install command available. Check the GitHub repository for manual installation instructions.
git clone https://github.com/catlog22/Claude-Code-WorkflowCopy the install command above and run it in your terminal.
Launch Claude Code, Cursor, or your preferred AI coding agent.
Use the prompt template or examples below to test the skill.
Adapt the skill to your specific use case and workflow.
Design a multi-agent CLI automation workflow for [TASK]. Use the following agents: [AGENT_1] for [RESPONSIBILITY_1], [AGENT_2] for [RESPONSIBILITY_2], and [AGENT_3] for [RESPONSIBILITY_3]. The workflow should: 1) Validate input parameters, 2) Execute [COMMAND_1] via [TOOL_1], 3) Process output with [AGENT_2], 4) Trigger [COMMAND_2] via [TOOL_2] if [CONDITION] is met, 5) Generate a summary report. Output the workflow as a runnable JSON config for Claude Code or similar CLI agent frameworks.
```json
{
"workflow_name": "production_deployment_verification",
"agents": {
"input_validator": {
"role": "Validates deployment parameters against configuration",
"tools": ["validate_json_schema"],
"prompt": "Check that [DEPLOY_ENV] is one of ['staging', 'production'], [VERSION] follows semantic versioning, and [SERVICE_LIST] contains valid services. Return errors if any checks fail."
},
"deployment_executor": {
"role": "Executes deployment commands and monitors status",
"tools": ["docker_compose", "kubectl"],
"prompt": "Run 'docker-compose -f [COMPOSE_FILE] up -d --build' for [SERVICE_LIST]. Verify all containers are running with 'docker ps'. Return success/failure status."
},
"health_checker": {
"role": "Performs post-deployment health checks",
"tools": ["curl", "postman"],
"prompt": "Check [HEALTH_ENDPOINTS] for each service in [SERVICE_LIST]. Verify response times < 500ms and status codes 200. Return detailed report."
},
"report_generator": {
"role": "Generates summary report for stakeholders",
"tools": ["markdown"],
"prompt": "Compile results from all agents. Include deployment status, health check results, and any warnings/errors. Format as a markdown report with sections for each service."
}
},
"execution_plan": [
{
"step": 1,
"agent": "input_validator",
"input": {"DEPLOY_ENV": "production", "VERSION": "2.4.1", "SERVICE_LIST": ["api", "frontend", "worker"], "COMPOSE_FILE": "./docker-compose.prod.yml", "HEALTH_ENDPOINTS": {"api": "/health", "frontend": "/status", "worker": "/ready"}},
"output": "Validation passed. All parameters are valid."
},
{
"step": 2,
"agent": "deployment_executor",
"input": {"COMPOSE_FILE": "./docker-compose.prod.yml", "SERVICE_LIST": ["api", "frontend", "worker"]},
"output": "Successfully deployed services. All containers are running (api: 1/1, frontend: 1/1, worker: 2/2)."
},
{
"step": 3,
"agent": "health_checker",
"input": {"HEALTH_ENDPOINTS": {"api": "/health", "frontend": "/status", "worker": "/ready"}},
"output": {
"api": {"status": "healthy", "response_time": "245ms", "status_code": 200},
"frontend": {"status": "healthy", "response_time": "310ms", "status_code": 200},
"worker": {"status": "healthy", "response_time": "180ms", "status_code": 200}
}
},
{
"step": 4,
"agent": "report_generator",
"input": {"deployment_status": "success", "health_checks": {...}},
"output": "# Production Deployment Report - 2024-05-15\n\n## Summary\nAll services deployed successfully. Health checks passed for all endpoints.\n\n## Details\n- **Deployment Status**: Success\n- **Services Deployed**: api, frontend, worker\n- **Health Check Results**:\n - api: 245ms (200 OK)\n - frontend: 310ms (200 OK)\n - worker: 180ms (200 OK)\n\n## Recommendations\nNo action required. All systems operational."
}
]
}
```Automate your browser workflows effortlessly
Your one-stop shop for church and ministry supplies.
Create and collaborate on interactive animations with powerful, user-friendly tools.
Google's multimodal AI model and assistant
AI assistant built for thoughtful, nuanced conversation
Automate your spreadsheet tasks with AI power
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan