Stream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows

Stream Chain Skill Execute sophisticated multi step workflows where each agent's output flows into the next, enabling complex data transformations and sequential processing pipelines. Overview Stream Chain provides two powerful modes for orchestrating multi agent workflows: 1. Custom Chains ( run ): Execute custom prompt sequences with full control 2. Predefined Pipelines ( pipeline ): Use battle tested workflows for common tasks Each step in a chain receives the complete output from the previous step, enabling sophisticated multi agent coordination through streaming data flow. Quick Start Run a Custom Chain Execute a Pipeline Custom Chains ( run ) Execute custom stream chains with your own prompts for maximum flexibility. Syntax Requirements: Minimum 2 prompts required Each prompt becomes a step in the chain Output flows sequentially through all steps Options Option Description Default verbose Show detailed execution information false timeout <seconds Timeout per step 30 debug Enable debug mode with full logging false How Context Flows Each step receives the previous output as context: Examples Basic Development Chain Security Audit Workflow Code Refactoring Chain Data Processing Pipeline Predefined Pipelines ( pipeline ) Execute battle tested workflows optimized for common development tasks. Syntax Available Pipelines 1. Analysis Pipeline Comprehensive codebase analysis and improvement identification. Workflow Steps: 1. Structure Analysis : Map directory structure and identify components 2. Issue Detection : Find potential improvements and problems 3. Recommendations : Generate actionable improvement report Use Cases: New codebase onboarding Technical debt assessment Architecture review Code quality audits 2. Refactor Pipeline Systematic code refactoring with prioritization. Workflow Steps: 1. Candidate Identification : Find code needing refactoring 2. Prioritization : Create ranked refactoring plan 3. Implementation : Provide refactored code for top priorities Use Cases: Technical debt reduction Code quality improvement Legacy code modernization Design pattern implementation 3. Test Pipeline Comprehensive test generation with coverage analysis. Workflow Steps: 1. Coverage Analysis : Identify areas lacking tests 2. Test Design : Create test cases for critical functions 3. Implementation : Generate unit tests with assertions Use Cases: Increasing test coverage TDD workflow support Regression test creation Quality assurance 4. Optimize Pipeline Performance optimization with profiling and implementation. Workflow Steps: 1. Profiling : Identify performance bottlenecks 2. Strategy : Analyze and suggest optimization approaches 3. Implementation : Provide optimized code Use Cases: Performance improvement Resource optimization Scalability enhancement Latency reduction Pipeline Options Option Description Default verbose Show detailed execution false timeout <seconds Timeout per step 30 debug Enable debug mode false Pipeline Examples Quick Analysis Extended Refactoring Debug Test Generation Comprehensive Optimization Pipeline Output Each pipeline execution provides: Progress : Step by step execution status Results : Success/failure per step Timing : Total and per step execution time Summary : Consolidated results and recommendations Custom Pipeline Definitions Define reusable pipelines in .claude flow/config.json : Configuration Format Execute Custom Pipeline Advanced Use Cases Multi Agent Coordination Chain different agent types for complex workflows: Data Transformation Pipeline Process and transform data through multiple stages: Code Migration Workflow Systematic code migration with validation: Quality Assurance Chain Comprehensive code quality workflow: Best Practices 1. Clear and Specific Prompts Good: Avoid: 2. Logical Progression Order prompts to build on previous outputs: 3. Appropriate Timeouts Simple tasks: 30 seconds (default) Analysis tasks: 45 60 seconds Implementation tasks: 60 90 seconds Complex workflows: 90 120 seconds 4. Verification Steps Include validation in your chains: 5. Iterative Refinement Use chains for iterative improvement: Integration with Claude Flow Combine with Swarm Coordination Memory Integration Stream chains automatically store context in memory for cross session persistence: Neural Pattern Training Successful chains train neural patterns for improved performance: Troubleshooting Chain Timeout If steps timeout, increase timeout value: Context Loss If context not flowing properly, use debug : Pipeline Not Found Verify pipeline name and custom definitions: Performance Characteristics Throughput : 2 5 steps per minute (varies by complexity) Context Size : Up to 100K tokens per step Memory Usage : ~50MB per active chain Concurrency : Supports parallel chain execution Related Skills SPARC Methodology : Systematic development workflow Swarm Coordination : Multi agent orchestration Memory Management : Persistent context storage Neural Patterns : Adaptive learning Examples Repository Complete Development Workflow Code Review Pipeline Migration Assistant Conclusion Stream Chain enables sophisticated multi step workflows by: Sequential Processing : Each step builds on previous results Context Preservation : Full output history flows through chain Flexible Orchestration : Custom chains or predefined pipelines Agent Coordination : Natural multi agent collaboration pattern Data Transformation : Complex processing through simple steps Use run for custom workflows and pipeline for battle tested solutions.

stream-chain