stream-chain

Stream outputs between agents to coordinate multi-step workflows.

2|1|Updated Jul 24, 2025
One-click install
npx skills add https://github.com/breddin/claude-flow-baseline --skill stream-chain-breddin
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: stream-chain
Source: https://github.com/breddin/claude-flow-baseline/tree/main/.claude/skills/stream-chain
Command: npx skills add https://github.com/breddin/claude-flow-baseline --skill stream-chain-breddin

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solves? This Skill simplifies complex multi-step workflows by allowing each AI agent's output to seamlessly flow as input to the next, eliminating manual handoffs and ensuring context preservation across sequential processing pipelines.

Core Features & Use Cases

  • Custom Chains: Define and execute custom sequences of prompts for maximum flexibility in multi-agent workflows.
  • Predefined Pipelines: Utilize battle-tested workflows optimized for common tasks like analysis, refactoring, testing, and optimization.
  • Context Preservation: Ensures the complete output history from previous steps flows through the chain, maintaining continuity and depth across all stages.
  • Use Case: Automate a code refactoring process: first, identify code smells; second, create a refactoring plan; third, apply refactoring to top priorities; and finally, verify the refactored code maintains its behavior.

Quick Start

Run a custom chain for basic development

claude-flow stream-chain run
"Write a user authentication function"
"Add input validation and error handling"
"Create unit tests with edge cases"

Frequently Asked Questions about stream-chain

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate multi-step workflows with AI agents?

Multi-step workflow automation chains AI agent outputs sequentially, with each step's result flowing as input to the next. stream-chain coordinates this by preserving full context across steps, eliminating manual handoffs and ensuring continuity in data transformation and processing pipelines.

Can I run predefined workflows for code analysis and refactoring?

Yes, stream-chain includes predefined pipelines optimized for analysis, refactoring, testing, and optimization. These battle-tested workflows automate common multi-agent tasks without requiring manual chain definition.

How do I define custom sequences of prompts for my pipeline?

Use the run mode to define custom chains by passing prompts as sequential arguments. Each prompt receives the complete output history from previous steps, enabling flexible multi-agent workflows tailored to your specific task requirements.

What happens to context when streaming between agents in a chain?

Context preservation ensures the complete output from each step flows through the entire chain. This maintains continuity and depth across all sequential processing stages, so downstream agents have full visibility into previous work.

Does stream-chain support debugging and monitoring pipeline execution?

Yes, CLI options include --verbose for detailed output tracking, --debug for troubleshooting, and --timeout for execution control. These enable visibility and control over multi-agent pipeline behavior during development and production runs.