stream-chain

Stream outputs between steps in multi-agent workflows.

75|17|Updated Jan 11, 2026
One-click install
npx skills add https://github.com/smith-horn/skillsmith --skill stream-chain-smith-horn
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: stream-chain
Source: https://github.com/smith-horn/skillsmith/tree/main/.claude/skills/stream-chain
Command: npx skills add https://github.com/smith-horn/skillsmith --skill stream-chain-smith-horn

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Stream-Chain orchestrates multi-agent workflows by streaming outputs between steps, enabling coordinated, sequential processing across multiple prompts or tasks.

Core Features & Use Cases

  • Custom Chains (run): execute user-defined prompt sequences with full control, passing outputs from one step to the next.
  • Predefined Pipelines (pipeline): reuse battle-tested workflows for common development tasks.
  • Deterministic execution with streaming context: each step receives the complete prior results, enabling robust multi-agent coordination.
  • Use cases include research-to-deployment automation, debugging pipelines, and data transformation workflows.

Quick Start

claude-flow stream-chain run "Analyze requirements" "Design solution" "Generate implementation plan" claude-flow stream-chain pipeline analysis

Frequently Asked Questions about stream-chain

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

FAQPage Schema
How do I orchestrate multi-agent workflows with streaming outputs in Claude Code?

You orchestrate multi-agent workflows by streaming outputs between sequential steps, ensuring each step receives the complete prior results for deterministic execution and coordinated processing across development tasks.

What is the best way to chain sequential prompts for a research-to-deployment pipeline?

Chaining sequential prompts is best handled by executing user-defined custom chains that pass outputs from one step directly to the next, enabling robust multi-agent coordination for research-to-deployment automation.

Can I reuse predefined pipelines for common development tasks like debugging and data transformation?

Yes, predefined pipelines allow you to reuse battle-tested workflows for common development tasks, executing deterministic steps with streaming context for debugging pipelines and data transformation workflows.

Does multi-agent orchestration require external dependencies to execute deterministic prompt chains?

No external dependencies are required to execute deterministic prompt chains, as the orchestration mechanism handles stepwise context sharing and sequential processing natively within the Claude Code environment.

When should I use custom chains versus predefined pipelines for multi-agent workflow automation?

Use custom chains when you need full control over user-defined prompt sequences, and use predefined pipelines when you want to reuse established workflows for common development tasks with deterministic execution.