stream-chain

Coordinate multi-agent pipelines with sequential prompts and streaming data flow.

436|78|Updated Sep 11, 2025

Search Tags:#workflow #multi-agent #streaming #orchestration #data transformation #pipeline #chaining

Ready to run

npx skills add https://github.com/proffesor-for-testing/agentic-qe --skill stream-chain-proffesor-for-testing

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: stream-chain
Source: https://github.com/proffesor-for-testing/agentic-qe/tree/main/.claude/skills/stream-chain
Command: npx skills add https://github.com/proffesor-for-testing/agentic-qe --skill stream-chain-proffesor-for-testing

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires claude-flow.

What problem does it solve?

This Skill orchestrates multi-step workflows where the output of one AI agent seamlessly becomes the input for the next, enabling complex data transformations and sequential processing pipelines that are difficult for single agents.

Core Features & Use Cases

Custom Chains: Execute user-defined sequences of prompts for maximum flexibility in multi-agent coordination.
Predefined Pipelines: Leverage battle-tested workflows (e.g., Analysis, Refactor, Test, Optimize) for common development tasks.
Context Flow: Ensures complete output from each step is passed as context to the next, maintaining continuity and enabling sophisticated transformations.
Use Case: Run a custom chain to "Write a sorting function," then "Add comprehensive tests," and finally "Optimize performance," with each step building on the previous one.

Quick Start

Use the stream-chain skill to run a custom chain that first "Analyzes codebase structure," then "Identifies improvement areas," and finally "Generates an action plan."

Frequently Asked Questions about stream-chain

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

FAQPage Schema

How do I chain multiple AI agents together for sequential workflows?▼

Stream-Chain orchestrates multi-agent pipelines by passing each agent's output as input to the next, enabling complex sequential workflows. Define custom chains or use predefined pipelines (Analysis, Refactor, Test, Optimize) where context flows continuously between steps, maintaining continuity across transformations like code analysis, refactoring, and test generation.

Can I use streaming data flow with multi-step AI prompts?▼

Yes. Stream-Chain supports streaming data flow across sequential prompts, allowing you to coordinate multi-agent pipelines where streaming context propagates from one step to the next. This enables sophisticated data transformations and complex processing pipelines difficult for single agents to handle.

What's the best way to automate code analysis, refactoring, and testing in sequence?▼

Use Stream-Chain's predefined pipelines or custom chains to run sequential tasks: analyze codebase structure, identify improvements, generate tests, and optimize performance. Each step builds on the previous output with full context propagation, structured progress tracking, timing data, and a final summary.

Does stream-chain work with claude-flow for orchestration?▼

Stream-Chain depends on claude-flow as its orchestration foundation, leveraging it to coordinate multi-agent execution, enforce per-step context propagation, and support configurable execution controls like verbose mode, timeouts, and debug settings.

How do I control execution behavior like timeouts and debugging in multi-agent workflows?▼

Stream-Chain provides configurable execution controls including verbose output, timeout settings, and debug mode. These settings apply across your custom chains or predefined pipelines, giving you visibility into each step and control over execution flow, timing, and error handling.

When should I use custom chains versus predefined pipelines?▼

Use predefined pipelines (Analysis, Refactor, Test, Optimize) for standard development tasks with proven workflows. Use custom chains for maximum flexibility when your sequential processing needs don't fit standard patterns or require specialized task combinations.