stream-chain

Stream outputs between multi-agent pipeline steps with custom chains and predefined pipelines.

Updated Aug 23, 2026

Search Tags:#workflow #multi-agent #streaming #pipeline #chaining

Ready to run

npx skills add https://github.com/wedosoft/project-a --skill stream-chain-wedosoft

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: stream-chain
Source: https://github.com/wedosoft/project-a/tree/main/.claude/skills/stream-chain
Command: npx skills add https://github.com/wedosoft/project-a --skill stream-chain-wedosoft

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Stream-Chain enables deterministic, multi-step workflows where each agent's output becomes the context for the next step, enabling complex data transformations with streaming coordination.

Core Features & Use Cases

Custom Chains: Define prompt sequences with full control using run.
Predefined Pipelines: Use battle-tested workflows via pipeline.
Full-context Propagation: Each step receives complete history from previous step.
Real-world Scenarios: Code analysis, security audits, refactoring, data pipelines.

Quick Start

Run a basic custom chain: claude-flow stream-chain run "Analyze code" "Propose improvements" "Implement".

Frequently Asked Questions about stream-chain

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

FAQPage Schema

How do I coordinate multi-step pipelines with streaming data flow between agents?▼

Stream-Chain coordinates multi-agent pipelines by streaming outputs from one step to the next, enabling each agent's output to become context for the following step. Use `run` for custom chains or `pipeline` for predefined workflows across code analysis, security audits, testing, and refactoring tasks.

What's the difference between custom chains and predefined pipelines in workflow automation?▼

Custom chains let you define prompt sequences with full control via `run`, while predefined pipelines provide battle-tested workflows via `pipeline`. Both propagate full context history through each step, but custom chains offer flexibility and pipelines offer proven patterns for common workflows.

Can I use streaming data flow for code analysis and security audits?▼

Yes, Stream-Chain applies to code analysis, security audits, testing, and refactoring by chaining multi-agent steps where each agent processes the previous step's output. This enables complex data transformations with deterministic, sequential processing across your security and analysis workflows.

How do I track execution progress and timing across multi-step workflows?▼

Stream-Chain provides comprehensive execution metadata including progress tracking, timing information, and results for each step. Configure verbose mode, timeout settings, and debug options to monitor and control your pipeline execution in real time.

What are the prerequisites for setting up a multi-agent streaming pipeline?▼

Stream-Chain requires prompt-based step definitions and supports configurable options like verbose logging, timeout limits, and debug mode. No external dependencies are needed; you define your workflow steps and the Skill handles streaming coordination and metadata collection.