stream-chain

Orchestrate multi-agent workflows with sequential step outputs and configurable execution controls.

5|Updated Oct 23, 2025
One-click install
npx skills add https://github.com/wrsmith108/figma-docker-init --skill stream-chain-wrsmith108
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: stream-chain
Source: https://github.com/wrsmith108/figma-docker-init/tree/main/.claude/skills/stream-chain
Command: npx skills add https://github.com/wrsmith108/figma-docker-init --skill stream-chain-wrsmith108

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires claude-flow.

What problem does it solve?

Breaking down complex tasks into sequential steps for AI agents can be challenging, leading to fragmented outputs or manual intervention. This Skill automates multi-step workflows by seamlessly passing the output of one agent as input to the next, ensuring coherent and efficient execution of complex pipelines.

Core Features & Use Cases

  • Custom Chains: Define and execute custom sequences of prompts for maximum flexibility in multi-agent pipelines.
  • Predefined Pipelines: Utilize battle-tested workflows for common tasks like analysis, refactoring, testing, and optimization.
  • Context Flow: Each step receives the complete output from the previous step, enabling sophisticated data transformation and sequential processing.
  • Use Case: Automate a security audit by chaining agents to "Analyze authentication system for vulnerabilities," then "Identify and categorize security issues," and finally "Propose fixes with implementation priority."

Quick Start

Run a custom chain to "Write a user authentication function," then "Add input validation and error handling," and finally "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 where each agent's output feeds into the next?

Stream-chain orchestrates multi-agent workflows by passing each step's output as input to the next agent, enabling sequential processing without manual intervention. It supports custom chains and predefined pipelines for automation across development, data processing, and security tasks.

Can I chain AI agents together for complex tasks like security auditing or code refactoring?

Yes. Stream-chain enables chaining agents for predefined workflows including security analysis, code refactoring, testing, and optimization. Each step receives complete context from the previous step, supporting sophisticated data transformation across sequential stages.

What's the difference between custom chains and predefined pipelines in stream-chain?

Custom chains let you define flexible prompt sequences for maximum control in multi-agent pipelines. Predefined pipelines provide battle-tested workflows for common tasks. Both pass streaming data between steps with full context propagation.

Does stream-chain support streaming data flow and per-step configuration?

Stream-chain supports streaming data flow between steps with configurable execution controls: per-step timeout, verbose output, and debug logging. Each step propagates complete context to enable flexible orchestration.

Can I control execution behavior like timeouts and debug output for individual steps?

Yes. Stream-chain provides per-step timeout configuration, verbose output modes, and debug logging for granular execution control. These settings apply to individual steps within your chain or pipeline.

What dependencies does stream-chain require to run?

Stream-chain depends on claude-flow for orchestration. This enables the multi-agent workflow foundation and streaming data flow between chained steps.