stream-chain

Orchestrates multi-agent workflows by streaming each step's output into the next.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/bjpl/hablas --skill stream-chain-bjpl
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: stream-chain
Source: https://github.com/bjpl/hablas/tree/main/.claude/skills/stream-chain
Command: npx skills add https://github.com/bjpl/hablas --skill stream-chain-bjpl

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires claude-flow.

What problem does it solve?

Orchestrating multi-step AI workflows where each step's output feeds into the next can be complex and error-prone. This skill simplifies the creation of sequential processing pipelines, ensuring seamless data flow and context preservation across agents.

Core Features & Use Cases

  • Custom Chains: Define and execute custom sequences of prompts for maximum flexibility.
  • Predefined Pipelines: Utilize battle-tested workflows for common tasks like analysis, refactoring, testing, and optimization.
  • Context Preservation: Each step receives the complete output from the previous step, maintaining full context.
  • Use Case: Need to refactor a codebase? Use the refactor pipeline to first identify code smells, then create a refactoring plan, and finally apply changes to high-priority items, all in an automated, sequential flow.

Quick Start

Run a custom chain to analyze codebase structure, identify improvement areas, and generate an action plan. claude-flow stream-chain run "Analyze codebase structure" "Identify improvement areas" "Generate 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 tasks together in a workflow?

Stream-chain orchestrates multi-step AI workflows by feeding each step's output into the next. Define a sequence of prompts using the `run` command, and each agent receives the complete prior output, maintaining full context throughout the pipeline.

Can I automate code refactoring with predefined pipelines?

Yes. Stream-chain includes predefined pipelines like `refactor` that automate multi-stage processes: identify code smells, create a refactoring plan, and apply changes sequentially without manual intervention between steps.

What's the best way to build custom chains for data transformation?

Define custom chains by specifying sequential prompts with `stream-chain run`. Each step receives prior output as input, enabling flexible data transformation pipelines for analysis, processing, or workflow automation tasks.

Does stream-chain preserve context across multiple processing steps?

Yes. Stream-chain ensures each step receives the complete output from the previous step, maintaining full context preservation across the entire chain, which is essential for coherent multi-agent workflows.

What options are available for monitoring streaming execution?

Stream-chain supports verbose, timeout, and debug options to enable observable execution and streaming data flow. These controls help you track and troubleshoot multi-step workflows as they execute.

Can I use stream-chain for data processing pipelines?

Yes. Stream-chain applies to software development, data processing, and workflow automation. It supports both custom chains and predefined pipelines for sequential, streaming coordination across processing tasks.