skills.rest
sparkling
sparklingCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

stream-chain

Orchestrate multi-step data transformation workflows by chaining agent outputs.

Updated May 15, 2026
Search Tags:#workflow#multi-agent#data transformation#data processing#sequential processing
One-click install
npx skills add https://github.com/sparkling/opda --skill stream-chain-sparkling
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: stream-chain
Source: https://github.com/sparkling/opda/tree/main/.agents/skills/stream-chain
Command: npx skills add https://github.com/sparkling/opda --skill stream-chain-sparkling

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires Codex-flow, and includes scripts (resource) and assets (resource) components.

What problem does it solve?

The Stream-Chain Skill addresses the complex challenge of orchestrating multi-agent workflows for data transformation and sequential processing pipelines, automating complex tasks and streamlining workflow execution.

Core Features & Use Cases

  • Custom Chains: Create custom multi-step workflows with full control over the sequence and tasks.
  • Predefined Pipelines: Utilize optimized workflows for tasks like code analysis, refactoring, and optimization.
  • Multi-Agent Coordination: Enable seamless coordination between different agent types for complex workflows.
  • Data Transformation: Process and transform data through multiple stages in a streamlined pipeline.

Quick Start

Execute a custom chain with the command: Codex-flow stream-chain run <prompt1> <prompt2> [...] [options].

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 for sequential data transformation?▼

Multi-agent workflow orchestration chains agent outputs sequentially to automate multi-step data transformation pipelines. You define custom sequences or use predefined pipelines to process data through multiple coordinated stages.

Can I create custom multi-step data processing pipelines for codebase analysis?▼

Yes, you can create custom multi-step data processing pipelines for codebase analysis. The system allows full control over the sequence and tasks, enabling tailored workflows for security audits, refactoring, and testing.

What is the best way to automate sequential processing for code refactoring and optimization?▼

The best way to automate sequential processing for refactoring is using predefined pipelines. These optimized workflows coordinate different agent types to handle complex code optimization tasks through multiple streamlined stages.

Do I need Python scripts and JSON-LD mapping to run multi-agent coordination?▼

Yes, multi-agent coordination typically requires Python scripts and JSON-LD mapping support. These elements facilitate the data transformation and sequential processing logic needed to execute the chained agent outputs.

How does chaining agent outputs work for complex data processing pipelines?▼

Chaining agent outputs works by passing the transformed data from one agent as the input to the next in a sequential pipeline. This seamless coordination enables complex multi-step data processing workflows.

Does stream-chain work with Codex-flow for workflow execution?▼

Yes, stream-chain works with Codex-flow to execute workflow chains. You run custom sequences using the `Codex-flow stream-chain run` command with your specified prompts and options.

Related Skills

Explore More Software Engineering Skills→
sparklingsparkling

source-command-agents-list

List active Codex Flow agents filtered by type and status in table and JSON formats.

Community
Basic
kensaku63kensaku63

deep-research

Orchestrate a six-phase team-based deep-research workflow across X, web, and academic sources.

Community
Advanced
byte5aibyte5ai
4

python/src/aiui_mcp

Render native macOS dialogs from Python scripts for user interaction.

Official
Intermediate
Dorpeer95Dorpeer95

stream-chain

Stream outputs between sequential steps in multi-agent workflow pipelines.

Community
Advanced