skills.rest
LLM-Dev-Ops
LLM-Dev-OpsOFFICIAL
Explore all skills by this author →
GitHub

stream-chain

Orchestrate streaming multi-agent workflows that transform and route outputs across steps.

1|2|Updated Nov 5, 2025
Search Tags:#automation#workflow#multi-agent#streaming#orchestration#pipeline#claude-flow
One-click install
npx skills add https://github.com/LLM-Dev-Ops/observatory --skill stream-chain-llm-dev-ops
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: stream-chain
Source: https://github.com/LLM-Dev-Ops/observatory/tree/main/.claude/skills/stream-chain
Command: npx skills add https://github.com/LLM-Dev-Ops/observatory --skill stream-chain-llm-dev-ops

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Coordinating complex multi-agent workflows where each agent's output becomes the next step, with streaming data flow and preserved context.

Core Features & Use Cases

  • Custom Chains (run): Define flexible, step-by-step prompt sequences with guaranteed sequential data flow.
  • Predefined Pipelines (pipeline): Use battle-tested workflows for common tasks to accelerate setup.
  • Streaming Context: Each step receives the complete output from the previous step, enabling rich inter-agent collaboration.
  • Examples: Security audit workflow, code refactor chain, data processing pipeline.

Quick Start

claude-flow stream-chain run "Analyze codebase structure" "Identify improvements" "Generate action plan" claude-flow stream-chain pipeline analysis

Frequently Asked Questions about stream-chain

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

FAQPage Schema
What is multi-agent workflow orchestration for streaming pipelines?▼

Multi-agent workflow orchestration coordinates complex agent sequences where each step's output becomes the next step's input, enabling streaming data flow and preserved context across development, debugging, and automation pipelines.

How do I create step-by-step prompt chains for multi-agent automation?▼

Define custom chains using the run mode to build flexible, step-by-step prompt sequences with guaranteed sequential data flow, where each step receives the complete streaming output from the previous step.

Can I use predefined pipelines for common multi-agent workflow tasks?▼

Yes, predefined pipelines in pipeline mode provide battle-tested workflows for common automation tasks, accelerating setup for scenarios like security audits, code refactors, and data processing pipelines.

How does streaming context work between agents in a chained workflow?▼

Streaming context passes the complete output from the previous step directly to the next agent, enabling rich inter-agent collaboration and maintaining context persistence throughout the entire orchestration pipeline.

Can I configure custom pipelines and timeouts for multi-agent orchestration?▼

Yes, custom pipelines, configurable timeouts, memory persistence, and streaming data flow can be defined and managed via the .claude-flow/config.json configuration file for the orchestration workflow.

What are the limitations of streaming multi-agent workflow orchestration?▼

Orchestration requires sequential data flow dependency between steps, meaning each agent must complete before the next begins, and custom pipelines need explicit configuration through .claude-flow/config.json to function correctly.

Related Skills

Explore More Software Engineering Skills→
smith-hornsmith-horn
75

stream-chain

Stream outputs between steps in multi-agent workflows.

Official
Intermediate
pingshian0131pingshian0131
1

openclaw-cron

Manage scheduled cron jobs for OpenClaw agents.

Community
Advanced
pradyumnasagarpradyumnasagar
6

agent-handoff

Automate inter-skill data transfer and provenance capture via JSON Material Passports.

Community
Advanced
tech-with-sethtech-with-seth
4

add-feature-flag

Implement PostHog feature flags for server-side and client-side gating.

Official
Intermediate