pipeline

Orchestrate AI agents into sequential, branching, and parallel-merge pipelines.

2|Updated Feb 3, 2026
One-click install
npx skills add https://github.com/chanhee-kang/oh-my-gemini --skill pipeline-chanhee-kang
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pipeline
Source: https://github.com/chanhee-kang/oh-my-gemini/tree/main/skills/pipeline
Command: npx skills add https://github.com/chanhee-kang/oh-my-gemini --skill pipeline-chanhee-kang

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill enables reliable orchestration of AI agents into pipelines with clear data handoffs, allowing complex tasks to be decomposed into modular, repeatable workflows.

Core Features & Use Cases

  • Sequential pipelines: chain agents in order to transform data through multiple steps.
  • Branching pipelines: route tasks based on intermediate results.
  • Parallel-then-merge: run independent stages in parallel and merge outputs.
  • Built-in presets and custom syntax for designing workflows.
  • Data passing protocol and state management to persist execution context across stages.
  • Robust error handling and retry strategies.
  • Use cases include code review, feature implementation, research, and multi-stage automation across software projects.

Quick Start

Start by describing your desired workflow, for example: explore -> architect -> executor, or use a command like /pipeline review "optimize authentication" to automatically create and run a pipeline.

Frequently Asked Questions about pipeline

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

FAQPage Schema
How do I orchestrate AI agents into a sequential pipeline?

You can orchestrate AI agent pipelines by describing your desired workflow, such as explore -> architect -> executor. This skill automates the sequence and enforces a structured pipeline_context to ensure clear data handoffs between each stage.

Can I run parallel AI agent workflows and merge the results?

Yes, you can run parallel AI agent workflows and merge their outputs. This skill supports a parallel-then-merge pattern, allowing independent stages to execute concurrently and combine results for tasks like multi-stage automation.

How do I route AI agent tasks based on intermediate results?

You route AI agent tasks using branching pipelines that direct workflow execution based on intermediate results. This pattern allows dynamic task routing to handle complex scenarios like code review or feature implementation across different conditions.

Does this AI agent orchestration support error handling and state persistence?

Yes, this AI agent orchestration supports robust error handling, retry strategies, and state persistence. It maintains execution context across stages using a data passing protocol, ensuring reliable workflow automation even when failures occur.

What is the best way to automate multi-stage software projects with AI agents?

The best way to automate multi-stage software projects is using preset workflows or custom syntax to design repeatable AI agent pipelines. You can trigger tasks like code review or research automatically, ensuring structured data flow across all execution stages.