skills.rest
Yeachan-Heo
Yeachan-HeoCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

pipeline

Orchestrate AI agent pipelines with branching, parallel execution, and state management.

38.5k|3.5k|Updated Jan 9, 2026
Search Tags:#automation#workflow#AI agents#branching#orchestration#parallel#pipeline
One-click install
npx skills add https://github.com/Yeachan-Heo/oh-my-claudecode --skill pipeline-yeachan-heo
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: pipeline
Source: https://github.com/Yeachan-Heo/oh-my-claudecode/tree/main/skills/pipeline
Command: npx skills add https://github.com/Yeachan-Heo/oh-my-claudecode --skill pipeline-yeachan-heo

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill enables chaining multiple agents into defined workflows where the output of one stage becomes the input to the next, enabling end-to-end automation of complex tasks without manual handoffs.

Core Features & Use Cases

  • Sequential Pipelines: Connect A -> B -> C to pass results along a deterministic chain.
  • Branching Pipelines: Route tasks based on conditions to different agents or sub-pipelines.
  • Parallel-Then-Merge Pipelines: Run multiple agents concurrently and merge their outputs for subsequent stages.
  • Built-in Presets: Predefined pipelines like Review, Implement, Debug, Research, Refactor, and Security to accelerate common workflows.
  • Custom Syntax & Data Protocol: Flexible definitions and structured context passed between stages to ensure consistent integration.
  • State & Error Management: Persist pipeline state, handle failures, retries, and recovery scenarios to maintain reliability.
  • Integration & Extensibility: Works with related skills for orchestration, debugging, and research workflows.

Quick Start

  1. Define a pipeline using a built-in preset, for example: /pipeline review <task>.
  2. Invoke or auto-detect a pipeline invocation from natural language input and monitor progress until completion.
  3. When done, review the final output and reuse the pipeline pattern for future tasks.

Quick Start Examples

  • /pipeline review "audit the codebase for security improvements"
  • /oh-my-claudecode:pipeline implement "add OAuth2 authentication to API"

Frequently Asked Questions about pipeline

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

FAQPage Schema
How do I automate AI agent workflows with branching and parallel execution?▼

To automate AI agent workflows, you can chain agents into defined pipelines where outputs are passed as inputs. This supports branching, parallel execution, and persistent state management for complex task automation.

What is the best way to chain multiple AI agents for code reviews and debugging?▼

Chaining multiple AI agents for code reviews and debugging is best handled by using built-in pipeline presets. Predefined workflows like Review, Debug, and Implement accelerate common software engineering tasks without manual handoffs.

Can I run multiple AI agents concurrently and merge their outputs in a pipeline?▼

Yes, you can run multiple AI agents concurrently using parallel-then-merge pipelines. This allows you to execute stages simultaneously and merge their structured outputs for subsequent pipeline steps.

How do I handle state persistence and error recovery in AI agent orchestration?▼

Handling state persistence and error recovery in AI agent orchestration requires built-in state and error management. This persists pipeline state, handles failures, and manages retries and recovery scenarios to maintain workflow reliability.

Does pipeline orchestration support conditional routing for different software tasks?▼

Pipeline orchestration supports conditional routing through branching pipelines. You can route tasks based on specific conditions to different agents or sub-pipelines to handle diverse software project requirements like refactoring and security.

Do I need predefined stages to orchestrate AI agent pipelines for feature implementation?▼

Yes, orchestrating AI agent pipelines for feature implementation requires defined stages and a structured data passing protocol. This ensures consistent integration and context passing between sequential or parallel agents.

Related Skills

Explore More Software Engineering Skills→
pradyumnasagarpradyumnasagar
6

agent-handoff

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

Community
Advanced
lucasfcostalucasfcosta
62

general-code-review

Automate code-review of diffs for correctness, simplicity, and test coverage.

Community
Advanced
pradyumnasagarpradyumnasagar
6

roadmap-author

Guide authors through creating and validating ORS SKILL.md files.

Community
Intermediate
AreteDriverAreteDriver
4

session-manager

Preserves cross-session AI agent context by generating structured handoff documents.

Community
Advanced