workflow-runner

Execute agency-orchestrator YAML workflows within AI tool sessions.

Updated Apr 19, 2026
One-click install
npx skills add https://github.com/OnClickListener2048/confluence-mcp --skill workflow-runner-onclicklistener2048
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: workflow-runner
Source: https://github.com/OnClickListener2048/confluence-mcp/tree/main/.claude/skills/workflow-runner
Command: npx skills add https://github.com/OnClickListener2048/confluence-mcp --skill workflow-runner-onclicklistener2048

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Directly executing agency-orchestrator YAML workflows inside Claude Code / OpenClaw / Cursor without API keys, using the current session's LLM as the execution engine.

Core Features & Use Cases

  • In-session orchestration of multi-role workflows defined in YAML.
  • No external API keys required; runs entirely within the current AI tool environment.
  • Ideal for scenarios like cross-role reviews (e.g., product manager + architect) or automated story creation using predefined YAML workflows.

Quick Start

Provide a YAML workflow file to be executed directly in this session.

Frequently Asked Questions about workflow-runner

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

FAQPage Schema
How do I run YAML multi-agent workflows inside Claude Code or Cursor without API keys?

To run YAML multi-agent workflows without API keys, you can execute agency-orchestrator YAML files directly inside AI tools like Claude Code or Cursor. The current session's LLM acts as the execution engine, requiring no external authentication.

What is in-session multi-agent orchestration and how does it work with YAML?

In-session multi-agent orchestration coordinates multiple AI roles defined in YAML within a single chat session. It uses the active LLM to execute cross-role collaborations, such as product manager and architect reviews, entirely locally.

Do I need role definition files to execute YAML workflows in my AI tool?

Yes, executing YAML workflows requires role definitions to be available in your environment. You need predefined agent roles, such as agency-agents-zh, loaded into the session to enable multi-role collaboration.

Can I use this to automate cross-role story creation and reviews?

Yes, you can automate cross-role story creation and reviews by supplying a predefined YAML workflow. The orchestrator manages the collaboration between agents, such as a product manager and an architect, within the current session.

What are the limitations of using the current LLM session as a workflow execution engine?

Using the current LLM session as the execution engine means workflows are constrained by the active session's context window and capabilities. It requires predefined role definitions in the environment and does not support external API integrations.