workflow-runner

Execute agency-orchestrator YAML workflows in-session with the active LLM.

Updated May 4, 2026
One-click install
npx skills add https://github.com/fred29910/migra-go --skill workflow-runner-fred29910
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: workflow-runner
Source: https://github.com/fred29910/migra-go/tree/main/.agents/skills/workflow-runner
Command: npx skills add https://github.com/fred29910/migra-go --skill workflow-runner-fred29910

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

在 AI 聊天工具内直接执行 agency-orchestrator 的 YAML 工作流,无需 API key,使用当前会话的 LLM 作为执行引擎。

Core Features & Use Cases

  • In-session multi-role orchestration: coordinate multiple agent roles inside the chat.
  • Role discovery and loading from agency-agents-zh or node_modules, enabling seamless access to predefined agent personas.
  • Automated workflow planning and per-layer execution: topological scheduling and layered prompts to ensure correct sequencing.
  • User-provided YAML workflows: support for both file-based and inline workflow definitions to trigger collaborative tasks.

Quick Start

在当前会话中提供一个 YAML 工作流文件即可开始执行。

Frequently Asked Questions about workflow-runner

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

FAQPage Schema
How do I run multi-role YAML workflows inside my LLM chat session?

To run multi-role YAML workflows inside your chat session, provide a .yaml workflow file or inline workflow definition, and the active LLM executes it as the engine for multi-role collaboration without requiring an API key.

What is topological scheduling for multi-role agent coordination?

Topological scheduling for multi-role agent coordination is an automated workflow planning mechanism that sequences layered prompts to ensure correct execution order across multiple roles defined in your YAML workflow.

Do I need an API key to execute agency-orchestrator YAML workflows?

No, you do not need an API key to execute agency-orchestrator YAML workflows because the skill uses the active LLM in your current chat session as the execution engine for all multi-role agent prompts.

Where does the skill discover role definitions for multi-role orchestration?

The skill discovers role definitions for multi-role orchestration by locating agency-agents-zh in various paths including the current directory, parent directory, relative to the YAML file, or inside node_modules.

Can I use inline YAML workflow definitions instead of a file for agent coordination?

Yes, you can use inline YAML workflow definitions instead of a file to trigger collaborative agent coordination tasks, and the skill will still handle role discovery, input collection, and per-layer execution.

What safety measures are included during in-session workflow execution?

During in-session workflow execution, the skill enforces strict safety prompts alongside in-session agent prompts to ensure secure multi-role collaboration while logging execution results for each topological layer.