houmao-agent-loop-pairwise-v5

Initialize loop directories, generate execplan artifacts, and manage agent lifecycle operations.

18|3|Updated Mar 5, 2026
One-click install
npx skills add https://github.com/igamenovoer/houmao --skill houmao-agent-loop-pairwise-v5
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: houmao-agent-loop-pairwise-v5
Source: https://github.com/igamenovoer/houmao/tree/main/src/houmao/agents/assets/system_skills/legacy/houmao-agent-loop-pairwise-v5
Command: npx skills add https://github.com/igamenovoer/houmao --skill houmao-agent-loop-pairwise-v5

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill helps you manually initialize a loop directory, clarify or generate an execplan, and then prepare and launch a tree-structured collaboration of loosely-coupled AI agents.

Core Features & Use Cases

  • Manual loop initialization and materialization: scaffolds editable intention sources under intention/ and generated operational material under execplan/.
  • Iterative execplan generation: clarifies intent and implementation coverage, then generates execplan specs, harness, skills, and concrete agent bindings.
  • Operational loop lifecycle management: prepares agents and workspace, validates readiness, launches agents, and supports start/status/pause/resume/recover/stop execution stages.

Quick Start

Use the houmao-agent-loop-pairwise-v5 skill to init your loop by providing the required <loop-dir> root, then generate the execplan step-by-step and finally start execution after launching agents.

Frequently Asked Questions about houmao-agent-loop-pairwise-v5

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

FAQPage Schema
How do I orchestrate a multi-agent workflow with a tree-structured collaboration?

To orchestrate a multi-agent workflow, initialize a loop directory to scaffold editable intention sources, generate an execplan step-by-step, and then prepare, validate, and launch your tree-structured AI agents.

What is the best way to generate an execplan for AI agent orchestration?

The best way to generate an execplan is to clarify your intent and implementation coverage iteratively, which produces operational specs, harness, skills, and concrete agent bindings under your generated execplan directory.

Can I manage execution stages like pause and resume for a launched agent loop?

Yes, you can manage execution stages for a launched agent loop. The operational lifecycle supports start, status, pause, resume, recover, and stop commands to control the runtime execution of your agents.

Do I need a specific directory structure to initialize an agent loop?

Yes, you need a user-selected loop directory root. This root must contain an intention directory for editable source material and an execplan directory to hold the generated operational artifacts required for execution.

Why must operational details route through subskills during agent launch?

Operational details must route through subskills and runtime reference pages to prevent the system from inventing missing runtime roots, ensuring that agent preparation and validation follow the correct execution path.