houmao-agent-loop-pro

Author and execute schema-rich Houmao agent collaboration loops from a loop directory.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

It solves the problem of turning a human intent description into an executable, topology-aware collaboration loop package that you can author, validate, and run across multiple loosely-coupled AI agents.

Core Features & Use Cases

  • Schema-rich loop authoring: scaffolds editable intention material and generates a structured execplan/contract layout for a loop rooted at intention/ and execplan/.
  • Deterministic staged execplan generation: supports fast-forward and step-by-step generation (with execplan ADRs) for process, contracts, harness, skills, bindings, and final docs.
  • Topology-aware execution control: prepares agents and workspaces, validates readiness, launches agents, starts the loop, and provides run lifecycle actions like pause/resume/recover/stop/status.
  • Operational boundaries & routing discipline: keeps platform mechanics routed to maintained Houmao skills while this skill focuses on generated loop packaging and its pro authoring/execution workflow.

Quick Start

Use houmao-agent-loop-pro init <loop-dir> to scaffold an empty pro loop workspace and create the intention source files (and do not generate files until you provide the loop directory).

Frequently Asked Questions about houmao-agent-loop-pro

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

FAQPage Schema
How do I generate an executable multi-agent collaboration loop from a human intent description?

To generate an executable multi-agent collaboration loop, you initiate a topology-aware loop workspace and scaffold editable intention materials to produce structured execplan and contract layouts.

What is topology-aware agent orchestration and how does it manage runtime control?

Topology-aware agent orchestration manages runtime control by validating workspace readiness, launching agents, and executing lifecycle actions like pause, resume, recover, and stop across loosely-coupled AI agents.

How do I scaffold a schema-rich agent loop directory and generate execution contracts?

You scaffold a schema-rich agent loop directory by initializing a root loop directory, which structures staged generation across process, specs, harness, skills, and bindings to output execution contracts.

Can I generate execplan contracts step-by-step instead of fast-forwarding the entire loop package?

Yes, you can generate execplan contracts step-by-step instead of fast-forwarding, allowing you to create architecture decision records for each stage of the loop package generation.

Do I need a specific directory structure to author and run topology-aware tree-loop packages?

Yes, you need a user-provided loop directory root to author and run topology-aware tree-loop packages, ensuring correct staged generation order for process, contracts, and harness artifacts.

Why does my multi-agent runtime control skill route platform operations to maintained skills instead of generating them locally?

Multi-agent runtime control routes platform operations to maintained skills to preserve operational boundaries, ensuring the skill focuses solely on generating loop-local contracts and execution artifacts.