rig-architect

Design, validate, and diagnose OpenRig multi-agent topologies.

60|9|Updated Apr 1, 2026
One-click install
npx skills add https://github.com/mvschwarz/openrig --skill rig-architect
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: rig-architect
Source: https://github.com/mvschwarz/openrig/tree/main/packages/daemon/specs/agents/shared/skills/rig-architect
Command: npx skills add https://github.com/mvschwarz/openrig --skill rig-architect

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Designing, authoring, and validating OpenRig topologies and the startup content that powers agent behavior, helping teams ship reliable multi-agent rigs.

Core Features & Use Cases

  • Author rig specs and agent specs
  • Create role guidance, startup context, and CULTURE.md
  • Diagnose why a launched rig's agents aren't behaving as intended
  • Validate rigs with standard rig tooling before deployment

Quick Start

Describe your rig intent and I will generate a complete rig spec and startup content ready to boot.

Frequently Asked Questions about rig-architect

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

FAQPage Schema
How do I design and validate a multi-agent topology?

Designing and validating a multi-agent topology involves authoring rig specs and agent specs, then validating them with standard rig tooling before deployment to ensure reliable agent behavior.

Why are my deployed multi-agent rig agents behaving unexpectedly?

Diagnosing unexpected multi-agent rig behavior involves analyzing the startup content powering the agents, including CULTURE.md, role guidance, and startup context files.

What files are needed to bootstrap an OpenRig multi-agent system?

Bootstrapping an OpenRig multi-agent system requires generating a rig.yaml file, CULTURE.md, guidance/role.md, and startup/context.md, along with optional pod SOPs and agent skills.

How do I write startup content for multi-agent rig specifications?

Writing startup content for multi-agent rig specifications involves creating role guidance, startup context, and CULTURE.md to define and control agent behavior.

Can I diagnose agent behavior issues without modifying the rig spec?

Diagnosing agent behavior issues without modifying the rig spec is possible by reviewing and adjusting the generated startup content, such as CULTURE.md and role guidance, that drives agent behavior.