craft

Coordinate multi-agent Loom workflows across Architect, Security, Coder, and Code Reviewer roles.

2|Updated Apr 4, 2026

Search Tags:#workflow #architecture #multi-agent #orchestration #code-review #loom

Ready to run

npx skills add https://github.com/Nickalus12/Loom --skill craft-nickalus12

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: craft
Source: https://github.com/Nickalus12/Loom/tree/main/claude/skills/craft
Command: npx skills add https://github.com/Nickalus12/Loom --skill craft-nickalus12

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates the delivery of complex, multi-role tasks by coordinating Loom's end-to-end orchestration pipeline (Architect, Security, Coder, Code Reviewer) into a single, repeatable workflow.

Core Features & Use Cases

End-to-end orchestration: Coordinates task decomposition, role assignment, and phased execution across Architect, Security, Coder, and Code Reviewer.
Mode versatility: Supports Cloud by default and Local mode for offline or private environments.
Verification & governance: Provides built-in verification steps and audit trails of results, files changed, and code review findings.
Use Case: Ideal for complex feature work, architecture audits, and reproducible engineering tasks.

Quick Start

Describe your task to the craft tool and initiate the multi-agent orchestration in Cloud or Local mode to begin.

Frequently Asked Questions about craft

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

FAQPage Schema

How do I orchestrate multi-agent workflows for complex code tasks?▼

Multi-agent orchestration coordinates role-based execution across Architect, Security, Coder, and Code Reviewer phases to decompose, implement, and verify complex engineering tasks into a single repeatable pipeline.

What is a multi-agent code review pipeline and how does it work?▼

A multi-agent code review pipeline assigns specialized roles like Security and Code Reviewer to audit implementation, generating verification steps and audit trails of files changed and review findings for reproducible governance.

Can I run multi-agent orchestration in local mode for offline environments?▼

Yes, multi-agent orchestration supports Local mode for offline or private environments, alongside Cloud mode by default, enabling staged collaboration across roles without requiring external connectivity.

How do I automate architecture audits and task decomposition for software engineering?▼

Automate architecture audits by describing your task to the orchestration tool, which decomposes it into Architect, Security, Coder, and Code Reviewer phases with built-in verification and audit trails.

Does multi-agent orchestration support staged collaboration across different engineering roles?▼

Yes, multi-agent orchestration supports staged collaboration by assigning tasks sequentially across Architect, Security, Coder, and Code Reviewer roles with verification steps and audit trails for end-to-end delivery.

What are the limitations of multi-agent orchestration for complex feature work?▼

Multi-agent orchestration requires tasks suited to role-based decomposition and phased execution; simple or single-step tasks may not benefit from the staged Architect, Security, Coder, and Code Reviewer pipeline overhead.