Turn a project description into a Claude Code team architecture with generated agents, shared skills, and orchestration patterns instead of hand-designing the whole setup.
Scanned 6/8/2026
Install via CLI
openskills install agentskillexchange/skills---
name: "Generate domain-specific Claude Code agent teams and shared skills with Harness"
slug: "generate-domain-specific-claude-code-agent-teams-and-shared-skills-with-harness"
description: "Turn a project description into a Claude Code team architecture with generated agents, shared skills, and orchestration patterns instead of hand-designing the whole setup."
github_stars: 2807
verification: "security_reviewed"
source: "https://github.com/revfactory/harness"
author: "revfactory"
publisher_type: "organization"
category: "Templates & Workflows"
framework: "Claude Code"
tool_ecosystem:
github_repo: "revfactory/harness"
github_stars: 2807
---
# Generate domain-specific Claude Code agent teams and shared skills with Harness
Turn a project description into a Claude Code team architecture with generated agents, shared skills, and orchestration patterns instead of hand-designing the whole setup.
## Prerequisites
Claude Code, Harness plugin or copied skill files, a project or domain description to turn into agent-team definitions
## Installation
Basic usage or getting-started notes:
- **Validation** — Trigger verification, dry-run testing, and with-skill vs without-skill comparison tests
- ### Via Marketplace
- #### Add the marketplace
- Source: https://github.com/revfactory/harness
- Extracted from upstream docs: https://raw.githubusercontent.com/revfactory/harness/HEAD/README.md
## Documentation
- https://github.com/revfactory/harness#readme
## Source
- [Agent Skill Exchange](https://agentskillexchange.com/skills/generate-domain-specific-claude-code-agent-teams-and-shared-skills-with-harness/)
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.