moonrepo-skill
AGENTS.md7 starsChanged 10 months agoApache-2.0View on GitHub
This skill package is compatible with the skills.sh open agent ecosystem. Activates when the user mentions: Activates when the user mentions: Contributions welcome! Please ensure skills follow the Agent Skills format.
The file
Files
Agent Compatibility
This skill package is compatible with the skills.sh open agent ecosystem.
Supported Agents
- claude-code — Anthropic's Claude Code CLI
- cursor — Cursor AI editor
- copilot — GitHub Copilot
- gemini — Google Gemini CLI
- amp — Amp agent
- opencode — Opencode agent
- antigravity — Antigravity agent
Installation
# Install for all supported agents
npx add-skill hyperb1iss/moonrepo-skill
# Install for specific agent
npx add-skill hyperb1iss/moonrepo-skill -a claude-code
npx add-skill hyperb1iss/moonrepo-skill -a cursor
# List available skills
npx add-skill hyperb1iss/moonrepo-skill --listSkills Provided
| Skill | Description |
moon | Polyglot monorepo build system configuration and usage |
proto | Multi-language version manager and plugin development |
Skill Triggers
moon
Activates when the user mentions:
moon.yml,.moon/workspace.yml,.moon/toolchains.yml- moon tasks, moon ci, moon query
- monorepo configuration, task orchestration
- moonrepo in general
proto
Activates when the user mentions:
.prototools, proto commands- Tool version management, version pinning
- Installing node/rust/python/go versions
- proto plugins, WASM plugins
Directory Structure
skills/
├── moon/
│ ├── SKILL.md # Core moon instructions
│ ├── references/
│ │ ├── workspace-config.md
│ │ ├── task-config.md
│ │ ├── cli-reference.md
│ │ └── v2-migration.md
│ └── examples/
│ ├── workspace.yml
│ ├── moon.yml
│ └── ci-workflow.yml
└── proto/
├── SKILL.md # Core proto instructions
├── references/
│ ├── config.md
│ └── commands.md
└── examples/
└── prototools-full.tomlContributing
Contributions welcome! Please ensure skills follow the Agent Skills format.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

