agentleFS
pedroiff0pedroiff0/awesome-skills/skills/autonomous-ai-agents/antigravity-guide/SKILL.md

antigravity-guide

Skill1 starsChanged 47 days agoMITView on GitHub

Provides a comprehensive guide, architecture reference, and quick-access sitemap for Google Antigravity (AGY), including CLI, Antigravity 2.0, IDE extensions, Python SDK, slash commands, keybindings, and customization hooks.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

Antigravity (AGY) Guide & Architecture Reference

Purity rules: Pure open documentation; no API keys, internal tokens, or closed endpoints.

This skill provides an authoritative operational reference for working with the Google Antigravity (AGY) ecosystem, covering the CLI, modern agent capabilities, slash command workflows, sidecars, and IDE features.

When to Use

  • Configuring or diagnosing Antigravity CLI (agy) or Antigravity IDE workspaces.
  • Authoring custom slash commands, agent modes, or persistent background tasks.
  • Integrating MCP (Model Context Protocol) servers and subagent topologies.
  • Troubleshooting terminal persistence, persistent runtimes, or task managers.

Key Architecture & Core Commands

# Start an interactive pair-programming session
agy

# Run directly against a specific repository or task
agy --dir /path/to/project --goal "Implement feature X with full test coverage"

# List and manage active background tasks and sidecars
agy task list
agy mcp list

Standard Workspace Hierarchy

<project_root>/
  ├── .agent/
  │   ├── skills/              # Workspace-scoped skills (SKILL.md)
  │   ├── rules/               # Contextual agent rules (*.md)
  │   └── mcp/                 # Local MCP configuration
  └── AGENTS.md                # Agent instructions & hard rules

Built-in Slash Command System

CommandPurpose
/goalAutonomous long-running execution mode; continues until goal is verified.
/planGenerates a structured multi-step execution plan artifact before coding.
/grill-meInteractive design alignment and architecture interview.
/scheduleConfigures cron schedules or one-shot notification timers.
/learnPersists user preferences and codebase corrections across conversations.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.