Advertise hereReach developers building with AI coding agents. →

Based on Google’s official docs, checked

Antigravity skills: create, store and run SKILL.md skills

Skills in Google Antigravity are folders with a SKILL.md file that teach the agent how to do one kind of task. On every turn the agent sees each skill’s name and description, and reads the full instructions only when a skill looks relevant. Skills are an open standard, so the same folder format works in other agents too. This guide follows Antigravity’s Agent skills docs, checked November 1, 2026, and covers where the App, CLI and IDE look for skills.

  1. 1. Create the skill folder

    Antigravity defaults to .agents/skills in your workspace (it still reads the older .agent/skills). Each skill is its own folder with a required SKILL.md and optional scripts/, examples/ and resources/ folders.

    mkdir -p .agents/skills/code-review
  2. 2. Write SKILL.md with frontmatter

    description is required and is what the agent reads to decide whether to use the skill; name is optional and defaults to the folder name (lowercase, hyphens). Write the description in the third person with keywords for when it applies.

    ---
    name: code-review
    description: Reviews code changes for bugs, style issues, and best practices. Use when reviewing pull requests or checking code quality.
    ---
    
    # Code Review Skill
    
    1. Correctness: verify the code meets the spec.
    2. Edge cases: check error conditions and boundaries.
  3. 3. Run it

    You don’t have to name a skill; the agent picks it from context. To force it, type / and the skill name in the App message box or the CLI prompt. In the CLI, every skill becomes a slash command; run /skills reload after adding one mid-session.

    /code-review
  4. 4. Share skills globally or as a plugin

    Put skills you want in every project in ~/.gemini/config/skills/, which the App and CLI share. In the CLI you can install skill bundles packaged as plugins with agy plugin install, from the official marketplace, a GitHub URL or a local path.

    agy plugin list --json
    agy plugin install ./my-skills-plugin

Where each surface looks for skills

App: .agents/skills/ in the workspace (and in each parent folder up to the repository root) and ~/.gemini/config/skills/ globally.

CLI: the same two locations plus plugin skills under ~/.gemini/config/plugins/, and ~/.gemini/antigravity-cli/skills/ and ~/.gemini/skills/, which the App doesn’t read.

IDE: .agents/skills/ in the workspace and ~/.gemini/config/skills/ globally, with the legacy ~/.gemini/antigravity/skills/ still supported. Check active skills from the Customizations menu in the agent side panel.

How the agent uses a skill

Antigravity uses progressive disclosure: discovery (names and descriptions on every turn), activation (it reads the full SKILL.md when relevant) and execution (it follows the instructions). That keeps unused skills cheap, so the description is the part worth the most care.

Best practices from the docs

Keep each skill focused on one job instead of a do-everything skill. Make the description specific about what the skill does and when. If a skill ships scripts, tell the agent to run them with --help rather than reading their source, to keep context focused. For complex skills, add a decision tree that helps the agent pick an approach.

Tips

Next steps

Verified MCP servers for Antigravity

→

Generate an MCP config for Antigravity

→

Google Antigravity hub

→

Google Antigravity vs Claude Code: documented features compared

→

Google Antigravity vs Cursor: documented features compared

→

How to add an MCP server to Codex

→

How to add an MCP server to Cursor

→

How to add an MCP server to GitHub Copilot in VS Code

→

How to add an MCP server to Google Antigravity

→

How to migrate from Gemini CLI to Antigravity CLI

→

Portable agent skills: one SKILL.md for every coding agent

→

Safe “always allow” rules for Claude Code and Codex CLI

→

GitHub Copilot CLI yolo mode: --allow-all and safer tool rules

→

Codex sandbox modes and approval policies explained

→

How to install Claude Code on macOS, Linux and Windows

→

How to install the OpenAI Codex CLI

→

Claude Code auto mode: what runs, what gets blocked, how to turn it off

→

Agent Skills moves to the Agentic AI Foundation: what changes

→

MCP security: the risks in MCP servers and how to lock them down

→

Claude Code in VS Code: install, shortcuts and CLI differences

→

What is AGENTS.md? The open instruction file for coding agents

→

Claude Code on Windows: native, WSL and common errors

→

Codex skills: create, install and use SKILL.md skills in Codex

→

GitHub Copilot CLI: install, sign in and start using it

→

Cursor Agent SDK: build, test and deploy agents as code

→

GPT-6.1 Terra in Codex and the API: setup, pricing and limits

→

MCP OAuth: connect a remote MCP server in Claude Code, Codex and Cursor

→

Codex config.toml: location, precedence and the settings to change

→

Codex on Windows: native sandbox setup, WSL and fixes

→

Antigravity CLI (agy): install, sign in, modes and commands

→

Google Antigravity on Windows: install, WSL, sandbox and fixes

→

GitHub Copilot coding agent (now cloud agent): how to use it

→

GitHub Copilot agent mode: how to use it in your IDE

→

Claude Code tips from Anthropic’s best practices

→

Claude Code with OpenRouter: setup, models and troubleshooting

→

How to add an MCP server: Claude Code, Codex, Cursor, Copilot and Antigravity

→

Supabase RLS for AI-built apps: grants, policies and tests

→

Claude Code in JetBrains IDEs: install, connect and fix issues

→

GitHub Copilot skills: create, install and use agent skills

→

Claude Code subagents: create, configure and run them

→

Check which plugins, hooks and MCP servers your agent loads

→

Cursor rules examples: .mdc files for each rule type

→

Fix spawn npx ENOENT when starting an MCP server

→

Frequently asked questions

Workspace skills go in .agents/skills/<skill-folder>/ and global skills in ~/.gemini/config/skills/<skill-folder>/.

Sources