How do I install the Antigravity skill?

Run npx skillmds@latest add dannykkh/antigravity in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Antigravity safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Antigravity?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Antigravity free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Antigravity?

Dannykkh (@dannykkh) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Antigravity by dannykkh — Agent Skill

Name: Antigravity
Author: Dannykkh

Antigravity

Use Google Antigravity CLI (`agy`) for independent code or plan review, large-context analysis, and a second-model opinion. Trigger on Antigravity CLI, agy, Google CLI review, or requests that previously used the Gemini CLI runtime.

Dannykkh c8f3af6 2.3 KB Updated Sep 17, 2026

File contents

Antigravity CLI

Google Antigravity CLI is the Google command-line runtime. Gemini remains a model family; do not invoke the retired gemini executable.

Workflow

Verify the runtime with agy --version. If it is unavailable, report that Antigravity CLI must be installed or repaired; do not fall back to gemini.
Run agy models when model choice matters. Use a currently listed model and never hardcode a preview model from memory.
Give Antigravity a bounded prompt that names the files, question, required evidence, and output format.
Prefer read-only review. Grant write or command permissions only when the user asked Antigravity to modify or execute something.
Capture the result, verify actionable claims against the repository or tests, and distinguish Antigravity findings from confirmed facts.

Headless usage

agy -p "Review the authentication flow. Cite file:line evidence and list only actionable findings." --output-format json

Optional controls:

--model <id>: choose an ID returned by agy models.
--effort <level>: tune reasoning effort when supported by the selected model.
--output-format text|json|stream-json: select machine-readable output for automation.
--continue or --conversation <id>: resume an existing Antigravity conversation.

Use a timeout supplied by the host runner for background jobs. Never use obsolete Gemini CLI flags such as --approval-mode, --sandbox, --yolo, or -i.

Permission boundary

Use Antigravity's configured permission policy for routine automation. --dangerously-skip-permissions bypasses safety prompts and is allowed only when the user explicitly authorized unrestricted tool execution for that run. A request for review or analysis alone is not that authorization.

Result contract

Return:

the model ID used, when explicitly selected;
the useful findings or recommendation;
which claims were independently verified;
any timeout, authentication, permission, or parse failure.

Do not present an Antigravity opinion as test evidence.

---name: antigravitydescription: Use Google Antigravity CLI (`agy`) for independent code or plan review, large-context analysis, and a second-model opinion. Trigger on Antigravity CLI, agy, Google CLI review, or requests that previously used the Gemini CLI runtime.---# Antigravity CLIGoogle Antigravity CLI is the Google command-line runtime. Gemini remains a model family; do not invoke the retired `gemini` executable.## Workflow1. Verify the runtime with `agy --version`. If it is unavailable, report that Antigravity CLI must be installed or repaired; do not fall back to `gemini`.2. Run `agy models` when model choice matters. Use a currently listed model and never hardcode a preview model from memory.3. Give Antigravity a bounded prompt that names the files, question, required evidence, and output format.4. Prefer read-only review. Grant write or command permissions only when the user asked Antigravity to modify or execute something.5. Capture the result, verify actionable claims against the repository or tests, and distinguish Antigravity findings from confirmed facts.## Headless usage```bashagy -p "Review the authentication flow. Cite file:line evidence and list only actionable findings." --output-format json```Optional controls:- `--model <id>`: choose an ID returned by `agy models`.- `--effort <level>`: tune reasoning effort when supported by the selected model.- `--output-format text|json|stream-json`: select machine-readable output for automation.- `--continue` or `--conversation <id>`: resume an existing Antigravity conversation.Use a timeout supplied by the host runner for background jobs. Never use obsolete Gemini CLI flags such as `--approval-mode`, `--sandbox`, `--yolo`, or `-i`.## Permission boundaryUse Antigravity's configured permission policy for routine automation. `--dangerously-skip-permissions` bypasses safety prompts and is allowed only when the user explicitly authorized unrestricted tool execution for that run. A request for review or analysis alone is not that authorization.## Result contractReturn:- the model ID used, when explicitly selected;- the useful findings or recommendation;- which claims were independently verified;- any timeout, authentication, permission, or parse failure.Do not present an Antigravity opinion as test evidence.

Frequently asked questions