Agents vs. skills
| Skills | Agents | |
|---|---|---|
| How they work | Process instructions | AI personas with defined identity |
| Activation | Fire automatically by context | Invoked explicitly |
| Output | Step-by-step guidance | Expert analysis in the agent’s voice |
| Stored in | ~/.gemini/antigravity/skills/ | ~/.gemini/antigravity/agents/ |
How to invoke an agent
Reference an agent by name in your message to Antigravity:/review uses the code-reviewer agent, and code-reviewer can delegate to security-engineer for security-specific review.
All agents
| Agent | Specializes in |
|---|---|
code-reviewer | Reviews implementation against plan and quality standards |
backend-architect | Backend systems, APIs, databases, reliability |
frontend-architect | UI components, state management, performance |
security-engineer | Vulnerability review, auth design, threat modeling |
deep-research | Multi-source research with source quality ranking |
system-architect | Distributed systems, migrations, observability |
socratic-mentor | Educational guide using Socratic discovery learning |
repo-index | Repository context compression and session initialization |
The review verdict system
Thecode-reviewer agent renders one of three verdicts at the end of every review:
- APPROVED — implementation meets the plan and quality bar; ready to merge
- APPROVED WITH SUGGESTIONS — implementation is sound but has non-blocking improvements worth addressing
- CHANGES REQUIRED — critical or important issues must be fixed before merging
Customizing agents
Agent files live in~/.gemini/antigravity/agents/. Each file is a plain Markdown file with a YAML frontmatter block (name, description) and a system prompt body. You can edit any agent file to adjust its persona, focus areas, or output format to suit your project.
Code reviewer
Reviews implementation against the plan across 6 structured areas and renders a verdict.
Backend architect
Designs reliable, scalable server-side systems: APIs, databases, and service boundaries.
Frontend architect
Builds maintainable, performant UIs: component design, state management, and accessibility.
Security engineer
Identifies vulnerabilities, models threats, and designs secure systems using OWASP.
Deep research
Gathers multi-source research with explicit source quality ranking and confidence levels.
System architect
Holistic system design across service boundaries, distributed systems, and migrations.
Socratic mentor
Guides learning through strategic questioning rather than direct answers.
Repo index
Compresses repository context at session start for token-efficient subsequent work.