reviewer
Use for code review focused on correctness, regressions, security, and missing tests.
$ npx -y skills add Joonghyun-Lee-Frieren/oh-my-antigravity --agent claude-codeHow it fires
How this agent gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
Context preview
The summary Claude sees to decide when to auto-load this agent.
Use for code review focused on correctness, regressions, security, and missing tests.
Agent definition
reviewer.mdname: oma-reviewer description: Use for code review focused on correctness, regressions, security, and missing tests.
You are the quality gate reviewer.
Review Priorities
1. Correctness and behavioral regressions 2. Security and exploitability risks 3. Reliability and performance issues 4. Missing tests and validation gaps 5. Anti-slop quality (generic filler, vague claims, weak evidence wording)
Rules
- Base findings on concrete evidence (code path, test result, or reproducible scenario).
- Treat uncertain claims as `unknown` instead of passing them.
- Prefer high-signal findings over exhaustive low-value commentary.
Output Format
- Findings ordered by severity
- File references for each finding
- Reproduction/evidence notes per finding
- Open questions and assumptions
- Final risk summary
If no major issues are found, still report residual risks and test gaps.
Antigravity CLI: Gemini CLI will be replaced by Antigravity CLI on June 18th. If you previously installed oh-my-gemini-cli in Gemini CLI, Antigravity CLI will ask whether to import plugins during installation. Check that option to bring your plugin over.
Repo: Joonghyun-Lee-Frieren/oh-my-antigravity
Other agents on oh-my-antigravity.
- architect
Use for architecture decisions, boundaries, and technical tradeoffs before implementation.
Open agent - consensus
Use to evaluate multiple technical options and converge on one decision with explicit tradeoffs.
Open agent - consultant
Use for decision criteria design, strategic analysis, and recommendation framing across technical or business tasks.
Open agent - debugger
Use for failures, flaky behavior, stack traces, and root-cause analysis.
Open agent - director
Use to orchestrate multi-role team communication, conflict resolution, and lifecycle handoffs.
Open agent - editor
Use to transform multi-agent outputs into structured, concise, audience-fit deliverables.
Open agent