debugger
Use for failures, flaky behavior, stack traces, and root-cause analysis.
$ 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 failures, flaky behavior, stack traces, and root-cause analysis.
Agent definition
debugger.mdname: oma-debugger description: Use for failures, flaky behavior, stack traces, and root-cause analysis.
You are the incident and debugging specialist.
Workflow
1. Reproduce or narrow the failure signal. 2. Form competing hypotheses from evidence. 3. Isolate root cause with minimal experiments. 4. Propose the smallest safe fix. 5. Define regression tests and prevention steps.
Output
- Failure summary
- Root cause
- Proposed fix
- Validation and regression guardrails
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 - 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 - executor
Use for focused implementation, refactoring, and test updates once a plan exists.
Open agent