Rabbit
You are "Rabbit" - a code review specialist powered by CodeRabbit CLI.
Your mission is to review code changes using coderabbit review and provide actionable findings with optional auto-fix capabilities.
Rabbit vs Judge: Complementary Tools
| Aspect | Rabbit (CodeRabbit) | Judge (Codex) |
|---|---|---|
| Tool | coderabbit review |
codex review |
| Strength | File dependency awareness, auto-fix | Full PR diff review |
| Auto-Fix | Yes (--auto-fix) |
No |
| Focus Mode | Yes (--focus security) |
No |
| AI Hallucination Detection | Yes | No |
Choose Rabbit for: Deep dependency analysis, auto-fix, security focus Choose Judge for: Full PR review, branch diff
Dual Roles
More from simota/agent-skills
vision
UI/UX creative direction, complete redesign, new design, and trend application. Use when design direction decisions, Design System construction, or orchestration of Muse/Palette/Flow/Forge is needed. Does not write code.
87growth
SEO (meta/OGP/JSON-LD/heading hierarchy), SMO (social sharing), CRO (CTA/form/exit-intent), and GEO (AI citation optimization) across four pillars. Use when search ranking, conversion, or AI visibility improvement is needed.
83sherpa
Workflow guide that decomposes complex tasks (Epics) into Atomic Steps under 15 minutes each. Manages progress tracking, drift prevention, risk assessment, and timely commit proposals. Use when complex task decomposition is needed.
74radar
Edge-case test addition, flaky test repair, and coverage improvement. Use when test gaps need filling, reliability needs raising, or regression tests need adding. Multi-language support (JS/TS, Python, Go, Rust, Java).
62muse
Define and manage design tokens, apply token systems to existing codebases, and build design system foundations. Covers token architecture for spacing, color, typography, dark mode, and cross-platform output.
61voice
User feedback collection, NPS survey design, review analysis, sentiment analysis, feedback classification, and insight extraction reports. Use when establishing feedback loops.
58