abanoub-ashraf/manus-skills-import/coderabbit-skill
Claude Code and agent skill by abanoub-ashraf/manus-skills-import
Trust tier 2
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
Use when the user wants to run CodeRabbit CLI locally, review staged or uncommitted changes, inspect CodeRabbit findings, or apply CodeRabbit feedback before commit or PR.
Install
npx vskill@latest install abanoub-ashraf/manus-skills-import/coderabbit-skillSKILL.md
CodeRabbit CLI Guide
Installation
macOS / Linux
Auth & Setup
CLI Commands Reference
Core Commands
| Command | Description | |
|---|---|---|
coderabbit review | Review staged changes (default) | |
coderabbit review --all | Review all uncommitted changes | |
coderabbit review --commit <hash> | Review a specific commit | |
coderabbit review --branch <name> | Review changes on a branch | |
coderabbit review --files <paths> | Review specific files | |
coderabbit status | Check review status | |
coderabbit config | View/edit configuration | |
coderabbit login | Authenticate with CodeRabbit | |
coderabbit logout | Log out | |
coderabbit --help | Show all available commands |
Review Modes
| Flag | Description | |
|---|---|---|
--staged | Review only staged changes (default) | |
--all | Review all uncommitted changes | |
--prompt-only | Output review as text (for AI agents) | |
--plain | No interactivity, pure text output | |
--type <scope> | Specify scope: staged, uncommitted, branch | |
--json | Output results in JSON format | |
--verbose | Show detailed output | |
--quiet | Minimal output |
Additional Options
| Flag | Description | |
|---|---|---|
--ignore <pattern> | Ignore files matching pattern | |
--include <pattern> | Only include files matching pattern | |
--severity <level> | Filter by severity (error, warning, info) | |
--max-issues <n> | Limit number of issues reported | |
--timeout <seconds> | Set timeout for review |
Pro Combos
Example Prompts for Claude Code
- Basic Review
"Runcoderabbit review --prompt-onlyand fix any issues found."
Typical Workflow
With Claude Code (Autonomous)
- Prompt Claude Code with your task + CodeRabbit instructions
- Claude Code writes code
- Claude runs
coderabbit review --prompt-only - Claude reads feedback and fixes issues
- Repeat until clean
- Claude commits/opens PR
Result: 98% production-ready code before human review.
Resources
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingcoderabbit-skill/SKILL.md
Popularity
- 7-day trend score
- 5
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/abanoub-ashraf/manus-skills-import/coderabbit-skill)