Skip to content
Agent Orchestration
Skill

/coderabbit-review

Unified CodeRabbit CLI execution via WSL with self-healing loop. Use this skill when running automated code review before commits, PRs, or QA gates. Handles WSL wrapper, severity filtering, and auto-fix iterations.

From plugin
aiox-core
3.1k27 skills18 agents24 commands

Claude Code

$ npx -y skills add SynkraAI/aiox-core --skill coderabbit-review --agent claude-code

SKILL.md

coderabbit-review.SKILL.md
name: coderabbit-review
description: |
  Unified CodeRabbit CLI execution via WSL with self-healing loop.
  Use this skill when running automated code review before commits, PRs, or QA gates.
  Handles WSL wrapper, severity filtering, and auto-fix iterations.
user-invocable: true
argument-hint: "[scope: uncommitted|committed|base]"

CodeRabbit Review

Centralized CodeRabbit CLI execution for automated code review via WSL.

Prerequisites

  • CodeRabbit CLI installed in WSL at `~/.local/bin/coderabbit`
  • WSL distribution: Ubuntu
  • Authenticated: `wsl bash -c '~/.local/bin/coderabbit auth status'`

Execution

1. Determine Scope

Parse `$ARGUMENTS` to determine review scope:

| Argument | Command | Use Case | |----------|---------|----------| | `uncommitted` (default) | `--prompt-only -t uncommitted` | Pre-commit review | | `committed` | `--prompt-only -t committed --base main` | QA story review | | `base {branch}` | `--prompt-only --base {branch}` | Pre-PR review against specific base |

2. Build WSL Command

wsl bash -c 'cd /mnt/c/path/to/aiox-core && ~/.local/bin/coderabbit {flags}'

**Timeout:** 15 minutes (900000ms) — CodeRabbit reviews take 7-30 min.

3. Execute Review

Run the command via Bash tool with appropriate timeout.

4. Parse Results

Classify findings by severity:

| Severity | Action | |----------|--------| | **CRITICAL** | Must fix immediately — blocks completion | | **HIGH** | Recommend fix before merge | | **MEDIUM** | Document as technical debt | | **LOW** | Optional improvement, note only |

5. Self-Healing Loop (if CRITICAL found)

iteration = 0
max_iterations = agent-specific (dev: 2, qa: 3, devops: 2)

WHILE iteration < max_iterations AND critical_issues_remain:
  1. Attempt auto-fix for each CRITICAL issue
  2. Re-run CodeRabbit review
  3. iteration++

IF critical_issues_remain after max_iterations:
  HALT and report to user

6. Report

Output a summary table:

## CodeRabbit Review Results

| Severity | Count | Status |
|----------|-------|--------|
| CRITICAL | N | Fixed/Remaining |
| HIGH | N | Documented |
| MEDIUM | N | Tech debt |
| LOW | N | Noted |

**Decision:** PASS / FAIL

Error Handling

| Error | Cause | Resolution | |-------|-------|------------| | `coderabbit: command not found` | Not installed in WSL | `wsl bash -c 'pip install coderabbit-cli'` | | Timeout (>15 min) | Large review | Increase timeout, review is still processing | | `not authenticated` | Auth expired | `wsl bash -c '~/.local/bin/coderabbit auth status'` |

Agent-Specific Configuration

| Agent | Max Iterations | Severity Filter | Trigger | |-------|---------------|-----------------|---------| | @dev | 2 | CRITICAL only | Pre-commit (story completion) | | @qa | 3 | CRITICAL + HIGH | Story review start | | @devops | 2 | CRITICAL + HIGH | Pre-push / Pre-PR |

Report Location

Save reports to: `docs/qa/coderabbit-reports/`

Read more
@synkraai
Ships withaiox-core

🌐 README por idioma: EN | PT | ES | ZH Devolvendo às pessoas o poder de criar — Framework open source de orquestração de IA que devolve o controle a quem tem coragem de construir.

3.1k27 skills18 agents
Get the whole plugin

Stars on GitHub

Momentum

stars in total
3.1k
Star history of SynkraAI/aiox-core on GitHub, a chart by star-history.com

Other skills on aiox-core.

aiox-master

aiox-master

Activate Orion (aiox-master) for AIOX Master Orchestrator & Framework Developer. Use when you need comprehensive expertise across…

@synkraai@synkraaiInstall Skill
analyst

analyst

Activate Atlas (analyst) for Business Analyst. Use for market research, competitive analysis, user research, brainstorming…

@synkraai@synkraaiInstall Skill
architect

architect

Activate Aria (architect) for Architect. Use for system architecture (fullstack, backend, frontend, infrastructure), technology…

@synkraai@synkraaiInstall Skill
data-engineer

data-engineer

Activate Dara (data-engineer) for Database Architect & Operations Engineer. Use for database design, schema architecture,…

@synkraai@synkraaiInstall Skill
dev

dev

Activate Dex (dev) for Full Stack Developer. Use for code implementation, debugging, refactoring, and development best practices

@synkraai@synkraaiInstall Skill
devops

devops

Activate Gage (devops) for GitHub Repository Manager & DevOps Specialist. Use for repository operations, version management,…

@synkraai@synkraaiInstall Skill

More skills from other plugins.

1password

1password

Set up and use 1Password CLI for sign-in, desktop integration, and reading or injecting secrets.

clawdis11d393k
@steipete@steipeteInstall Skill
computer-use

computer-use

Drives the GUI of a visible local app window through `orca computer`: accessibility tree, clicks, typing, menus, dialogs, and…

orca11d111k
@stablyai@stablyaiInstall Skill
agentmail

agentmail

Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by…

paperclip11d109k
@paperclipai@paperclipaiInstall Skill
adr-create

adr-create

Create a new Architecture Decision Record with sequential numbering and AgentDB registration

@ruvnet@ruvnetInstall Skill

Questions about coderabbit-review.

Which coding agents can use coderabbit-review?
coderabbit-review installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.