CO

coderabbit-reference-architecture

Provides a standard configuration and architecture template for integrating CodeRabbit into development workflows.

Install

mkdir -p .claude/skills/coderabbit-reference-architecture && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/2404" && unzip -o skill.zip -d .claude/skills/coderabbit-reference-architecture && rm skill.zip

Installs to .claude/skills/coderabbit-reference-architecture

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Implement CodeRabbit reference architecture with production-grade .coderabbit.yaml
82 charsno explicit “when” trigger
Intermediate

Key capabilities

  • Configure CodeRabbit for production teams
  • Define path-specific review instructions
  • Integrate CodeRabbit into CI pipelines
  • Generate a team onboarding document
  • Customize review behavior and automatic triggers

How it works

This skill provides a reference architecture for CodeRabbit AI code review, including configuration files, path-specific instructions, and CI pipeline integration patterns. It generates a starting template that can be customized for a team's specific needs.

Inputs & outputs

You give it
CodeRabbit configuration requirements, project structure, and desired review behaviors
You get back
A complete .coderabbit.yaml file, path instruction templates, CI integration, and a team onboarding document

When to use coderabbit-reference-architecture

  • Designing new CodeRabbit integrations
  • Reviewing project structure standards
  • Establishing AI-driven code review config
  • Setting up CI pipeline reviews

About this skill

CodeRabbit Reference Architecture

Overview

Complete reference architecture for CodeRabbit AI code review in a production team. Covers the full configuration file, path-specific review instructions per project type, tool integrations, CI pipeline integration, and the review lifecycle. Use this as a starting template and customize for your team.

Architecture Diagram

Developer pushes code
         │
         ▼
┌─────────────────────────┐
│     Pull Request        │
│  (targets base branch)  │
└─────────┬───────────────┘
          │
          ▼
┌─────────────────────────┐
│   CodeRabbit AI Review  │
│  Reads: .coderabbit.yaml│
│  from base branch       │
│                         │
│  Outputs:               │
│  ├── Walkthrough summary│
│  ├── Sequence diagrams  │
│  ├── Line-level comments│
│  └── Review state       │
└─────────┬───────────────┘
          │
    ┌─────┴──────┐
    │            │
    ▼            ▼
┌────────┐  ┌────────────┐
│ APPROVED│  │ CHANGES    │
│         │  │ REQUESTED  │
└────┬───┘  └─────┬──────┘
     │            │
     ▼            ▼
  Merge      Developer fixes
  (if branch   and pushes
  protection   (incremental
  passes)      re-review)

Instructions

Step 1: Full Reference Configuration

# .coderabbit.yaml - Production Reference Architecture
# Copy this file and customize for your project.

language: "en-US"
early_access: false

# Tone customization
tone_instructions: |
  Be concise and direct. Use bullet points for multiple suggestions.
  Include code examples for non-obvious fixes.
  Rate severity: Critical > Warning > Suggestion > Nitpick.

reviews:
  # Review behavior
  profile: "assertive"
  request_changes_workflow: true
  high_level_summary: true
  high_level_summary_in_walkthrough: true
  review_status: true
  collapse_walkthrough: false
  sequence_diagrams: true
  poem: false

  # Automatic review triggers
  auto_review:
    enabled: true
    drafts: false
    base_branches:
      - main
      - develop
      - "release/*"
    ignore_title_keywords:
      - "WIP"
      - "DO NOT MERGE"
      - "chore: bump"
      - "chore(deps)"

  # File exclusions (skip files with no review value)
  path_filters:
    - "!**/*.lock"
    - "!**/package-lock.json"
    - "!**/pnpm-lock.yaml"
    - "!**/yarn.lock"
    - "!**/*.snap"
    - "!**/*.generated.*"
    - "!**/generated/**"
    - "!dist/**"
    - "!build/**"
    - "!**/*.min.js"
    - "!**/*.min.css"
    - "!vendor/**"
    - "!**/__mocks__/**"
    - "!**/fixtures/**"

  # Path-specific review instructions
  path_instructions:
    # API layer
    - path: "src/api/**"
      instructions: |
        Review for:
        - Input validation on all request parameters
        - Proper HTTP status codes (don't use 200 for errors)
        - Auth middleware applied to protected routes
        - Error response format (consistent structure)
        - Rate limiting on public endpoints
        Flag: missing error handling, unvalidated input, SQL injection

    # Database layer
    - path: "src/db/**"
      instructions: |
        Review for:
        - Parameterized queries (no string concatenation in SQL)
        - Transaction boundaries on multi-table mutations
        - Connection cleanup (no connection leaks)
        - Index usage for complex queries
        Flag: N+1 query patterns, raw SQL with user input

    # Authentication
    - path: "src/auth/**"
      instructions: |
        SECURITY-CRITICAL. Review for:
        - Password hashing (bcrypt/argon2 only, never MD5/SHA)
        - Token expiry configuration
        - Session management and fixation prevention
        - CSRF protection on state-changing operations
        - Brute force protection

    # Frontend components
    - path: "src/components/**"
      instructions: |
        Review for:
        - Accessibility (aria labels, keyboard navigation, screen reader support)
        - Performance (memoization, lazy loading, bundle size impact)
        - Proper state management (no prop drilling beyond 2 levels)
        Ignore: CSS naming conventions, import order

    # Tests
    - path: "**/*.test.*"
      instructions: |
        Review for:
        - Assertion completeness (not just checking status codes)
        - Edge case coverage (null, empty, boundary values)
        - Proper async handling (await, done callbacks)
        - Test isolation (no shared mutable state)
        Do NOT comment on: test naming conventions, import order

    # CI/CD pipelines
    - path: ".github/workflows/**"
      instructions: |
        Review for:
        - Pin action versions to SHA commit hash (not tags)
        - No secrets in step names, echo, or log output
        - timeout-minutes on all jobs
        - Use OIDC for cloud provider auth
        - Minimal permissions on GITHUB_TOKEN

    # Infrastructure
    - path: "**/*.tf"
      instructions: |
        Review for:
        - No hardcoded credentials or keys
        - Encryption enabled on storage and databases
        - Security groups: no 0.0.0.0/0 ingress except 443
        - IAM: least privilege, no wildcard actions

  # Finishing touches (Pro+)
  finishing_touches:
    docstrings:
      enabled: true

  # Linter tool integrations
  tools:
    eslint:
      enabled: true
    biome:
      enabled: true
    shellcheck:
      enabled: true
    markdownlint:
      enabled: true

chat:
  auto_reply: true

Step 2: Project-Specific Templates

Node.js/TypeScript Backend:

# Add to path_instructions:
    - path: "src/middleware/**"
      instructions: "Review for proper error propagation, request/response typing."
    - path: "src/services/**"
      instructions: "Review for dependency injection, proper error handling, testability."
    - path: "prisma/migrations/**"
      instructions: "Verify: backward compatibility, rollback safety, no data loss."

React/Next.js Frontend:

# Add to path_instructions:
    - path: "src/hooks/**"
      instructions: "Review for: cleanup in useEffect, dependency arrays, race conditions."
    - path: "src/pages/**"
      instructions: "Review for: SSR/SSG correctness, SEO meta tags, performance."
    - path: "src/lib/**"
      instructions: "Review for: tree-shaking friendly exports, no side effects."

Python/Django Backend:

# Add to path_instructions:
    - path: "**/*.py"
      instructions: |
        Review for: type hints, proper exception handling, no mutable default args.
        Check: context manager usage, proper async patterns.
    - path: "**/models.py"
      instructions: "Review for: index definitions, migration compatibility, field validation."
    - path: "**/views.py"
      instructions: "Review for: permission classes, serializer validation, query optimization."

Step 3: CI Pipeline Integration

# .github/workflows/pr-checks.yml
name: PR Checks

on:
  pull_request:
    types: [opened, synchronize, reopened]

jobs:
  # Your existing CI checks
  test:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - run: npm ci
      - run: npm test

  # CodeRabbit review gate (optional)
  coderabbit-gate:
    runs-on: ubuntu-latest
    if: github.event.action == 'opened'
    steps:
      - name: CodeRabbit review expected
        uses: actions/github-script@v7
        with:
          script: |
            core.info('CodeRabbit will review this PR automatically.');
            core.info('Reviews typically post within 2-5 minutes.');

Step 4: Team Onboarding Document

# CodeRabbit Quick Reference for Developers

## What happens when you open a PR:
1. CodeRabbit reviews automatically (2-5 min)
2. Posts a walkthrough summary comment
3. Adds line-level suggestions
4. Sets review state (Approved / Changes Requested)

## Commands (post in any PR comment):
@coderabbitai full review       - Re-review all files
@coderabbitai summary           - Regenerate walkthrough
@coderabbitai resolve           - Mark all comments resolved
@coderabbitai generate-docstrings - Auto-generate docstrings
@coderabbitai configuration     - Show active config
@coderabbitai help              - List all commands

## Tips:
- Reply to comments to teach CodeRabbit your preferences
- Add "WIP" to PR title to skip review
- Keep PRs under 500 lines for best review quality
- Use @coderabbitai run <recipe> for finishing touches

Output

  • Complete reference .coderabbit.yaml with all configuration sections
  • Project-specific path instruction templates
  • CI pipeline integration for review gating
  • Team onboarding quick reference document

Error Handling

IssueCauseSolution
Config not appliedYAML syntax errorValidate with python3 -c "import yaml; yaml.safe_load(open('.coderabbit.yaml'))"
Too many commentsProfile too aggressive or no path_instructionsSwitch to chill or add contextual instructions
Reviews on generated filesMissing path_filtersAdd !**/generated/** and similar exclusions
Wrong branch configConfig not on base branchCommit .coderabbit.yaml to the PR's target branch

Resources

Next Steps

For initial setup, see coderabbit-install-auth. For tuning, see coderabbit-core-workflow-b.

Limitations

  • Configuration not applied due to YAML syntax error
  • Reviews on generated files due to missing path_filters
  • Wrong branch config if .coderabbit.yaml is not on the base branch

How it compares

This skill provides a structured, production-grade configuration for CodeRabbit, unlike manually setting up individual review rules.

Compared to similar skills

coderabbit-reference-architecture side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
coderabbit-reference-architecture (this skill)327dReviewIntermediate
resolve-conflicts818moReviewIntermediate
claude-automation-recommender472moReviewBeginner
codex-skill125moReviewAdvanced

Try saying

Example prompts that trigger this skill in your AI assistant.

More by jeremylongshore

View all by jeremylongshore

analyzing-logs

jeremylongshore

Analyze application logs to detect performance issues, identify error patterns, and improve stability by extracting key insights.

14123

ollama-setup

jeremylongshore

Configure auto-configure Ollama when user needs local LLM deployment, free AI alternatives, or wants to eliminate hosted API costs. Trigger phrases: "install ollama", "local AI", "free LLM", "self-hosted AI", "replace OpenAI", "no API costs". Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.

1167

backtesting-trading-strategies

jeremylongshore

Backtest crypto and traditional trading strategies against historical data. Calculates performance metrics (Sharpe, Sortino, max drawdown), generates equity curves, and optimizes strategy parameters. Use when user wants to test a trading strategy, validate signals, or compare approaches. Trigger with phrases like "backtest strategy", "test trading strategy", "historical performance", "simulate trades", "optimize parameters", or "validate signals".

1071

generating-database-seed-data

jeremylongshore

Process this skill enables AI assistant to generate realistic test data and database seed scripts for development and testing environments. it uses faker libraries to create realistic data, maintains relational integrity, and allows configurable data volumes. u... Use when working with databases or data models. Trigger with phrases like 'database', 'query', or 'schema'.

1033

cursor-codebase-indexing

jeremylongshore

Execute set up and optimize Cursor codebase indexing. Triggers on "cursor index setup", "codebase indexing", "index codebase", "cursor semantic search". Use when working with cursor codebase indexing functionality. Trigger with phrases like "cursor codebase indexing", "cursor indexing", "cursor".

885

testing-mobile-apps

jeremylongshore

Execute mobile app testing on iOS and Android devices/simulators. Use when performing specialized testing. Trigger with phrases like "test mobile app", "run iOS tests", or "validate Android functionality".

810

You might also like

resolve-conflicts

antinomyhq

Use this skill immediately when the user mentions merge conflicts that need to be resolved. Do not attempt to resolve conflicts directly - invoke this skill first. This skill specializes in providing a structured framework for merging imports, tests, lock files (regeneration), configuration files, and handling deleted-but-modified files with backup and analysis.

81334

claude-automation-recommender

anthropics

Analyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers). Use when user asks for automation recommendations, wants to optimize their Claude Code setup, mentions improving Claude Code workflows, asks how to first set up Claude Code for a project, or wants to know what Claude Code features they should use.

47140

codex-skill

feiskyer

Use when user asks to leverage codex, gpt-5, or gpt-5.1 to implement something (usually implement a plan or feature designed by Claude). Provides non-interactive automation mode for hands-off task execution without approval prompts.

12110

git-advanced-workflows

wshobson

Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.

1197

subagent-driven-development

davila7

Use when executing implementation plans with independent tasks in the current session

1493

validate-openapi-specs

epieczko

Validates and registers hook manifest files (YAML) in the Hook Registry for versioned hook management.

594

Search skills

Search the agent skills registry