OpenParable
Skip to content
← Back to skills

Coderabbit Hello World

Apps & Automation
coderabbit-hello-world

Coderabbit Hello World is an Agent Skill for apps & automation published in the jeremylongshore/claude-code-plugins-plus-skills repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Create a minimal working CodeRabbit configuration and trigger your first AI review. Use when starting with CodeRabbit, testing your setup, or learning basic .coderabbit.yaml patterns. Trigger with phrases like "coderabbit hello world", "coderabbit example", "coderabbit quick start", "first coderabbit review".

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/jeremylongshore/claude-code-plugins-plus-skills/blob/HEAD/plugins/saas-packs/coderabbit-pack/skills/coderabbit-hello-world/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/coderabbit-hello-world, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

CodeRabbit Hello World

Overview

Minimal working example demonstrating CodeRabbit AI code review. CodeRabbit reviews PRs automatically via a GitHub/GitLab App -- no SDK or API calls needed. You configure behavior through a .coderabbit.yaml file and interact via PR comments.

Prerequisites

  • CodeRabbit GitHub App installed (see coderabbit-install-auth)
  • A repository with at least one branch

Instructions

Step 1: Create Minimal Configuration

# .coderabbit.yaml (repository root)
language: "en-US"
reviews:
  profile: "assertive"
  high_level_summary: true
  auto_review:
    enabled: true
    drafts: false
chat:
  auto_reply: true

Step 2: Add Path-Specific Instructions

# .coderabbit.yaml - add review context for better feedback
reviews:
  profile: "assertive"
  high_level_summary: true
  auto_review:
    enabled: true
    drafts: false
  path_instructions:
    - path: "src/**/*.ts"
      instructions: "Check for proper TypeScript types. Flag any use of `any`."
    - path: "**/*.test.*"
      instructions: "Verify edge cases are covered. Check async handling."
chat:
  auto_reply: true

Step 3: Create a PR to Trigger Review

set -euo pipefail
git checkout -b feat/hello-coderabbit

# Add the configuration file
cat > .coderabbit.yaml << 'YAML'
language: "en-US"
reviews:
  profile: "assertive"
  high_level_summary: true
  auto_review:
    enabled: true
    drafts: false
  path_instructions:
    - path: "src/**"
      instructions: "Check for proper error handling and input validation."
chat:
  auto_reply: true
YAML

git add .coderabbit.yaml
git commit -m "feat: add CodeRabbit AI code review configuration"
git push -u origin feat/hello-coderabbit
gh pr create --title "feat: enable CodeRabbit AI code review" \
  --body "Adding .coderabbit.yaml for automated code reviews"

Step 4: Interact with CodeRabbit on the PR

Once CodeRabbit posts its review (typically 2-5 minutes), you can interact:

# In a PR comment, use these commands:
@coderabbitai summary        # Get a walkthrough of all changes
@coderabbitai full review    # Re-run a complete review from scratch
@coderabbitai resolve        # Mark all CodeRabbit comments as resolved
@coderabbitai help           # List all available commands

# Reply to any CodeRabbit comment to have a conversation about the feedback
# CodeRabbit will respond with context-aware explanations

Step 5: Try the CLI for Local Reviews (Optional)

set -euo pipefail
# Review staged changes before committing
git add -A
cr review

# Review with interactive mode for back-and-forth discussion
cr review --interactive

# Review specific files
cr review src/index.ts src/utils.ts

What CodeRabbit Posts on Your PR

  1. Walkthrough comment: High-level summary of all changes with a file-by-file breakdown
  2. Sequence diagram: Visual control flow of the changes (if enabled)
  3. Line-level comments: Specific suggestions on individual code lines
  4. Review status: Approved or changes-requested based on severity of findings

Output

  • .coderabbit.yaml committed to repository root
  • First AI review posted on a test PR within 2-5 minutes
  • Interactive review conversation demonstrated

Error Handling

IssueCauseSolution
No review appearsApp not installed on this repoCheck GitHub App > Repository access
YAML syntax errorInvalid configurationValidate YAML at yamlchecker.com
Review on wrong branchMissing base_branches filterAdd base_branches: [main] to config
Bot not responding to commandsTypo in mentionMust use exact @coderabbitai mention

Resources

Next Steps

Proceed to coderabbit-local-dev-loop for a full development workflow with CodeRabbit.