An automated senior-level code review assistant for Bitbucket Pull Requests that identifies bugs, security risks, and style violations.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install pr-code-reviewer
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install pr-code-reviewer using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
The PR Code Reviewer is a robust tool designed to function as an automated Senior Code Reviewer within your development pipeline. By leveraging Openclaw Skills, this tool scans Pull Request diffs to identify syntax errors, security vulnerabilities, and violations of team-specific coding standards. It supports a wide range of languages including JavaScript, TypeScript, PHP, and Python, ensuring that only high-quality code reaches your production branches.
This skill doesn't just point out errors; it provides context and actionable suggestions. It mimics the behavior of a human reviewer by understanding the overall intent of the changes rather than just looking at lines in isolation. Utilizing Openclaw Skills for your code reviews reduces the manual burden on lead developers and increases the overall velocity of the engineering team.
To integrate this skill into your environment, ensure you have the necessary reference files available in your project structure.
# Move the skill definition to your active skills folder
mv pr-code-reviewer.md ./.agent/skills/
# Ensure your reference markdown files are in place
mkdir -p references
# Add your team-conventions.md and security.md to the references directory
Configure your Openclaw Skills runner to trigger the PR Code Reviewer whenever a new diff is provided by your CI/CD pipeline or manual input.
The PR Code Reviewer organizes its analysis into a clear, hierarchical format to make reviews easy to digest:
| Component | Description |
|---|---|
| Verdict | The final status: Approve, Approve with Changes, or Reject. |
| Summary Stats | Counts of findings categorized as Blocker, Warning, Suggestion, or Nit. |
| File Path | The specific location of the finding in the repository. |
| Diff Comparison | Side-by-side view of the problematic code vs. the suggested improvement. |
| Reasoning | A technical justification explaining the 'why' behind each suggestion. |
Loading
A high-speed Google search integration that extracts full-text web content for comprehensive AI research.

A high-performance search skill that retrieves Google results and extracts full-page readable text for deep context research.

A lightweight RSS aggregator that fetches real-time headlines across news, gaming, and finance categories without requiring external API keys.

A macOS-native command-line interface for the Drafts app that enables programmatic note management and workflow automation.

A real-time communication platform where AI agents engage in live conversation while humans observe the stream.

A professional automation skill for creating, editing, and exporting Google Slides presentations via CLI and Python scripts.








































