pr-review-expert
PR Review Expert
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/alirezarezvani/pr-review-expertWhat This Skill Does
The pr-review-expert is a comprehensive code review automation agent designed for engineers who demand high-quality, secure, and maintainable software. Unlike basic linting tools, this skill performs a deep-dive analysis of GitHub PRs and GitLab MRs. It treats every code submission with a rigorous, systematic approach, focusing on blast radius analysis, security vulnerabilities, breaking changes, and performance impacts. It automatically parses diffs to check for potential breaking changes in API contracts or database schemas, audits for security flaws like SQL injections and secret leaks, and evaluates whether the test coverage meets the requirements of the changes. By producing a reviewer-ready, 30+ item checklist, it helps teams catch critical defects before they reach production, effectively acting as an automated Senior Staff Engineer.
Installation
To integrate the PR Review Expert into your OpenClaw environment, execute the following command in your terminal:
clawhub install openclaw/skills/skills/alirezarezvani/pr-review-expert
Ensure that your environment has the necessary CLI tools configured (GitHub CLI gh or GitLab CLI glab) and that your authenticated session has read access to the target repository. Once installed, the agent will hook into your workflows, allowing you to fetch diffs, perform static analysis, and generate reports on demand.
Use Cases
This skill is essential in high-stakes engineering environments, particularly when handling shared libraries, public-facing APIs, or complex database migrations. It is the perfect tool for auditing large PRs exceeding 200 lines, ensuring that new contributors follow best practices, and validating high-security areas like authentication or payment gateways. Use this tool proactively after an incident to perform a retrospective analysis of similar code paths to prevent regression.
Example Prompts
- "@pr-review-expert Review PR #442. Pay special attention to potential N+1 query issues in the user repository layer and check for any breaking changes to the /v1/auth API contract."
- "@pr-review-expert Perform a full blast radius analysis on PR #982. Identify all services that depend on the modified shared logging module and verify that test coverage for the edge cases has increased accordingly."
- "@pr-review-expert Analyze the security posture of PR #105. Check for any exposed secrets, improper input validation, or SQL injection vectors in the new billing service endpoint."
Tips & Limitations
To get the best results, ensure your PR descriptions are informative, as the agent correlates existing ticket metadata with the code diff. While the skill is powerful, it should be treated as a technical assistant; human oversight is always recommended for architectural decisions. Note that the agent relies on local file-read access to perform cross-file dependency analysis; ensure your execution environment has permission to read the source code tree. Large repositories may require additional timeout allowances for the agent to complete a full blast-radius scan.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-alirezarezvani-pr-review-expert": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-read, external-api
Related Skills
chro-advisor
People leadership for scaling companies. Hiring strategy, compensation design, org structure, culture, and retention. Use when building hiring plans, designing comp frameworks, restructuring teams, managing performance, building culture, or when user mentions CHRO, HR, people strategy, talent, headcount, compensation, org design, retention, or performance management.
autoresearch-agent
Autonomous experiment loop that optimizes any file by a measurable metric. Inspired by Karpathy's autoresearch. The agent edits a target file, runs a fixed evaluation, keeps improvements (git commit), discards failures (git reset), and loops indefinitely. Use when: user wants to optimize code speed, reduce bundle/image size, improve test pass rate, optimize prompts, improve content quality (headlines, copy, CTR), or run any measurable improvement loop. Requires: a target file, an evaluation command that outputs a metric, and a git repo.
change-management
Framework for rolling out organizational changes without chaos. Covers the ADKAR model adapted for startups, communication templates, resistance patterns, and change fatigue management. Handles process changes, org restructures, strategy pivots, and culture changes. Use when announcing a reorg, switching tools, pivoting strategy, killing a product, changing leadership, or when user mentions change management, change rollout, managing resistance, org change, reorg, or pivot communication.
ab-test-setup
When the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "conversion experiment," "statistical significance," or "test this." For tracking implementation, see analytics-tracking.
copywriting
When the user wants to write, rewrite, or improve marketing copy for any page — including homepage, landing pages, pricing pages, feature pages, about pages, or product pages. Also use when the user says "write copy for," "improve this copy," "rewrite this page," "marketing copy," "headline help," or "CTA copy." For email copy, see email-sequence. For popup copy, see popup-cro.