pr-reviewer
Automated GitHub PR code review with diff analysis, lint integration, and structured reports. Use when reviewing pull requests, checking for security issues, error handling gaps, test coverage, or code style problems. Supports Go, Python, and JavaScript/TypeScript. Requires `gh` CLI authenticated with repo access.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/briancolinger/pr-reviewerWhat This Skill Does
The pr-reviewer skill acts as an automated security and code quality auditor for GitHub repositories. By integrating directly with the gh CLI, it performs deep analysis of pull request diffs, cross-referencing changes against industry standards for security, error handling, and maintainability. It effectively acts as a persistent pair programmer that never gets tired, ensuring that common pitfalls—such as hardcoded credentials, unchecked errors in Go, or broad except blocks in Python—are flagged before human intervention is even required. Beyond simple linting, it tracks PR state to provide smart re-reviews, only alerting developers when new code has been pushed to a branch, which helps reduce noise in fast-moving development environments.
Installation
To integrate this into your workflow, execute the following command in your terminal:
clawhub install openclaw/skills/skills/briancolinger/pr-reviewer
Ensure that you have the GitHub CLI (gh) installed and authenticated with adequate repository permissions. For optimal results, ensure that golangci-lint or ruff are installed on the local system where the agent executes, allowing the agent to perform granular local linting in addition to its automated heuristic-based diff analysis.
Use Cases
This skill is ideal for engineering teams looking to enforce high code standards without manual overhead. It is perfect for:
- Automated pre-review checks: Run it as a cron job or CI task to list and review unapproved PRs.
- Security gatekeeping: Instantly identify secrets or unsafe patterns pushed to feature branches.
- Educational feedback: Helping junior developers understand error handling and testing gaps by providing structured, actionable feedback.
- Maintaining legacy codebases: Flagging unchecked errors or inconsistent style markers like TODOs and HACKs.
Example Prompts
- "Hey, can you run a review on PR #42 and post the findings as a comment?"
- "Check all currently open PRs in the repository and list the ones that haven't been reviewed yet.",
- "Perform a deep scan on the latest commit in PR #105, focusing specifically on error handling and potential security vulnerabilities."
Tips & Limitations
The pr-reviewer is highly effective but works best when the repository environment is correctly configured. Always ensure the PR_REVIEW_OUTDIR is accessible for tracking purposes. Note that while the tool supports Go, Python, and JavaScript/TypeScript, its effectiveness scales with the strictness of your local linting tools. If you use custom linting configurations, ensure they are present in the root directory for the script to pick them up. Finally, remember that the tool is a static analysis aid; it does not replace human logic, especially for complex architectural reviews.
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-briancolinger-pr-reviewer": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access, file-write, file-read, external-api
Related Skills
email-triage
IMAP email scanning and triage with AI classification via a local Ollama LLM. Scans unread emails, categorizes them as urgent, needs-response, informational, or spam, and surfaces important messages for agent consumption. Works standalone with heuristic fallback — Ollama optional but recommended.
dreaming
Creative exploration during quiet hours. Turns idle heartbeat time into freeform thinking — hypotheticals, future scenarios, reflections, unexpected connections. Use when you want your agent to do something meaningful during low-activity periods instead of just returning HEARTBEAT_OK. Outputs written to files for human review later (like remembering dreams in the morning).
aws-ecs-monitor
AWS ECS production health monitoring with CloudWatch log analysis — monitors ECS service health, ALB targets, SSL certificates, and provides deep CloudWatch log analysis for error categorization, restart detection, and production alerts.