skills.rest
blake-goodwyn
blake-goodwynCOMMUNITY
Explore all skills by this author →
GitHub

pr-review

Automate pull request code review with confidence-scored issues.

Updated Jan 22, 2026
Search Tags:#automation#multi-agent#CLAUDE.md#code-review#pull-request#pr-review#confidence-score
One-click install
npx skills add https://github.com/blake-goodwyn/sloppy-pancakes --skill pr-review-blake-goodwyn
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: pr-review
Source: https://github.com/blake-goodwyn/sloppy-pancakes/tree/main/.claude/skills/pr-review
Command: npx skills add https://github.com/blake-goodwyn/sloppy-pancakes --skill pr-review-blake-goodwyn

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill automates code review for pull requests by providing a structured, multi-agent assessment that enforces CLAUDE.md compliance and accelerates feedback.

Core Features & Use Cases

  • Multi-agent parallel review: Launches five independent reviewers to analyze a PR for bugs and quality issues.
  • CLAUDE.md compliance checking: Ensures documentation alignment and project standards.
  • Confidence scoring: Issues are scored on a 0-100 scale to prioritize fixes.
  • Configurable threshold: Filter and report only high-confidence issues based on a user-defined threshold.
  • Use Case: When a PR is opened in run-milestone, run /pr-review <PR_NUMBER> to automatically surface actionable findings.

Quick Start

  • Invoke the skill with a PR number: /pr-review 123

Frequently Asked Questions about pr-review

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate pull request code reviews to enforce project documentation compliance?▼

Automated pull request code reviews enforce project documentation compliance by checking new PRs against CLAUDE.md standards. A multi-agent system launches five parallel reviewers to analyze code and surface findings that align with your project's specific rules.

What is confidence scoring in automated code review and how does it filter issues?▼

Confidence scoring in automated code review rates identified issues on a 0-100 scale to prioritize fixes. A configurable threshold filters the output so that only high-confidence findings are reported, reducing noise and focusing developer attention on actionable bugs.

How do I run a multi-agent code review on a specific pull request number?▼

To run a multi-agent code review on a specific pull request, invoke the /pr-review command followed by the PR number. This triggers five independent reviewers to analyze the PR for bugs and quality issues within the run-milestone workflow.

Can I use multi-agent PR review within an automated milestone workflow?▼

Yes, multi-agent PR review operates within the run-milestone workflow to automatically review newly created PRs. It assesses code quality and enforces documentation standards without requiring manual invocation for every new pull request.

What is the best way to reduce noise in automated PR code reviews?▼

The best way to reduce noise in automated PR code reviews is to configure a high confidence score threshold. By setting this filter, the review system only reports issues that meet a strict confidence level, ignoring low-probability findings and minimizing false positives.

Do I need external dependencies to run multi-agent code reviews with confidence scoring?▼

No external dependencies are required to run multi-agent code reviews with confidence scoring. The skill operates independently using its internal five-agent parallel review system and configurable threshold logic to evaluate pull requests.

Related Skills

Explore More Software Engineering Skills→
alessioroberto82alessioroberto82

code-review

Audit GitHub pull requests for bugs and security vulnerabilities.

Community
Advanced
SantiagoisperSantiagoisper

ce-code-review

Automate code review with confidence-gated findings and autofix capabilities.

Community
Advanced
All-The-VibesAll-The-Vibes
50

land

Commit changes, push to the remote, and open a pull request for handoff.

Official
Advanced
inbharataiinbharatai
22

code-reviewer

Analyzes code for bugs, security vulnerabilities, performance bottlenecks, and style violations.

Community
Advanced