athena-pr-reviewer

Name: athena-pr-reviewer
Availability: InStock
Author: emiperez95

Analyze PR diffs, Jira context, and CLAUDE.md guidelines to generate review artifacts.

Updated Dec 3, 2025

Search Tags:#code quality #code review #parallel processing #pull request #GitHub #hallucination filtering #multi-LLM

Ready to run

npx skills add https://github.com/emiperez95/cc-toolkit --skill athena-pr-reviewer

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: athena-pr-reviewer
Source: https://github.com/emiperez95/cc-toolkit/tree/main/skills/athena-pr-reviewer/skills/athena-pr-reviewer
Command: npx skills add https://github.com/emiperez95/cc-toolkit --skill athena-pr-reviewer

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires gh, acli, rclone, gemini, codex, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill eliminates the time-consuming manual process of code review by orchestrating multiple specialized AI reviewers in parallel, delivering comprehensive feedback in minutes instead of hours.

Core Features & Use Cases

Parallel Multi-LLM Reviews: Runs up to 8 specialized reviewers simultaneously including Claude specialists, Gemini, and Codex.
Hallucination Filtering: Verifies all findings against actual code to eliminate false positives and wasted time.
Use Case: When you have a complex PR with 50+ files changed, Athena automatically gathers context, runs specialized reviewers, and presents only verified, actionable feedback.

Quick Start

Review PR 456 and run all available reviewers to get comprehensive feedback on code quality, tests, errors, and documentation.

Consensus Boosting: Issues flagged by multiple reviewers get priority elevation, ensuring critical problems are addressed first.

Frequently Asked Questions about athena-pr-reviewer

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

FAQPage Schema

How do I automate code review across multiple pull requests on GitHub?▼

Automate code review by orchestrating parallel multi-LLM analysis that gathers PR diffs, Jira context, and CLAUDE.md guidelines to surface actionable feedback. This Skill runs up to 8 specialized reviewers simultaneously—including Claude, Gemini, and Codex—filtering hallucinations against actual code and prioritizing findings flagged by multiple agents.

Can I run parallel code reviews with multiple LLMs on the same PR?▼

Yes. This Skill coordinates parallel reviews from specialized Claude reviewers, Gemini, and Codex agents in a single pass, each analyzing code quality, tests, errors, and documentation. Consensus across reviewers elevates critical issues, and all findings are verified against actual diffs to eliminate false positives.

How do I integrate GitHub and Jira context into automated code reviews?▼

The Skill cross-gathers PR metadata, diffs, Jira tickets, epics, git blame, prior comments, and CLAUDE.md guidelines automatically. It assembles this context into structured artifacts (context.md, pr.json, jira.json) and feeds them to parallel reviewers, ensuring feedback is grounded in full project context.

What does hallucination filtering do in PR reviews?▼

Hallucination filtering verifies all AI-generated review findings against actual code to eliminate false positives. This ensures only accurate, actionable feedback reaches you, reducing wasted time on phantom issues and improving review reliability across large or complex pull requests.

Does this work with large pull requests with 50+ file changes?▼

Yes. This Skill is designed for complex PRs with many files. It dynamically selects specialized reviewers, gathers cross-source context in parallel, runs all agents simultaneously, and presents prioritized, verified feedback—turning comprehensive reviews that would take hours into minutes.

What platforms and tools do I need to use this Skill?▼

You need GitHub for PR management, Jira for ticket context, and the gh CLI for GitHub integration. The Skill also requires acli for Jira, rclone for data transfer, and access to Claude, Gemini, and Codex APIs for multi-LLM review orchestration.