/gemini-review

allowed-tools: Bash(gh:*), Read, Grep, TodoWrite, Edit, MultiEdit
argument-hint: [pr-number] | --analyze-only | --preview | --priority high|medium|low
description: Transform Gemini Code Assist PR reviews into prioritized TodoLists with automated execution
model: claude-sonnet-4-5-20250929

Gemini PR Review Automation

Why This Command Exists

**The Problem**: Gemini Code Assist provides free, automated PR reviews on GitHub. But AI-generated reviews often get ignored because they lack the urgency of human feedback.

**The Pain Point**: Manually asking Claude Code to: 1. "Analyze PR #42's Gemini review" 2. "Prioritize the issues" 3. "Create a TodoList" 4. "Start working on them"

...gets tedious fast.

**The Solution**: One command that automatically fetches Gemini's review, analyzes severity, creates prioritized TodoLists, and optionally starts execution.

What Makes This Different

| | Code Analysis | Code Improvement | Gemini Review | |---|---|---|---| | **Trigger** | When you want analysis | When you want improvements | **When Gemini already reviewed** | | **Input** | Local codebase | Local codebase | **GitHub PR's Gemini comments** | | **Purpose** | General analysis | General improvements | **Convert AI review → actionable TODOs** | | **Output** | Analysis report | Applied improvements | **TodoList + Priority + Execution** |

Triggers

• PR has Gemini Code Assist review comments waiting to be addressed
• Need to convert AI feedback into structured action items
• Want to systematically process automated review feedback
• Reduce manual context switching between GitHub and development

Usage

/gemini-review [pr-number] [--analyze-only] [--preview] [--priority high|medium|low]

Behavioral Flow

1. **Fetch**: Retrieve PR details and Gemini review comments using GitHub CLI 2. **Analyze**: Parse and categorize review comments by type and severity 3. **Prioritize**: Assess each comment for refactoring necessity and impact 4. **TodoList**: Generate structured TodoList with priority ordering 5. **Execute**: (Optional) Start working on high-priority items with user confirmation

Key behaviors:

• Intelligent comment categorization (critical, improvement, suggestion, style)
• Impact assessment for each review item with effort estimation
• Automatic TodoList creation with priority matrix (must-fix, should-fix, nice-to-have)
• Code location mapping and dependency analysis
• Implementation strategy with phased approach

Tool Coordination

• **Bash**: GitHub CLI operations for PR and review data fetching
• **Sequential Thinking**: Multi-step reasoning for complex refactoring decisions
• **Grep**: Code pattern analysis and issue location identification
• **Read**: Source code inspection for context understanding
• **TodoWrite**: Automatic TodoList generation with priorities
• **Edit/MultiEdit**: Code modifications when executing fixes

Key Patterns

• **Review Parsing**: Gemini comments → structured analysis data
• **Severity Classification**: Comment type → priority level assignment (Must-fix/Should-fix/Nice-to-have/Skip)
• **TodoList Generation**: Analysis results → TodoWrite with prioritized items
• **Impact Analysis**: Code changes → ripple effect assessment
• **Execution Planning**: Strategy → actionable implementation steps

Examples

Analyze Current Branch's PR

/gemini-review
# Automatically detects current branch's PR
# Generates prioritized TodoList from Gemini review
# Ready to execute after user confirmation

Analyze Specific PR

/gemini-review 42
# Analyzes Gemini review comments on PR #42
# Creates prioritized TodoList with effort estimates

Preview Mode (Safe Execution)

/gemini-review --preview
# Shows what would be fixed without applying changes
# Creates TodoList for manual execution
# Allows review before implementation

Real Workflow Example

**Before (Manual, Tedious)**:

1. Open GitHub PR page
2. Read Gemini review (often skipped because "AI generated")
3. Tell Claude: "Analyze PR #42 Gemini review"
4. Tell Claude: "Prioritize these issues"
5. Tell Claude: "Create TodoList"
6. Tell Claude: "Start working on them"

**After (Automated)**:

/gemini-review 42
# → TodoList automatically created
# → Priorities set based on severity
# → Ready to execute immediately

Analysis Output Structure

1. Review Summary

• Total comments count by severity
• Severity distribution (critical/improvement/suggestion/style)
• Common themes and patterns identified
• Overall review sentiment and key focus areas
• Estimated total effort required

2. Categorized Analysis

For each review comment:

• **Category**: Critical | Improvement | Suggestion | Style
• **Location**: File path and line numbers with context
• **Issue**: Description of the problem from Gemini
• **Impact**: Potential consequences if unaddressed
• **Decision**: Must-fix | Should-fix | Nice-to-have | Skip
• **Reasoning**: Why this priority was assigned
• **Effort**: Estimated implementation time (Small/Medium/Large)

3. TodoList Generation

**Automatically creates TodoList with user confirmation before execution**

High Priority (Must-Fix):
✓ Fix SQL injection in auth.js:45 (15 min)
✓ Remove exposed API key in config.js:12 (5 min)

Medium Priority (Should-Fix):
○ Refactor UserService complexity (45 min)
○ Add error handling to payment flow (30 min)

Low Priority (Nice-to-Have):
○ Update JSDoc comments (20 min)
○ Rename variable for clarity (5 min)

Skipped:
- Style suggestion conflicts with project standards
- Already addressed in different approach

*Note: User reviews and confirms TodoList before any code modifications are made*

4. Execution Plan

• **Phase 1 - Critical Fixes**: Security and breaking issues (immediate)
• **Phase 2 - Important Improvements**: Maintainability and performance (same PR)
• **Phase 3 - Optional Enhancements**: Style and documentation (future PR)
• **Dependencies**: Order of impl