Proactive Review Workflow
Automate multi-pass code review across quality, security, and performance dimensions
Best use case
Proactive Review Workflow is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Automate multi-pass code review across quality, security, and performance dimensions
Teams using Proactive Review Workflow should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/proactive-review-workflow/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How Proactive Review Workflow Compares
| Feature / Agent | Proactive Review Workflow | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Automate multi-pass code review across quality, security, and performance dimensions
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
Cursor vs Codex for AI Workflows
Compare Cursor and Codex for AI coding workflows, repository assistance, debugging, refactoring, and reusable developer skills.
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
SKILL.md Source
# Proactive Review Workflow Skill Automate multi-pass code review across quality, security, and performance dimensions. ## Trigger Conditions - PR opened or updated - Merge event - User invokes with "proactive review" or "full review" ## Input Contract - **Required:** PR diff or file changes - **Optional:** Review focus areas, prior review comments ## Output Contract - Multi-dimensional review report (quality, security, performance) - Categorized findings (blocking, suggestion, nit) - Post-merge validation results ## Tool Permissions - **Read:** PR diffs, source code, test files, configs - **Write:** Review comments, review reports - **Search:** Related code and patterns ## Execution Steps 1. Analyze PR diff for scope and affected components 2. Run quality pass (complexity, naming, error handling, dead code) 3. Run security pass (injection, auth, secrets, dependencies) 4. Run performance pass (N+1 queries, unbounded collections, missing indexes) 5. Categorize findings: blocking (must fix), suggestion (consider), nit (style) 6. Run post-merge validation on merged result 7. Generate review report ## Success Criteria - All three dimensions reviewed (quality, security, performance) - Findings categorized by severity - No blocking findings remain unresolved - Post-merge validation passes ## Escalation Rules - Escalate if PR is >400 lines (diminishing review quality) - Escalate if Critical security finding detected - Escalate if architectural drift detected ## Example Invocations **Input:** "Run proactive review on PR #42" **Output:** Review: 3 files, 89 lines changed. Quality: 1 suggestion (extract helper function). Security: 1 blocking (SQL injection in search query — use parameterized query). Performance: 1 suggestion (add index for new WHERE clause). Post-merge: clean, no composition errors.
Related Skills
prisma-workflow
Prisma workflow for schema changes, migrations, and common pitfalls in this repo.
performing-code-reviews
Use when reviewing code for quality, security, and maintainability. Enforces verification tooling as table stakes, loads skill-based review lenses, and produces structured actionable output.
performance-testing-review-multi-agent-review
Use when working with performance testing review multi agent review
performance-testing-review-ai-review
You are an expert AI-powered code review specialist combining automated static analysis, intelligent pattern recognition, and modern DevOps practices. Leverage AI tools (GitHub Copilot, Qodo, GPT-5, C
parallel-workflows
Optimizes parallel execution of multiple tasks. Use when user mentions 並列で実行, 同時にやって, まとめてやって, run in parallel, do these together. Do NOT load for: 単一タスク, 順次実行が必要な作業, 依存関係のあるタスク.
osf-workflow-integrator
Skill for integrating with Open Science Framework workflows
odoo-code-review
Review Odoo code for correctness, security, performance, and Odoo 18 standards. Use when reviewing Odoo modules, diffs, or pull requests; produce a scored report with weighted criteria.
nextjs-code-reviewer
code reviews. Use when Codex needs this specialist perspective or review style.
n8n-workflow
Create, modify, and understand n8n automation workflows. Use when building n8n workflow JSON files, configuring nodes (HTTP Request, Code, IF, Merge, Webhook, Schedule), writing expressions with {{ $json }}, or implementing flow logic (conditionals, loops, error handling). Triggers for requests involving n8n, workflow automation, or node-based pipeline creation.
n8n-workflow-patterns
Proven workflow architectural patterns from real n8n workflows. Use when building new workflows, designing workflow structure, choosing workflow patterns, planning workflow architecture, or asking about webhook processing, HTTP API integration, database operations, AI agent workflows, or scheduled tasks.
n8n-workflow-automation
Build no-code/low-code automation workflows for construction using n8n. Automate data extraction, cost estimation, report generation, and system integrations without writing code.
n8n-workflow-architect
Strategic automation architecture advisor. Use when users want to plan automation solutions, evaluate their tech stack (Shopify, Zoho, HubSpot, etc.), decide between n8n vs Python/Claude Code, or need guidance on production-ready automation design. Invokes plan mode for complex architectural decisions.