whole codebase refactor manager

The problem

Large-scale refactoring across multiple modules often leads to broken imports, missing files, and inconsistent patterns when handled manually. Developers struggle to maintain focus and verification standards when migrating conventions or deleting features across dozens of files.

What it does

• Scans codebase architecture and dependencies to map out cross-module relationships.
• Generates a comprehensive, file-by-file change plan with associated risk assessments.
• Executes changes in parallel by splitting tasks across multiple agent sections based on layers.
• Runs local test suites and application startup checks to verify the integrity of the refactor.
• Provides a detailed plan-versus-actual report highlighting every modification and regression.

Frameworks & tools

Compatible with any Git-based repository. Automatically detects and adapts to React, Vue, and various backend service frameworks.

Why this beats prompting it yourself

Standard LLM prompts often lose context or hallucinate when dealing with wide-reaching architectural changes. This skill enforces a strict multi-step workflow of analysis, planning, and verification that prevents the "partial refactor" trap common in manual sessions.

Use cases

• Adding unique test IDs across all UI components for automated testing.
• Safely deleting deprecated features and their associated dependencies across services.
• Migrating naming conventions or API patterns throughout a large codebase.
• Reorganizing directory structures and updating all affected relative imports.