automation-refactor

Automation Refactor

Expert system for refactoring and optimizing automation workflows across multiple platforms while maintaining functional equivalence and improving code quality.

Supported Platforms

• Power Automate (Microsoft)
• n8n (Open-source automation)
• Make (formerly Integromat)
• Zapier
• Other JSON-based workflow platforms

Purpose

This skill provides comprehensive workflow refactoring by:

1. Analyzing existing workflow JSON for improvement opportunities
2. Applying platform-specific best practices from documentation (Docs/ directory)
3. Optimizing performance, reliability, and maintainability
4. Generating refactored JSON that maintains original functionality
5. Providing detailed report of changes and additional optimization suggestions
6. Ensuring no hallucinations by strictly referencing platform documentation

Common Pitfalls to AVOID

❌ CRITICAL ERROR #1: Assuming Data Structures (Most Common!)

The Mistake:

// You see a variable used in a filter
"where": "@contains(item(), 'keyword')"

// And you ASSUME it's an array of objects, so you write:
"value": "@items('Loop')?['PropertyName']"  // ← WRONG!

The Reality:

// item() without property → Array of STRINGS!
// Correct usage:
"value": "@items('Loop')"  // ← RIGHT!

How to Avoid:

1. ALWAYS look at the filter's where clause first
2. item() = array of primitives (strings/numbers)
3. item()?['Prop'] = array of objects
4. Ask user if unsure - never guess!

---

❌ ERROR #2: Not Researching Documentation

The Mistake: Guessing connector outputs, property names, or behaviors

How to Avoid:

1. Search local Docs/ directory FIRST
2. Use WebSearch for official docs if not found locally
3. Ask user to confirm if documentation is unclear
4. Reference specific documentation sections in your output

---

❌ ERROR #3: Overconfidence Without Validation

The Mistake: Providing fixes without verifying against actual data structures