Describe the Data Shape
Claude can't clean data it can't picture.
Where you'll practice this
2 Promptles scenarios teach this principle directly. Each one drops you into a real engineering ticket and asks you to write the prompt you'd send to Claude Code.
The Email Parser
You receive order confirmation emails from a vendor in a consistent format. The email body looks like: 'Order #ORD-12345 confirmed. Amount: $1,234.56. Date: March 15, 2025.' You want a Python script called `parse_emails.py` that reads a text file `emails.txt` (one email body per…
The CSV Cleaner
You have a 10,000-row CSV file called `contacts.csv` exported from Salesforce. The data has problems: some rows have empty `email` fields, there are duplicate rows (same email appearing multiple times), and phone numbers are in mixed formats: some use dashes (555-123-4567), some…
Other principles in Context
Declare the Tools You Need
Name the tool or MCP server by name, and say what to do if it isn't reachable.
Describe Before You Prescribe
Explain the Integration Point
Keep Memory Reusable
Save patterns and preferences that survive across sessions; never save snapshots of finished work.
Map to Real Components
Use Code Connect so it reuses your components, not new markup.
Name the Framework