File: csv-converter.md | Updated: 11/15/2025
Agent Skills are now available! Learn more about extending Claude's capabilities with Agent Skills .
English
Search...
Ctrl K
Search...
Navigation
Prompt Library
CSV converter
Home Developer Guide API Reference Model Context Protocol (MCP) Resources Release Notes
On this page
Copy this prompt into our developer Console to try it for yourself!
| | Content | | --- | --- | | System | As a data conversion expert, your task is to convert data from different formats (JSON, XML, etc.) into properly formatted CSV files. The user will provide the input data in the original format, along with any specific requirements or preferences for the CSV output (e.g., column order, delimiter, encoding). Ensure that you have a clear understanding of the data structure and the desired CSV format, asking any clarifying questions as needed. Once you have the necessary information, generate the CSV output by following the appropriate formatting rules, such as using commas as delimiters, enclosing values in quotes if necessary, and handling special characters or line breaks correctly. Finally, provide any additional instructions or tips for saving or using the CSV file. | | User | Please convert the following JSON data into a CSV file: <br> <br>[ <br>{ <br>“name”: “John Doe”, <br>“age”: 30, <br>“city”: “New York”, <br>“email”: “john.doe@example.com<br>” <br>}, <br>{ <br>“name”: “Jane Smith”, <br>“age”: 25, <br>“city”: “London”, <br>“email”: “jane.smith@example.com<br>” <br>}, <br>{ <br>“name”: “Bob Johnson”, <br>“age”: 35, <br>“city”: “Paris”, <br>“email”: “bob.johnson@example.com<br>” <br>} <br>] <br>Requirements: <br>- Columns in the CSV should be in the order: name, age, city, email <br>- Use semicolons (;) as delimiters <br>- Enclose all values in double quotes (“) |
Based on the provided JSON data and requirements, here’s the converted CSV file:
csv
Copy
"name";"age";"city";"email"
"John Doe";"30";"New York";"john.doe@example.com"
"Jane Smith";"25";"London";"jane.smith@example.com"
"Bob Johnson";"35";"Paris";"bob.johnson@example.com"
Explanation:
To save the CSV file:
Note: When opening the CSV file in a spreadsheet application (e.g., Microsoft Excel, Google Sheets), make sure to specify the correct delimiter (semicolon) and the presence of double quotes around the values to ensure proper formatting.
Copy
import anthropic
client = anthropic.Anthropic( # defaults to os.environ.get("ANTHROPIC_API_KEY")
api_key="my_api_key",
)
message = client.messages.create(
model="claude-sonnet-4-5",
max_tokens=1000,
temperature=0,
system="As a data conversion expert, your task is to convert data from different formats (JSON, XML, etc.) into properly formatted CSV files. The user will provide the input data in the original format, along with any specific requirements or preferences for the CSV output (e.g., column order, delimiter, encoding). Ensure that you have a clear understanding of the data structure and the desired CSV format, asking any clarifying questions as needed. Once you have the necessary information, generate the CSV output by following the appropriate formatting rules, such as using commas as delimiters, enclosing values in quotes if necessary, and handling special characters or line breaks correctly. Finally, provide any additional instructions or tips for saving or using the CSV file.",
messages=[\
{\
"role": "user",\
"content": [\
{\
"type": "text",\
"text": 'Please convert the following JSON data into a CSV file: \n \n[ \n { \n "name": "John Doe", \n "age": 30, \n "city": "New York", \n "email": "[email protected]" \n }, \n { \n "name": "Jane Smith", \n "age": 25, \n "city": "London", \n "email": "[email protected]" \n }, \n { \n "name": "Bob Johnson", \n "age": 35, \n "city": "Paris", \n "email": "[email protected]" \n } \n] \n \nRequirements: \n- Columns in the CSV should be in the order: name, age, city, email \n- Use semicolons (;) as delimiters \n- Enclose all values in double quotes (")',\
}\
],\
}\
],
)
print(message.content)
Was this page helpful?
YesNo
Neologism creator Emoji encoder
Assistant
Responses are generated using AI and may contain mistakes.