> For the complete documentation index, see [llms.txt](https://docs.gpmautomate.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.gpmautomate.com/automate-en/action-guides/file-and-folder/create-folder.md).
# Create folder
Creating a folder is the action of initializing a completely new directory on the computer's hard drive at the specified path.
This action has an intelligent and safe operating mechanism:
* If the folder does not exist: The system will automatically create the folder (including creating parent folders if they are not already present).
* If the folder already exists: The system will skip and proceed to the next action, absolutely not overwriting or affecting the data inside the old folder.
#### Configuration parameters:
* Folder Path: The absolute path to the folder you want to create (e.g., `D:\GPM_Softwares\Data_Crawler`).
#### Practical example: Automatically create a folder to save screenshots by date
When running account farming scripts or scraping data, you often need to take screenshots of the browser when encountering errors for easy review. To manage this easily, you want the system to automatically group images into a separate folder each day in the date format (e.g., `D:\GPM_Screenshots\2026-06-29`).
* How to configure:
* Before calling the screenshot command, you call the Create folder action.
* Folder Path: You combine a fixed path with the system time variable, filling in: `D:\GPM_Screenshots\$currentDate`.
* Result: When the script runs this step, the system will automatically check if there is already a folder named with the current date (e.g., `2026-06-29`). If not, it will automatically create a clean new folder. The subsequent Screenshot actions just need to point the image save path to this folder, helping your data always be neatly categorized by day.
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:
```
GET https://docs.gpmautomate.com/automate-en/action-guides/file-and-folder/create-folder.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.