# Custom Commands just like in Cody **URL:** \ **Category:** Feature Requests\ **Created:** [September 19, 2024, 3:20pm UTC](https://forum.cursor.com/t/custom-commands-just-like-in-cody/17627 "2024-09-19T15:20:48Z")\ **Posts on this page:** 1\ **Showing post:** 5
**Author:** ![litecode](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/litecode/32/2966_2.png) [@litecode](https://forum.cursor.com/u/litecode)\ **Post date:** [September 24, 2024, 8:22am UTC](https://forum.cursor.com/t/custom-commands-just-like-in-cody/17627/5 "2024-09-24T08:22:48Z")
Hi @19h , You may be interested in the ideas that arose in this topic regarding ‘canned prompts’: > [@Context Groups: Defining collections of files as a single context for prompting](https://forum.cursor.com/t/context-groups-defining-collections-of-files-as-a-single-context-for-prompting/7405/6): > > I wonder if some sort of ‘canned responses’ feature could achieve the desired results, but also be adaptable to other scenarios as well. You know how helpdesk software has canned responses, eg from a quick Google search: [https://www.helpdesk.com/help/what-are-canned-responses/](https://www.helpdesk.com/help/what-are-canned-responses/)[https://www.livechat.com/help/set-canned-responses](https://www.livechat.com/help/set-canned-responses)[https://www.customerly.io/canned-response-templates](https://www.customerly.io/canned-response-templates) It seems Cursor already has the underlying mechanism for ‘tagging’ specific content through the @ symbols feature,… > [@Context Groups: Defining collections of files as a single context for prompting](https://forum.cursor.com/t/context-groups-defining-collections-of-files-as-a-single-context-for-prompting/7405/12): > > @connor, So as an immediate solution you could either: Create 1 file for each canned prompt: canned\_prompt\_1 canned\_prompt\_2 canned\_prompt\_3 Create 1 file that had all the canned prompts within it canned\_prompts And then you could just @ either: the specific canned\_prompt file the single canned\_prompts file (and reference the relevant entry) Example canned prompt files below. Multiple Canned Prompts File # Canned Prompts This file contains canned prompts designed to … And also this topic: > [@Workaround for lack of memory between chats](https://forum.cursor.com/t/workaround-for-lack-of-memory-between-chats/7605): > > I guess this is a combo of showcase, workaround & feature request. I’ve been hoping for project memory to eventually be retained between chats, especially as chat length increases and subsequently degrades the quality of responses. Basically I’ve just created a projectContext.md file top-level in my codebase that describes the project / codebase and any current tasks being worked on. Essentially it just contains any information I would want to be persisted between chats. So I can just @project… And the notion of storing, and writing, local prompt and logging files was expanded upon further in this video: by echohive, 3 mins [![](https://us1.discourse-cdn.com/cursor1/original/2X/1/14038c1f5259fc58a48c1dc4e3008a29de6af907.jpeg "Cursor Composer Auto saves your prompts to a file") ](https://www.youtube.com/watch?v=5QknrE1VRuc) Similar ideas about generating markdown files as prompts to keep things relevant and on track are talked about in this video: by Yaron Been, 17 mins [![](https://us1.discourse-cdn.com/cursor1/original/2X/c/cac7f3cb21d450aa3a4d5bd0ca040bd372670d26.jpeg "This HACK WILL CREATE THE PERFECT CODE FOR YOU") ](https://www.youtube.com/watch?v=HA5e0YIBOjk) The thing I like about all these ideas is that they are trivial to implement, yield powerful results, and let you be as creative as you like with them. --- _[View the full topic](https://forum.cursor.com/t/custom-commands-just-like-in-cody/17627)._