Hi @dev-mico ,
I really enjoyed that thread.
Out of interest, could you explain further why you think this example approach would not do the job?
@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 …
I think you mentioned that you didn’t think @ ’ing ‘canned prompt’ files would be as good as a UI feature linked to a behind-the-scenes function because the canned prompt files couldn’t reference other required context? Is that a correct understanding of what you were saying?
Have you tried creating perform_magic.md, putting some prompts in it, and including some references to other folders or files to see if it can incorporate that context when you ’@perform_magic.md` in a chat prompt?
I am away from computer but will try tomorrow.
Edit :
Some other related posts:
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…
Hi Cursor Team,
Great job on building an amazing product so far!
Since GPT-4 is very steerable, I would love the ability to save and edit custom prompts in Cursor to be able to reuse common instructions and include it in the chat using @Prompts or something similar (just like @Docs for example).
I guess this is already possible by maybe creating text files of instructions and using @Files but a dedicated @Prompts tag + add/edit/delete functionality would be much better UX for creating reusabl…
Hey, I would really like to have this feature I use pretty much 95% over entering manual prompts in Cody every day:
[CleanShot 2024-09-19 at 17.18.00@2x]
These are essentially prompts to do repetitive things like cleanup, certain refactoring, optimizations, etc.
My Usecase:
I have a .cursor directory with metaproject scripts and analysis and information, and inside of there I keep track a description.md a roadmap.md and a plan_of_action.md that I find myself using over and over and over again.
Even if i weren’t doing that specifically, I also have a folder of .md files that I reference so often, I would love to favorite that folder that contains them so that it would bubble up to the top of the drop-down recommendation list and be even easier to click…
Currently in Chat we can go back and modify any request, and it will effectively branch off into a different conversation from there.
It doesn’t seem to be possible in Composer at the moment.
Please consider adding this, as Composer becomes more and more used, this feature would be extremely helpful and it avoids having to start a new Composer flow and losing the context