Universal resources
Universal resources avoid vendor-specific syntax, tool names and system-prompt tricks. They rely only on plain instructions, an explicit output shape and clearly marked input, which every instruction-tuned model understands. If a prompt here needs a change to run somewhere else, that change is written in the usage notes rather than hidden in the text.
Universal prompts
All 11- Universal
Debug from a stack trace
Works from the trace and the relevant source to name the most likely cause, with the check that would confirm it.
- Universal
Translate while keeping terminology fixed
Translates text while leaving a named glossary of terms untouched - useful for documentation and interfaces.
- Universal
Turn a vague request into a written brief
Takes a one-line request from a colleague or client and returns the questions that have to be answered before work starts.
- Universal
Write a SQL query from a plain question
Produces one query against a schema you provide, and asks a question instead of guessing when the schema is ambiguous.
- Universal
Rewrite a product description for a specific audience
Rewrites shop copy to a fixed length and audience while keeping the technical specifications exactly as given.
- Universal
Explain this code to a new maintainer
Explains what a file does, why it is shaped that way, and where the traps are - aimed at someone about to change it.
Configuration files
All 2- Universal
Editor rules for a Django project
A rules file that pins the Django and Python versions, the app layout and the things an assistant should never regenerate.
- Universal
System prompt for a support triage bot
A system prompt for classifying incoming support messages into a fixed set of routes, with an explicit escape for the unclear ones.
Guides
- Universal
Giving a model a role and constraints
How naming the audience, the format and the exclusions turns unpredictable answers into repeatable ones.
- Universal
Choosing a model for the job
A practical comparison of what to reach for when, based on the shape of the task rather than benchmark scores.
- Universal
Working with long documents and code
Why long sessions drift, what a large context window actually buys you, and how to keep a model on task across a big input.