Skip to main content
AI / LLM PromptingCurated

Prompt Compression

For high-volume prompts where token cost per call actually adds up.

The prompt
Here is a 400-word prompt: [paste]. Rewrite it to under 120 words without losing any instruction that changes model behavior. List which lines you removed and why they were redundant.

Anything in square brackets is meant to be replaced. The builder turns those into fields you can type into.

Tired of re-pasting the same context into every new chat? That is what the Unimatrix MCP server is for.

Browse the rest of the library