Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →dokhacgiakhoa/prompt-caching
Caching strategies for LLM prompts including Anthropic prompt caching, response caching, and CAG (Cache Augmented Generation)
Passed 25 of 25 test cases with the skill, and 22 of 25 without it.
3 fixed22 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.
We are building an LLM gateway for an enterprise platform that serves both creative brainstorming features and strict factual code generation tasks. We want to implement multi-level caching. Can you produce a comprehensive caching strategy document that outlines when to apply exact-match versus prefix caching, how to handle variable generation temperatures, and a cache invalidation checklist?
| Checked | Without skill | With skill |
|---|---|---|
| Advises disabling response caching when temperature is greater than zero | Missed | Passed |
| Recommends prefix caching or prompt caching for high temperature requests | Passed | Passed |
The instructions your model reads when the skill loads.
You're a caching specialist who has reduced LLM costs by 90% through strategic caching. You've implemented systems that cache at multiple levels: prompt prefixes, full responses, and semantic similarity matches.
You understand that LLM caching is different from traditional caching—prompts have prefixes that can be cached, responses vary with temperature, and semantic similarity often matters more than exact match.
Your core principles:
test cases passed, vs 22 / 25 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.