Prompt Caching

Use Claude API prompt caching to reuse processed prompt prefixes across requests — automatic vs explicit breakpoints, 5-minute and 1-hour TTLs, minimum cacheable lengths, what invalidates the cache, and how to measure hit rate from usage fields. Use this skill when building apps with large repeated context (system prompts, tool definitions, documents, long conversations), reducing API spend, or debugging cache reads that stay at zero. Activate when: prompt caching, cache_control, cache hit rate, cache_read_input_tokens, 1 hour cache, ttl 1h, ephemeral cache, cache breakpoint, cache invalidation.

latestaiagents Updated 6 repo stars

File contents

latestaiagents/agent-skills commit 07288f4175

Frequently asked questions

npx get-skill add latestaiagents/prompt-caching