About prompt-caching
A skill covering caching strategies for LLM prompts and responses, including prefix caching, semantic matches, and Cache Augmented Generation. It also outlines cache invalidation concerns and patterns for choosing what to cache.
Key features
- 01Prompt-prefix caching guidance
- 02Full-response caching for exact or similar queries
- 03KV-cache and CAG patterns
- 04Cache invalidation considerations
- 05Caching anti-patterns and edge cases
Use cases
- 01Reduce repeated LLM work with cached responses
- 02Choose between prefix and response caching
- 03Pre-cache documents for Cache Augmented Generation
Install
Copy the command and run it in a terminal.
npx skills add https:/After installing, type/prompt-cachingin Claude Code to confirm it loaded.
Details
From the project READMEPrompt Caching
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:
- Cache at the right level—prefix, response, or both
- K
Capabilities
- prompt-cache
- response-cache
- kv-cache
- cag-patterns
- cache-invalidation
Patterns
Anthropic Prompt Caching
Use Claude's native prompt caching for repeated prefixes
Response Caching
Cache full LLM responses for identical or similar queries
Cache Augmented Generation (CAG)
Pre-cache documents in prompt instead of RAG retrieval
Anti-Patterns
❌ Caching with High Temperature
❌ No Cache Invalidation
❌ Caching Everything
⚠️ Sharp Edges
| Issue | Severity | Solution |
|---|---|---|
| Cache miss causes latency spike with additional overhead | high | // Optimize for cache misses, not just hits |
| Cached responses become incorrect over time | high | // Implement proper cache invalidation |
| Prompt caching doesn't work due to prefix changes | medium | // Structure prompts for optimal caching |
Related Skills
Works well with: context-window-management, rag-implementation, conversation-memory