/ai--semantic-cache

/ai--semantic-cache is a Claude Code skill in the AI & Agents section. Adds a cache in front of LLM calls so repeated or near-duplicate requests get a stored answer, and measures whether it helps without serving wrong ones.

Author's description

Add semantic caching to LLM calls - embedding keys, thresholds, invalidation

How to ask for it

/ai--semantic-cache cache answers for similar questions, not just identical ones
/ai--semantic-cache tune the similarity threshold for the semantic cache
/ai--semantic-cache invalidate the cache when source documents change

Install

curl -fsSL https://raw.githubusercontent.com/sgomez-dev/claude-skills/main/install.sh | bash

After installing with the script, type /ai--semantic-cache. Using Cursor, Windsurf or Codex? Platform guides

Demo coming soon

/ai--structured-outputReliable LLM structured output
Makes a model return dependable JSON or typed objects: schema design, native structured modes, validation and bounded repair loops.
Built here
/ai--tool-callingLLM tool calling
Audits or implements the tools a model can call: clear schemas, parallel calls, error handling that lets the model recover, and an accuracy eval.
Built here
/ai--voice-agentReal-time voice agent
Designs a low-latency voice agent that handles interruptions: speech-to-text and text-to-speech choice, latency budget and conversation design.
Built here
/deep-researchIn-depth web research
Applies a multi-phase research method, with several angles and sources, before answering or creating content that needs up-to-date information.
By Hainrixz
/meta--health-checkSkills health check
Checks every installed skill for structure, declared permissions and safety, then produces a health report of what passes and what fails.
Built here
/meta--pipeline-runRunning a skill pipeline
Runs a chain of skills defined in a pipeline file, with quality gates between steps and a final summary showing the result of each step.
Built here

How to ask for it

Install

More from this section