# Semantic cache for LLM calls (/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.

- Web version: https://skills.sgomez.dev/en/s/ai--semantic-cache
- Section: [AI & Agents](https://skills.sgomez.dev/en/ai.md)
- Author: Santiago Gómez de la Torre
- License: MIT
- Source: https://github.com/sgomez-dev/claude-skills/blob/main/skills/ai/semantic-cache.md
- Updated 10 Jul 2026

## 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

macOS · Linux:

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

Windows:

```
irm https://raw.githubusercontent.com/sgomez-dev/claude-skills/main/install.ps1 | iex
```

Claude Code plugin:

```
/plugin marketplace add sgomez-dev/claude-skills
/plugin install ai-skills@claude-skills-collection
```

## Permissions

- Reads: `**/*`
- Writes: `**/*`
- Runs: `project test/eval runners`
- Network: No
- Destructive: No

## Author's description

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

- [How we review this](https://skills.sgomez.dev/en/methodology.md)