# LLM context window tuning (/ai--context-engineering)

/ai--context-engineering is a Claude Code skill in the AI & Agents section. Audits what goes into your AI app's context window and decides what to retrieve, summarize or compact, then checks the result with an eval.

- Web version: https://skills.sgomez.dev/en/s/ai--context-engineering
- 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/context-engineering.md
- Updated 10 Jul 2026

## How to ask for it

- `/ai--context-engineering my agent runs out of context in long conversations`
- `/ai--context-engineering should I use retrieval or stuff the whole doc in the prompt?`
- `/ai--context-engineering help me compact chat history to save tokens`

## 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: —
- Network: No
- Destructive: No

## Author's description

Context engineering: what goes in the window, retrieval vs stuffing, compaction

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