# LLM call monitoring (/ai--llm-observability)

/ai--llm-observability is a Claude Code skill in the AI & Agents section. Instruments your AI app with traces, token and cost tracking, quality signals, dashboards and alerts for every model call.

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

## How to ask for it

- `/ai--llm-observability I want to see how many tokens each model call uses`
- `/ai--llm-observability add tracing to debug the agent's responses`
- `/ai--llm-observability alert me when response quality drops`

## 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

Instrument LLM calls - tracing, token/cost tracking, quality dashboards, alerts

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