# cue

> cue — manuelcattelan-cue. Use this tool when you need to streamline prompt engineering for AI workflows, as it provides a front-loaded solution for managing and optimizing prompts. The cue tool solves problems related to inefficient prompt design and deployment, allowing for seamless integration with git for version control. It takes in prompts and workflows as input and outputs optimized configurations for agentic workflows.

Canonical page: https://skillsregistry.net/skills/manuelcattelan-cue  
JSON: https://api.skillsregistry.net/v1/skills/manuelcattelan-cue

## Description

MCP server designed to front-load prompt engineering for agentic workflows.

## Trust

- **Trust score (0–1):** 0.93
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** GPL-3.0
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/manuelcattelan/cue)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "manuelcattelan-cue"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/manuelcattelan-cue` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/manuelcattelan-cue/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt