# flompt

> Use this tool when you need to optimize and refine AI prompts for better performance, as it decomposes raw prompts into semantic blocks and recompiles them into optimized XML. The flompt tool solves problems of inefficient or unclear prompts, allowing for more effective interaction with AI models like Claude. It takes raw prompts as input and outputs optimized XML via its decompose_prompt and compile_prompt tools.

Canonical page: https://skillsregistry.net/skills/nyrok-flompt  
JSON: https://api.skillsregistry.net/v1/skills/nyrok-flompt

## Description

Visual AI prompt builder that decomposes any raw prompt into 12 semantic blocks and recompiles them into Claude-optimized XML. Exposes decompose_prompt and compile_prompt tools via MCP.

## Trust

- **Trust score (0–1):** 0.91
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-28

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/hq5fw47xhb)
- **Repository:** <https://github.com/Nyrok/flompt>

## 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": "nyrok-flompt"
    }
  }
}
```

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