---
title: "prompt-engineering"
description: "Prompt engineering patterns and Anthropic agent-prompting best practices, sourced from NeoLabHQ/context-engineering-kit."
canonical: https://agentpluginsdirectory.com/plugins/prompt-engineering
last-updated: 2026-09-09
---

# prompt-engineering
Prompt engineering patterns and Anthropic agent-prompting best practices, sourced from NeoLabHQ/context-engineering-kit.
- Slug: prompt-engineering
- Publisher: fu4k6pingu
- Repository: https://github.com/fu4k6pingu/agent-plugins-loader
- Manifest: prompt-engineering-plugin/plugin.json
- Version: 1.0.0
- License: MIT
- Category (editorial): other
- Skills: 1 (prompt-engineering)
- MCP servers: 0
- Stars: 0
- Repository created: 2026-09-08
- Repository last pushed: 2026-09-08
- Publisher type: User
- Listing: https://agentpluginsdirectory.com/plugins/prompt-engineering
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## What prompt-engineering does, in the publisher's words

A small bridge that loads Agent Plugins (v1.0.0) formatted plugin folders into a self-hosted Open WebUI install, specifically its mcpo MCP-to-HTTP bridge and its native Skills feature.

Agent Plugins is an emerging open spec (backed by Amazon, Cursor, Microsoft, OpenAI, and Vercel) for packaging an agent's tools (MCP servers) and instructions (skills) into one portable folder. No current client, not Open WebUI, not Claude Desktop/Code, has native support for the format. This tool is a working bridge for one of them.

Open WebUI reaches MCP servers through mcpo, a small process that exposes each configured MCP server as an OpenAPI-compatible HTTP endpoint. There's no built-in way to hand it a standard Agent Plugins folder and have it "just work", someone has to translate the plugin's mcp.json into mcpo's own config format, and separately import the plugin's skill files into Open WebUI's database. This script does both translations, safely.

From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/fu4k6pingu/agent-plugins-loader/HEAD/README.md

## Skills

- prompt-engineering: Use this skill when you writing commands, hooks, skills for Agent, or prompts for sub agents or any other LLM interaction, including optimizing prompts, improving LLM outputs, or designing production prompt templates.

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.