prompt-engineer

Prompt Engineer - AI Prompt Intelligent Optimization Skill

Skill Overview

Prompt Engineer is an automated prompt optimization tool that transforms vague original prompts into structured, high-quality prompts. It intelligently selects the most suitable prompt framework (e.g., RTF, RISEN, Chain of Thought, etc.) to help users achieve better AI output results.

Use Cases

1. Convert Vague Requirements into Structured Prompts

When you only have a vague idea (e.g., “help me write Python”), Prompt Engineer analyzes your intent, automatically chooses an appropriate framework, and generates a professional prompt containing complete elements such as role definition, task description, output format, and more.

2. Build Prompts for Complex Tasks

For tasks that require step-by-step reasoning, system design, or in-depth analysis, the skill automatically applies advanced frameworks like Chain of Thought, RODES, or RISEN to ensure the AI produces clear, logically rigorous answers.

3. Cross-Platform, General Prompt Optimization

Whether you use GitHub Copilot CLI, Claude Code, or other AI tools, Prompt Engineer works without relying on any specific project structure or configuration files.

Core Features

1. Intelligent Framework Selection

The skill includes 11 prompt frameworks (RTF, RISEN, Chain of Thought, RODES, Chain of Density, RACE, RISE, STAR, SOAP, CLEAR, GROW). It automatically matches the best framework based on the task type and complexity. For example, debugging tasks trigger Chain of Thought, while complex project design may combine RODES + Chain of Thought.

2. Intent Analysis and Clarification

In “silent mode,” it analyzes user intent and only asks the user when key information is missing, avoiding excessive interruptions. The output is ready to use and does not include technical explanations or framework terminology.

3. Multilingual Support

Supports prompt optimization in both Chinese and English. It adapts automatically based on the input language. For mixed-language inputs, it defaults to English (more universal).

Frequently Asked Questions

Which AI platforms does Prompt Engineer support?

It supports mainstream AI development tools such as GitHub Copilot CLI, Claude Code, Codex, and more. The skill is platform-independent, can be used in any terminal environment, and does not depend on Obsidian or any specific project structure.

Do I need to learn these prompt frameworks to use it?

Not at all. The skill works in “silent mode”—it automatically selects the most suitable framework in the background. You only need to provide your original idea to directly get an optimized prompt, without learning frameworks like RTF or RISEN.

In what cases will Prompt Engineer ask me proactively?

It only asks when key information is severely missing and an effective prompt cannot be generated. For example, if you only say “optimize my prompt” but provide no specific content, it will ask. In normal circumstances, the skill will generate an optimized result directly based on the existing information.

Does this skill support Chinese prompt optimization?

Yes, fully. The skill automatically detects the input language and generates optimized prompts in the same language. For mixed Chinese-English inputs, it defaults to English output.