Prompt Optimizer logo

Prompt Optimizer

Community
LingyiChen-AI
prompt-optimizer

Prompt engineering expert that helps users craft optimized prompts using 57 proven frameworks. Use when users want to optimize prompts, improve AI instructions, create better prompts for specific tasks, or need help selecting the best prompt framework for their use case.

Overview

PublisherLingyiChen-AI
RepositoryOpenSkills
Skill nameprompt-optimizer
Stars
69
Forks
5
Bundled files
58
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 58 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by LingyiChen-AI on GitHub. Read the source before you install it.

Installation

Install the Prompt Optimizer AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/LingyiChen-AI/OpenSkills.git /tmp/OpenSkills
mkdir -p .claude/skills
cp -r /tmp/OpenSkills/examples/prompt-optimizer .claude/skills/prompt-optimizer
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Prompt Optimizer in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Prompt Optimizer on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Prompt Optimizer is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Prompt Optimizer

A comprehensive prompt engineering skill that helps users craft high-quality, effective prompts using proven frameworks.

Workflow

When a user requests prompt optimization, follow these steps:

Step 1: Analyze User Input

Receive the user's request, which may be:

  • A raw prompt that needs optimization
  • A task description or requirement
  • A vague idea that needs to be turned into a prompt

Step 2: Match Scenario and Select Framework

Read the references/Frameworks_Summary.md file to:

  1. Identify the user's scenario from the application scenarios listed
  2. Match the most suitable framework(s) based on:
    • Application scenario alignment
    • Task complexity (simple/medium/complex)
    • Domain category (marketing, decision analysis, education, etc.)

Framework Selection Guide by Complexity:

ComplexityRecommended Frameworks
Simple (≤3 elements)APE, ERA, TAG, RTF, BAB, PEE, ELI5
Medium (4-5 elements)RACE, CIDI, SPEAR, SPAR, FOCUS, SMART, GOPA, ORID, CARE, ROSE, PAUSE, TRACE, GRADE, TRACI, RODES
Complex (6+ elements)RACEF, CRISPE, SCAMPER, Six Thinking Hats, ROSES, PROMPT, RISEN, RASCEF, Atomic Prompting

Framework Selection Guide by Domain:

DomainRecommended Frameworks
Marketing ContentBAB, SPEAR, Challenge-Solution-Benefit, BLOG, PROMPT, RHODES
Decision AnalysisRICE, Pros and Cons, Six Thinking Hats, Tree of Thought, PAUSE, What If
Education & TrainingBloom's Taxonomy, ELI5, Socratic Method, PEE, Hamburger Model
Product DevelopmentSCAMPER, HMW, CIDI, RELIC, 3Cs Model
AI Dialogue/AssistantCOAST, ROSES, TRACE, RACE, RASCEF
Writing & CreationBLOG, 4S Method, Hamburger Model, Few-shot, RHODES, Chain of Destiny
Image GenerationAtomic Prompting
Quick Simple TasksZero-shot, ERA, TAG, APE, RTF
Complex ReasoningChain of Thought, Tree of Thought

Step 3: Load Framework Details

Once the best framework is identified, read the corresponding framework file from the references/frameworks/ directory:

  • File naming pattern: XX_FrameworkName_Framework.md
  • Example: For RACEF framework, read references/frameworks/01_RACEF_Framework.md

The framework file contains:

  • Framework overview and components
  • Detailed explanation of each element
  • Pros and cons
  • Best practice examples

Step 4: Clarify Ambiguities

Before generating the final prompt, verify with the user:

  1. Goal Clarity: Is the intended outcome clear?
  2. Target Audience: Who will receive the AI's response?
  3. Context Completeness: Is sufficient background information provided?
  4. Format Requirements: Are there specific output format needs?
  5. Constraints: Are there any limitations or restrictions?

Ask clarifying questions if any information is:

  • Missing
  • Ambiguous
  • Incomplete
  • Contradictory

Example clarifying questions:

  • "What specific outcome are you hoping to achieve?"
  • "Who is the target audience for this content?"
  • "Are there any format or length requirements?"
  • "What context should the AI consider?"

Step 5: Generate Optimized Prompt

Apply the selected framework to create the final prompt:

  1. Structure the prompt according to framework components
  2. Incorporate all clarified information
  3. Ensure clarity and specificity
  4. Include relevant examples if the framework requires
  5. Add any necessary constraints or guidelines

Step 6: Present and Iterate

Present the optimized prompt to the user with:

  1. The selected framework name and why it was chosen
  2. The complete optimized prompt
  3. Explanation of how each framework element was applied
  4. Suggestions for potential variations or improvements

If the user requests changes, iterate on the prompt while maintaining framework structure.

Framework Reference Files

All framework details are stored in the references/frameworks/ directory. Each file contains:

  • Application scenarios
  • Framework components with explanations
  • Advantages and disadvantages
  • Multiple practical examples

Quick Framework Selection

For users unsure which framework to use:

User SaysRecommended Framework
"I need a simple prompt"APE, ERA, TAG
"I want to persuade/sell"BAB, SPEAR, Challenge-Solution-Benefit
"I need to analyze/decide"RICE, Pros and Cons, Chain of Thought
"I want to teach/explain"ELI5, Bloom's Taxonomy, Socratic Method
"I need creative ideas"SCAMPER, HMW, SPARK, Imagine
"I want structured writing"BLOG, 4S Method, Hamburger Model
"I need step-by-step reasoning"Chain of Thought, Tree of Thought
"I'm generating images"Atomic Prompting
"I need a detailed plan"RISEN, RASCEF, CRISPE

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Prompt Optimizer AI skill do?

Prompt engineering expert that helps users craft optimized prompts using 57 proven frameworks. Use when users want to optimize prompts, improve AI instructions, create better prompts for specific tasks, or need help selecting the best prompt framework for their use case.

Why use Prompt Optimizer on TypingMind?

Because you install it once and use it with any model. Prompt Optimizer is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Prompt Optimizer in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/LingyiChen-AI/OpenSkills/tree/main/examples/prompt-optimizer. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Prompt Optimizer?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Prompt Optimizer?

As many as you like. As long as a model supports skills, you can use Prompt Optimizer with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Prompt Optimizer AI skill free?

Yes. It is published on GitHub by LingyiChen-AI under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇