Prompt Rewriter

Overview

Help users transform vague, ineffective prompts into powerful, well-structured instructions that produce consistent, high-quality results from AI models. Analyzes prompts across multiple quality dimensions and provides actionable suggestions.

Quick Start

User says: "Help me rewrite this prompt: 'Write a blog post about AI'"

You should:

1. Analyze the original prompt's weaknesses (too vague, no audience specified, no format defined)
2. Identify improvement areas (add topic specificity, target audience, tone, length, structure)
3. Provide 2-3 rewrite options with different approaches
4. Explain the changes and why they matter

Core Capabilities

1. Prompt Quality Analysis

Evaluate prompts across five key dimensions:

Clarity (0-2)

• Is the request unambiguous?
• Are terms defined?
• Can Claude understand without clarification?

Specificity (0-2)

• Are constraints clear?
• Is output format specified?
• Are boundaries defined?

Structure (0-2)

• Is information organized logically?
• Are steps clear if applicable?
• Is there a framework?

Completeness (0-2)

• Is sufficient context provided?
• Are requirements comprehensive?
• Is missing information flagged?

Usability (0-2)

• Is it reusable?
• Can it be adapted easily?
• Is the language natural?

Scoring:

• 8-10: Excellent prompt, minor tweaks needed
• 6-7: Good prompt, moderate improvements possible
• 4-5: Functional but has significant weaknesses
• 0-3: Poor prompt, needs major rework

2. Rewrite Generation

Generate 2-3 rewrite variations using different approaches:

Variation 1: Conservative Fix

• Keep original intent
• Add specificity and structure
• Minimal stylistic changes
• Best when user wants to preserve voice

Variation 2: Technique Enhancement

• Apply prompt engineering patterns (CoT, few-shot, etc.)
• Add advanced techniques
• Focus on effectiveness
• Best when user wants optimal results

Variation 3: Simplification

• Strip complexity while keeping core request
• Make more conversational
• Focus on ease of use
• Best for beginners or quick tasks

3. Improvement Explanation

For each rewrite, explain:

• What changed (specific modifications)
• Why it matters (impact on AI output)
• When to use (appropriate scenarios)

4. Pattern Application

Apply proven prompt engineering techniques:

Chain of Thought (CoT)

• "Let's think step by step"
• "First, analyze... Then, evaluate..."
• Best for: complex reasoning, math, logic

Few-Shot Learning

• Provide 2-3 examples before request
• Pattern: Example 1 → Example 2 → Example 3 → Your task
• Best for: format specification, style matching

Role-Based Prompts

• "Act as a senior engineer..."
• "You are a marketing expert..."
• Best for: specialized knowledge, tone control

Output Structure

• Use templates and headers
• Define sections explicitly
• Best for: reports, documentation, structured content