prompt-rewriter
Advanced prompt rewriting and optimization service. Analyzes prompts for clarity, specificity, structure, completeness, and usability. Identifies weaknesses, suggests improvements, and generates multiple rewrite options. Use when users need to improve an existing prompt's effectiveness, understand why a prompt isn't working well, generate variations of a prompt for A/B testing, or learn prompt engineering best practices through examples.
Install
mkdir -p .claude/skills/prompt-rewriter && curl -L -o skill.zip "https://mcp.directory/api/skills/download/2493" && unzip -o skill.zip -d .claude/skills/prompt-rewriter && rm skill.zipInstalls to .claude/skills/prompt-rewriter
About this skill
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:
- Analyze the original prompt's weaknesses (too vague, no audience specified, no format defined)
- Identify improvement areas (add topic specificity, target audience, tone, length, structure)
- Provide 2-3 rewrite options with different approaches
- 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
Constraint Definition
- "Limit response to 500 words"
- "Exclude jargon for non-technical audience"
- Best for: length control, accessibility
5. A/B Testing Guidance
Help users test prompts effectively:
- Generate variations systematically
- Suggest test methodology
- Recommend evaluation criteria
Workflow
Step 1: Receive and Analyze
- Extract the prompt to rewrite
- Identify user's intent (what do they want to achieve?)
- Check for constraints (tone, format, length, audience)
- Evaluate against 5 quality dimensions
- Calculate score and identify primary weaknesses
Step 2: Generate Rewrites
- Variation 1 (Conservative): Add structure, clarify terms, define output
- Variation 2 (Technique-Enhanced): Apply relevant patterns (CoT, few-shot, etc.)
- Variation 3 (Simplified): Make conversational, reduce complexity
Step 3: Present Options
For each rewrite:
- Show the improved prompt
- Explain the changes
- Highlight which techniques were used
- Recommend which to use based on context
Step 4: Educational Component
Briefly explain:
- Which prompt engineering techniques were applied
- Why they work in this context
- How the user can apply them in future prompts
Common Patterns and Fixes
Pattern: Too Vague
Weak: "Write about climate change" Fix: Add specificity - audience, purpose, format, depth
Strong: "Write a 1000-word blog post for a general audience explaining climate change's causes, effects, and potential solutions. Use an optimistic but realistic tone. Include: (1) introduction with hook, (2) 3 main sections with data, (3) conclusion with actionable advice."
Pattern: No Structure
Weak: "Analyze this data" Fix: Add framework or step-by-step instructions
Strong: "Analyze the sales data provided. Structure your response as:
- Executive Summary (3 bullet points of key findings)
- Detailed Analysis (break down by region and product)
- Trend Identification (what patterns emerge?)
- Recommendations (3 actionable steps based on data)"
Pattern: Missing Context
Weak: "Improve this email" Fix: Add context about audience, goal, constraints
Strong: "Improve this email for a C-level executive audience. Goal: Get approval for a $50k project. Keep it under 200 words. Tone: Professional but persuasive. Current email: [paste]"
Pattern: Unclear Output Format
Weak: "Create marketing content" Fix: Specify format, style, deliverables
Strong: "Create marketing content for our new product launch. Deliver:
- Social media post (LinkedIn, 150 words, professional tone)
- Email blurb (75 words, excitement-focused)
- Website headline (catchy, under 10 words)
- 3 key benefits (each under 15 words)"
Examples
Example 1: Content Creation
Input Prompt: "Write an article about remote work"
Analysis:
- Clarity: 1/2 (clear topic but vague on specifics)
- Specificity: 0/2 (no format, audience, length)
- Structure: 0/2 (no framework)
- Completeness: 0/2 (missing key details)
- Usability: 1/2 (somewhat reusable)
- Score: 2/10 - Major weaknesses across dimensions
Rewrite Option 1 (Conservative):
Write a 1500-word article about remote work for business professionals. Cover:
1. Benefits of remote work (productivity, cost savings, flexibility)
2. Challenges (isolation, communication, work-life balance)
3. Best practices for success (routine, communication tools, workspace setup)
4. Future trends (hybrid models, technology evolution)
Tone: Informative and balanced
Format: Use headings and bullet points
Rewrite Option 2 (Technique-Enhanced):
Act as an experienced remote work consultant. Write a comprehensive article about remote work for business leaders considering transitioning their teams.
Structure your response using the following framework:
**Introduction (150 words)**
- Hook with a surprising statistic
- Briefly state the article's purpose
- Outline what will be covered
**Section 1: The Business Case (400 words)**
Let's think about this step by step:
- Analyze cost benefits (real estate, equipment, turnover)
- Evaluate productivity studies (with data sources)
- Consider talent access (hiring from anywhere)
**Section 2: Implementation Challenges (350 words)**
- Communication breakdowns (provide examples)
- Culture maintenance (specific strategies)
- Performance management (tools and metrics)
**Section 3: Success Framework (400 words)**
Provide a concrete 90-day rollout plan:
- Month 1: Foundation and tools
- Month 2: Training and feedback
- Month 3: Optimization and refinement
**Conclusion (200 words)**
- Summarize key takeaways
- Provide 3 actionable next steps
- End with an inspiring vision
Tone: Professional yet engaging
Examples: Include 2-3 real company case studies
Rewrite Option 3 (Simplified):
Write an article about remote work. Make it about 1500 words long and aimed at business people who are thinking about letting employees work from home. Talk about:
- Why it's good (saves money, people like it)
- What's hard (staying in touch, managing performance)
- How to do it right (tools, schedules, clear expectations)
Use a helpful, informative tone with clear headings.
Recommendation: Use Option 2 if the user wants maximum impact. Use Option 1 for clarity and professionalism. Use Option 3 for quick, casual needs.
Example 2: Code Review
Input Prompt: "Review this code"
Analysis:
- Clarity: 0/2 (completely unclear what to look for)
- Specificity: 0/2 (no criteria, no scope)
- Structure: 0/2 (no framework)
- Completeness: 0/2 (missing all context)
- Usability: 0/2 (not reusable)
- Score: 0/10 - Needs complete rework
Rewrite Option 1 (Conservative):
Review the code provided below. Focus on:
1. Bugs or errors
2. Performance issues
3. Code style and readability
4. Potential security vulnerabilities
Provide specific line references and suggestions for each issue found.
Rewrite Option 2 (Technique-Enhanced):
Act as a senior software engineer conducting a thorough code review. Analyze the provided code following this systematic approach:
**Step 1: Functional Analysis**
Let's check if the code works correctly:
- Verify logic correctness (walk through execution)
- Check edge cases (null inputs, empty arrays, boundary conditions)
- Validate error handling (try-catch blocks, meaningful error messages)
**Step 2: Performance Evaluation**
Analyze computational complexity:
- Time complexity: Big-O notation
- Space complexity: Memory usage
- Identify any O(n²) or worse bottlenecks
- Suggest optimization opportunities
**Step 3: Security Review**
Look for common vulnerabilities:
- SQL injection risks
- XSS vulnerabilities
- Improper input validation
- Sensitive data exposure
**Step 4: Code Quality**
Assess adherence to best practices:
- Naming conventions (descriptive, consistent)
- Comments (helpful, not redundant)
- DRY principle (Don't Repe
---
*Content truncated.*
More by openclaw
View all skills by openclaw →You might also like
flutter-development
aj-geddes
Build beautiful cross-platform mobile apps with Flutter and Dart. Covers widgets, state management with Provider/BLoC, navigation, API integration, and material design.
drawio-diagrams-enhanced
jgtolentino
Create professional draw.io (diagrams.net) diagrams in XML format (.drawio files) with integrated PMP/PMBOK methodologies, extensive visual asset libraries, and industry-standard professional templates. Use this skill when users ask to create flowcharts, swimlane diagrams, cross-functional flowcharts, org charts, network diagrams, UML diagrams, BPMN, project management diagrams (WBS, Gantt, PERT, RACI), risk matrices, stakeholder maps, or any other visual diagram in draw.io format. This skill includes access to custom shape libraries for icons, clipart, and professional symbols.
ui-ux-pro-max
nextlevelbuilder
"UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient."
godot
bfollington
This skill should be used when working on Godot Engine projects. It provides specialized knowledge of Godot's file formats (.gd, .tscn, .tres), architecture patterns (component-based, signal-driven, resource-based), common pitfalls, validation tools, code templates, and CLI workflows. The `godot` command is available for running the game, validating scripts, importing resources, and exporting builds. Use this skill for tasks involving Godot game development, debugging scene/resource files, implementing game systems, or creating new Godot components.
nano-banana-pro
garg-aayush
Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports both text-to-image generation and image-to-image editing with configurable resolution (1K default, 2K, or 4K for high resolution). DO NOT read the image file first - use this skill directly with the --input-image parameter.
fastapi-templates
wshobson
Create production-ready FastAPI projects with async patterns, dependency injection, and comprehensive error handling. Use when building new FastAPI applications or setting up backend API projects.
Related MCP Servers
Browse all serversHoutini LM delivers advanced prompt engineering with 35+ functions for code analysis, generation, security audits, and d
Universal Image Generator is an AI image generator that supports multi-provider photo creation, advanced editing, and au
Unlock AI-ready web data with Firecrawl: scrape any website, handle dynamic content, and automate web scraping for resea
Boost Postgres performance with Postgres MCP Pro—AI-driven index tuning, health checks, and safe, intelligent SQL optimi
Integrate with Google Sheets and Google Drive to manage spreadsheets easily using the Google Sheets API and advanced aut
Seamlessly integrate with Odoo ERP for advanced business record management, automation, and secure data workflows via XM
Stay ahead of the MCP ecosystem
Get weekly updates on new skills and servers.