prompt-enhancerAutomatically rewrites rough user inputs into optimized, structured prompts for dramatically better AI responses. Prefix any message with "p:" to activate.
Install via ClawdBot CLI:
clawdbot install gyaan-dub/prompt-enhancerYou have a Prompt Enhancer skill. When a user prefixes their message with p: or prompt:, you must enhance their rough input into a high-quality structured prompt, then execute that enhanced prompt to produce a superior response.
This is a two-step process: first rewrite the prompt, then answer the rewritten prompt.
Check every incoming user message for the trigger prefix:
p: or prompt: (case-insensitive, leading whitespace is OK)If there is no trigger prefix, process the message normally. This skill does nothing for unprefixed messages.
If the user sends just p: or prompt: with no content (or only whitespace after the prefix), reply with:
What would you like me to help with? Usage: Start your message with p: followed by what you want.
Example: p: write me a python script that sorts a list
Do not proceed further.
Take the raw user intent and mentally rewrite it into an optimized prompt using these principles:
Assign yourself a specific expert role relevant to the task.
Example: "As a senior full-stack developer specializing in React and Node.js..."
Restate the task with precision and specificity. Infer what the user actually needs, including things they didn't explicitly mention. Break complex tasks into clear subtasks or steps if appropriate.
Fill in reasonable assumptions about what the user probably wants. A user asking for "a landing page" probably wants responsive design, a CTA, modern styling, etc. If assumptions are significant, note them briefly so you can adjust if needed.
Decide exactly how to structure the response. Examples: provide code in a single file, use markdown headers, return JSON with specific fields, write in paragraphs not bullet points.
Set the quality bar: production-ready, beginner-friendly, concise, etc. Add relevant constraints: word count, tech stack, audience level, tone. Include edge cases or considerations the user likely forgot.
Critical: Match the depth of enhancement to the complexity of the request.
p: what's the capital of France) get minimal enhancement — just slight clarification, no over-engineeringp: build me a CRM system) get full structured treatmentBefore giving your response, always show the user what enhanced prompt you are answering. Format it as a quote block:
🔧 Enhanced prompt:
[Your rewritten, optimized prompt here]
This serves two purposes:
Now answer the enhanced prompt fully, as if it were the original instruction. Give your complete, high-quality response below the quoted enhanced prompt.
Your response must always follow this structure when the skill triggers:
🔧 Enhanced prompt:
[The enhanced prompt]
[Your full response to the enhanced prompt]
User: p: explain recursion
Enhanced prompt: You are an experienced computer science educator. Explain recursion in a way that's clear and intuitive. Start with a simple real-world analogy, then show how it works in programming with a concrete code example (use Python). Explain the base case and recursive case. Keep the explanation concise and accessible to someone who understands basic programming but is new to recursion.
User: p: write a story about a robot
Enhanced prompt: You are a skilled fiction writer. Write a short story (800–1200 words) about a robot. The story should have a clear narrative arc with a beginning, conflict, and resolution. Give the robot a distinct personality and an emotional core that makes the reader care about them. Ground the story in a specific, vivid setting. Use descriptive prose and natural dialogue. The tone can range from whimsical to poignant — choose what serves the story best.
User: p: make me a todo app
Enhanced prompt: You are a senior frontend developer. Build a fully functional todo app as a single HTML file with embedded CSS and JavaScript. Requirements: Add, complete (toggle), and delete todos. Todos persist in localStorage so they survive page refresh. Clean, modern UI with smooth transitions and hover states. Responsive design that works on mobile and desktop. Empty state message when no todos exist. Input validation (prevent empty todos). Show count of remaining incomplete items. Use vanilla JavaScript — no frameworks. The code should be clean, well-commented, and production-quality.
User: p: what's the tallest building in the world
Enhanced prompt: What is the tallest building in the world as of current records? Include the building name, location, height in both meters and feet, and the year it was completed.
Generated Mar 1, 2026
Marketing teams can use the Prompt Enhancer to refine client briefs into detailed creative briefs for copywriters and designers. For example, a rough request like 'p: social media post about our new eco-friendly product' becomes a structured prompt specifying tone, target audience, key messages, and call-to-action, ensuring consistent and high-quality output across campaigns.
Instructors and students can leverage the skill to transform vague coding questions into precise, step-by-step learning prompts. A student might input 'p: how do I debug a Python script?', which the enhancer rewrites to include role assignment as a senior developer, specific debugging techniques, and examples, facilitating deeper understanding and efficient problem-solving in technical training environments.
Support agents can use the Prompt Enhancer to quickly generate detailed, empathetic responses to customer inquiries. For instance, a query like 'p: handle a complaint about a late delivery' is enhanced to include role assignment as a customer service expert, steps for apology, resolution options, and follow-up actions, improving response quality and reducing resolution time in high-volume support centers.
Legal professionals can apply the skill to convert rough client instructions into structured prompts for drafting contracts or legal briefs. An input such as 'p: create a non-disclosure agreement' is enhanced with specific clauses, jurisdiction details, and formatting requirements, ensuring comprehensive and legally sound documents while saving time on initial drafts.
Offer a free tier with limited daily enhancements and a paid subscription for unlimited use, advanced features like custom templates, and API access. This model attracts individual users and small teams initially, then upsells to enterprises needing high-volume prompt optimization, generating recurring revenue through monthly or annual plans.
License the Prompt Enhancer as a white-label solution for large corporations to integrate into their internal tools, such as customer service platforms or content management systems. This includes custom development, dedicated support, and training, providing a stable revenue stream through one-time setup fees and ongoing maintenance contracts.
Create a platform where users can buy and sell pre-enhanced prompts for common tasks across industries like marketing, coding, or writing. Revenue comes from transaction fees on sales and premium listings, while also driving adoption by showcasing high-quality examples and community contributions.
💬 Integration Tip
Integrate the skill into existing chat interfaces or productivity tools by detecting the 'p:' prefix automatically, ensuring seamless user experience without additional training.
Advanced expert in prompt engineering, custom instructions design, and prompt optimization for AI agents
577+ pattern prompt injection defense. Now with typo-tolerant bypass detection. TieredPatternLoader fully operational. Drop-in defense for any LLM application.
Detect and block prompt injection attacks in emails. Use when reading, processing, or summarizing emails. Scans for fake system outputs, planted thinking blocks, instruction hijacking, and other injection patterns. Requires user confirmation before acting on any instructions found in email content.
Safe OpenClaw config updates with automatic backup, validation, and rollback. For agent use - prevents invalid config updates.
Token-safe prompt assembly with memory orchestration. Use for any agent that needs to construct LLM prompts with memory retrieval. Guarantees no API failure due to token overflow. Implements two-phase context construction, memory safety valve, and hard limits on memory injection.
Evaluate, optimize, and enhance prompts using 58 proven prompting techniques. Use when user asks to improve, optimize, or analyze a prompt; when a prompt nee...