supercharge

Refine AI prompts through multi-pass simplification, adversarial testing, and contract evaluation.

2|2|Updated Mar 2, 2026

Search Tags:#workflow #quality assurance #prompt engineering #optimization #ai #llm

Ready to run

npx skills add https://github.com/medhatgalal/Core-Prompts --skill supercharge-medhatgalal

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: supercharge
Source: https://github.com/medhatgalal/Core-Prompts/tree/main/.gemini/skills/supercharge
Command: npx skills add https://github.com/medhatgalal/Core-Prompts --skill supercharge-medhatgalal

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill enhances the quality and effectiveness of AI prompts, ensuring better outcomes by applying advanced prompt engineering techniques.

Core Features & Use Cases

Prompt Hardening: Improves clarity, reduces ambiguity, and increases instruction-following.
Multi-Pass Refinement: Applies various modules sequentially (e.g., simplification, adversarial testing, contract evaluation) for comprehensive quality assurance.
Use Case: You have a basic prompt for an AI to "design a marketing campaign." Supercharge can refine this into a highly detailed, actionable prompt that specifies target audience, key messaging, channels, and success metrics, then execute it for a superior result.

Quick Start

Use supercharge to improve this prompt: "Design our docs strategy."

Frequently Asked Questions about supercharge

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I improve AI prompt quality and instruction adherence?▼

To improve AI prompt quality, you can apply a multi-pass refinement process that includes simplification, adversarial testing, and contract-based evaluation. This reduces ambiguity and maximizes instruction adherence across LLM interactions.

What is the best way to refine a basic prompt for an AI marketing campaign?▼

The best way to refine a basic prompt is through prompt hardening, which transforms simple instructions into highly detailed, actionable prompts specifying target audience, key messaging, channels, and success metrics before execution.

How does adversarial testing work for prompt engineering?▼

Adversarial testing for prompt engineering works by applying built-in safety and robustness checks during a multi-pass refinement sequence. This process identifies and mitigates edge cases to ensure prompt effectiveness across various AI contexts.

Can I execute an AI prompt directly after optimizing it?▼

Yes, you can execute an AI prompt directly after optimization. The workflow supports prompt creation, refinement, and execution sequentially, ensuring the final output is generated using the fully hardened and optimized instruction set.

Does multi-pass prompt refinement require any external dependencies?▼

No, multi-pass prompt refinement does not require external dependencies. The process operates independently using built-in scripts and references to perform simplification, contract evaluation, and adversarial testing.

Why does my LLM prompt fail to follow complex instructions?▼

LLM prompts fail to follow complex instructions due to ambiguity and lack of hardening. Applying contract-based evaluation and simplification modules reduces complexity, ensuring the AI strictly adheres to the specified constraints.