prompt-doctor

What problem does it solve?

This Skill addresses issues with unstable, inaccurate, or insecure AI prompts by systematically diagnosing and rewriting them to be clearer, more executable, and safer.

Core Features & Use Cases

• Prompt Diagnosis: Identifies specific problems like format inconsistencies, hallucinations, prompt injection vulnerabilities, and tool misuse.
• Structured Rewriting: Transforms vague prompts into structured instructions with defined roles, goals, inputs, tool constraints, output schemas, and refusal policies.
• Security Enhancement: Implements strategies to prevent prompt injection and protect sensitive information.
• Test Case Generation: Provides minimal, usable test cases to verify the rewritten prompt's effectiveness.
• Use Case: You have a complex system prompt for an AI customer service agent that sometimes provides incorrect information or is susceptible to user manipulation. Use this Skill to analyze the prompt, identify its weaknesses, and generate a robust, secure, and reliable version.

Quick Start

Use the prompt-doctor skill to diagnose and rewrite the provided system prompt.