The problem

Most prompt engineers focus entirely on technical execution while ignoring market viability. You spend weeks refining a prompt only to realize no one wants to buy it, it sounds exactly like a basic ChatGPT request, or it overpromises and underdelivers.

What it does

• Identifies specific failure patterns like "Generic AI Slop" or "Promise-Delivery Mismatch" using a library of 20 forensic categories.
• Scores your prompt or product listing across five diagnostic dimensions including Prompt Mechanics and Marketability.
• Delivers a definitive Kill, Revive, or Reposition verdict to prevent wasted development time.
• Analyzes buyer-side damage to determine why potential customers are bouncing from your listing.
• Provides a remediation priority matrix to separate high-impact fixes from low-value polish.

Why this beats prompting it yourself

Typical LLMs are too polite and default to vague encouragement. This skill is professionally cynical, strictly following internal score caps and failure patterns to find the exact reason a product is underperforming without softening the blow.

Use cases

• Audit a PromptBase or Gumroad listing that has high views but zero conversions.
• Decide whether to abandon a prompt project or pivot to a new target audience.
• Vetting a prompt pack's structural integrity before a public launch.
• Diagnosing why a custom GPT or AI tool feels "thin" or "generic" to users.

Known limitations

This skill measures commercial and structural viability, not platform-specific algorithm behavior or SEO rankings.