result to prompt rebuilder

The problem

Reverse-engineering a prompt from a successful output is tedious and prone to error. Manually identifying which parts of a result are static instructions versus dynamic variables often leads to "leaky" templates that fail on new inputs.

What it does

• Analyzes a single example output and its source input values to map data flow.
• Separates variable-driven content from fixed structural instructions and formatting constraints.
• Reconstructs a clean, imperative prompt template using double-curly-brace placeholders.
• Generates a PromptBase-style INPUTS block for standardized execution.
• Produces an inference ledger that flags every rule as observed or speculative for targeted testing.

Why this beats prompting it yourself

This skill moves beyond guessing. It uses a structured evidence map to distinguish between coincidence and intent, preventing you from hard-coding incidental details that break your prompt's versatility. It provides a formal test plan to validate the reconstruction across edge cases immediately.

Use cases

• Turn a one-off successful AI response into a reusable tool or a sellable PromptBase product.
• Recover lost prompt logic when you only have the historical logs of inputs and outputs.
• Standardize internal prompt libraries by converting varied examples into a consistent template format.
• Debug why a prompt works by isolating the specific rules that drive the successful output.

Known limitations

Requires both the complete output and the exact input values that generated it. It reconstructs behavior, not the original author's exact wording.