scan-mechanicality

To evaluate prompt mechanicality, analyze the Markdown content to classify it as POSITIVO, AMBÍGUO, or NEGATIVO by extracting deterministic substrings and providing objective justification from the text. This ignores narrative metadata to focus on substantive rules.

Prompt mechanicality classification is used to determine whether agent stubs or SKILL.md content is predominantly deterministic or heuristic-semantic, enabling teams to identify where automation is feasible across embedded code blocks.

Yes, you can audit system prompts by extracting candidate substrings that map to deterministic rules. The diagnostic process provides objective justification from the text, categorizing the substance to show where mechanization is viable.

Yes, the diagnostic classification ignores prose and metadata in embedded prompts to focus exclusively on substantive content. This ensures reliable assessment of mechanically actionable substrings across different languages.

A limitation of evaluating prompt mechanicality is handling AMBÍGUO classifications, where prompt content blends deterministic rules with heuristic-semantic interpretation, making it difficult to clearly separate viable automation candidates.

The best way to classify SKILL.md content for mechanization viability is to analyze the Markdown prompt and return a POSITIVO, AMBÍGUO, or NEGATIVO classification alongside identified mechanically actionable substrings with objective justifications.