Move prompts into embedded Markdown assets

internal/prompts/assets/validators/meaning_reversal_review/user.md

@@ -0,0 +1,17 @@
+Review these proposed transcript corrections and decide whether each one avoids reversing the segment meaning.
+
+Rules:
+- Return one validation decision for every correction_index in the input.
+- Reject corrections that introduce antonyms or otherwise reverse the meaning of the original segment.
+- Reject examples like changing "visible" to "invisible" or "up" to "down" when that reverses the segment meaning.
+- Evaluate the full original_segment_text and corrected_segment_text, not only the replacement span.
+- Do not reject a correction merely because the literal written word changes.
+- Do not act as a general semantic-style reviewer; this validator is only a guard against antonyms and meaning reversals.
+- If a correction includes categories, treat them as additional segment context.
+- Each returned validation must contain only correction_index, approved, confidence, and reason.
+- confidence must be between 0.0 and 1.0.
+
+{{ hardening }}
+
+{{ .TranscriptDescriptionBlock }}Corrections to validate:
+{{ .PayloadJSON }}