fix: add unnecessary negative contrast detection to voice linting

- New lint check: 'doesn't just X. They Y' pattern (Claude rhetorical crutch)
- Fixed last instance in judgment essay: 'doesn't just lose income. They lose'
  → 'loses the acknowledgment... The income is secondary.'
- Updated voice-check skill dimension 2 with the pattern description
- Updated AGENTS.md with the new check
- Tightened regex to avoid false positives on legitimate 'isn't only' framing

🤖 Generated with Amplifier

Co-Authored-By: Amplifier <240397093+microsoft-amplifier@users.noreply.github.com>

.amplifier/AGENTS.md

@@ -33,6 +33,7 @@ with full awareness of what's wrong.
 - Em-dash density (>5 per post = FAIL, Claude fingerprint)
 - AI trigger words (delve, tapestry, nuanced, landscape, etc.)
 - Hedging phrases ("it's worth noting", "one might argue")
+- Unnecessary negative contrast ("doesn't just X. They Y" -- Claude crutch)
 - Filler transitions ("in conclusion", "that being said")
 - Resolution closers ("the key takeaway", "at the end of the day")
 - Missing receipts (0 links + 0 code + 0 URLs in 500+ words = WARN)

.amplifier/skills/voice-check/SKILL.md

@@ -61,6 +61,12 @@ Does the writing hedge when it should assert? Look for:
   clearly believes
 - Passive constructions that hide the actor ("it was found" vs "I found")
 - False balance ("on the other hand" when there IS no valid other hand)
+- **Unnecessary negative contrast**: the "doesn't just X. They Y" or "isn't
+  only X. It's Y" pattern. This is a Claude rhetorical crutch that creates
+  the *appearance* of depth through contrast without saying anything the
+  second clause didn't already imply. Example: "A doctor doesn't just lose
+  income. They lose the acknowledgment that..." Fix: state Y directly.
+  "A doctor loses the acknowledgment that..."
 
 The voice profile says: "High, earned. States opinions as conclusions from
 experience, not as positions to defend."