feat(polymarket): outcome-aware scoring and synthesis instructions

- _compute_text_similarity() now checks outcome names with bidirectional
  substring matching (0.85) and token overlap (0.7), not just event titles
- Collect outcomes from ALL active markets per event, filter to >1% price
- Reorder outcome_prices to surface topic-matching outcome before top-3 truncation
- Add SKILL.md "Prediction Markets" synthesis section with structural/long-term
  market preference, domain examples, citation format, and narrative weaving
- Add Polymarket to citation priority list between HN and Web
- Update stats box template to show up to 5 market odds
- Fix render.py "vol24h" label to "volume"
- Add NCAA seed fixture event for outcome-only matching tests
- 82 polymarket tests pass (14 new)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

scripts/lib/render.py

@@ -295,11 +295,11 @@ def render_compact(report: schema.Report, limit: int = 15, missing_keys: str = "
                 parts = []
                 if eng.volume is not None:
                     if eng.volume >= 1_000_000:
-                        parts.append(f"${eng.volume/1_000_000:.1f}M vol24h")
+                        parts.append(f"${eng.volume/1_000_000:.1f}M volume")
                     elif eng.volume >= 1_000:
-                        parts.append(f"${eng.volume/1_000:.0f}K vol24h")
+                        parts.append(f"${eng.volume/1_000:.0f}K volume")
                     else:
-                        parts.append(f"${eng.volume:.0f} vol24h")
+                        parts.append(f"${eng.volume:.0f} volume")
                 if eng.liquidity is not None:
                     if eng.liquidity >= 1_000_000:
                         parts.append(f"${eng.liquidity/1_000_000:.1f}M liquidity")