Add story-to-pack research and a structured situation review

Research toward building a content pack from a story corpus, kept on its own
branch and independent of the game. Records the selection experiments against
blind labels, and settles selection as gate G2 followed by a human review:
review.py writes REVIEW.md and a review.json form, apply_review.py checks the
filled form and writes situations.json for the next stage.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01C6UDQ9o6L6Ey173U7XVou6

tools/story-to-pack/probe/summary_embeddings.measure.json

@@ -0,0 +1,42 @@
+{
+ "file": "summary_embeddings.json",
+ "chunks": 838,
+ "rows": [
+  {
+   "k": 25,
+   "sized": 25,
+   "median_dominant": 0.13636363636363635,
+   "recurring": 23,
+   "coverage": 0.9737470167064439,
+   "tight_recurring": 11,
+   "tight_coverage": 0.39737470167064437
+  },
+  {
+   "k": 40,
+   "sized": 36,
+   "median_dominant": 0.17444219066937122,
+   "recurring": 32,
+   "coverage": 0.9463007159904535,
+   "tight_recurring": 14,
+   "tight_coverage": 0.3568019093078759
+  },
+  {
+   "k": 60,
+   "sized": 51,
+   "median_dominant": 0.2222222222222222,
+   "recurring": 41,
+   "coverage": 0.8651551312649165,
+   "tight_recurring": 18,
+   "tight_coverage": 0.2613365155131265
+  },
+  {
+   "k": 100,
+   "sized": 70,
+   "median_dominant": 0.2792207792207792,
+   "recurring": 50,
+   "coverage": 0.7303102625298329,
+   "tight_recurring": 20,
+   "tight_coverage": 0.18973747016706444
+  }
+ ]
+}