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/recover.log

@@ -0,0 +1,10 @@
+seed 13: 42 candidates; B accepts 4
+M1: pool 729, k=36; accepts 4 (0 new)
+M2: accepts 3
+M3: accepts 16 (12 recovered by pruning); scenes in >1 cluster: 68
+blind sheet: 21 distinct clusters, 576 lines
+
+real	0m54.699s
+user	0m39.193s
+sys	0m14.866s
+exit 0