evaluate: switch to Elo ratings with skillratings crate

Replace sort-based ranking with proper Elo system:
- Each agent TYPE has a persistent Elo rating (agent-elo.json)
- Each matchup: pick two random types, grab a recent action from
  each, LLM compares, update ratings
- Ratings persist across daily evaluations — natural recency bias
  from continuous updates against current opponents
- K=32 for fast adaptation to prompt changes

Usage: poc-memory agent evaluate --matchups 30 --model haiku

Co-Authored-By: Kent Overstreet <kent.overstreet@linux.dev>

Cargo.lock

@@ -1908,6 +1908,7 @@ dependencies = [
  "rkyv",
  "serde",
  "serde_json",
+ "skillratings",
  "uuid",
 ]
 
@@ -2615,6 +2616,12 @@ version = "0.1.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "e3a9fe34e3e7a50316060351f37187a3f546bce95496156754b601a5fa71b76e"
 
+[[package]]
+name = "skillratings"
+version = "0.28.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1a6ee7559737c1adcd9184f168a04dc360c84878907c3ecc5c33c2320be1d47a"
+
 [[package]]
 name = "slab"
 version = "0.4.12"