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>

poc-memory/Cargo.toml

@@ -24,6 +24,7 @@ jobkit-daemon = { path = "../jobkit-daemon" }
 redb = "2"
 log = "0.4"
 ratatui = "0.29"
+skillratings = "0.28"
 crossterm = { version = "0.28", features = ["event-stream"] }
 
 [build-dependencies]