feat: convert ai-optimizer from cron job to manual skill

- Update README.md for manual execution workflow
- Change model queue to deepseek-coder-v2:16b (better coding model)
- Remove automated scheduling references
- Add skill usage instructions for post-PR#1 merge

assets/ai-optimizer/state.json

@@ -1,6 +1,6 @@
 {
   "track": "gpu",
-  "current_model": "devstral-small-2:24b",
+  "current_model": "deepseek-coder-v2:16b",
   "model_index": 0,
   "phase": "context_scaling",
   "backend": "ollama",
@@ -14,8 +14,8 @@
     "ram": {}
   },
   "completed_models": [],
-  "gpu_queue": ["devstral-small-2:24b", "qwen2.5-coder:32b", "codellama:34b-instruct"],
+  "gpu_queue": ["deepseek-coder-v2:16b", "qwen2.5-coder:32b", "codellama:34b-instruct"],
   "ram_queue": ["qwen2.5:72b", "nemotron-3-nano:30b", "mixtral:8x7b-instruct"],
   "context_steps": [32768, 65536, 98304, 131072, 163840, 200704, 262144, 327680],
-  "last_updated": "2026-04-28T17:00:00Z"
+  "last_updated": "2026-04-30T00:00:00Z"
 }