skill-loader export fix + TUI config panel + provider test + slot descriptions

- Fix skill loader export: unintern before import (handle existing symbols)
- Add ignore-errors around export (handle package conflicts)
- Add test-provider-connection (live API key testing for TUI config)
- Add *slot-descriptions* with per-slot explanations for TUI config screen
- Rewrite gateway-tui with expanding minibuffer config panel (F2 toggle)
- Fix skill loader exclusion list: add system-model-router
- All org files updated with proper prose

lisp/system-model-explorer.lisp

@@ -60,4 +60,10 @@
     (:background
      '((:id "meta-llama/llama-3.2-3b-instruct:free" :name "Llama 3.2 3B" :context 131072 :free t :note "Small, fast, efficient")
        (:id "liquid/lfm-2.5-1.2b-instruct:free" :name "LFM 2.5 1.2B" :context 32768 :free t :note "Ultra-compact, edge-ready")))
-    (t '((:id "meta-llama/llama-3.3-70b-instruct:free" :name "Llama 3.3 70B" :context 65536 :free t :note "Safe fallback")))))
+     (t '((:id "meta-llama/llama-3.3-70b-instruct:free" :name "Llama 3.3 70B" :context 65536 :free t :note "Safe fallback")))))
+
+(defvar *slot-descriptions*
+  '((:code . "Code generation, refactoring, debugging. Needs strong reasoning and large context.\nRecommend: Qwen3 Coder (free, 35B active) or Laguna M.1 (coding agent).")
+    (:chat . "Casual conversation, Q&A, creative writing. Prefer balanced quality, low latency.\nRecommend: Llama 3.3 70B (strong generalist) or Gemma 4 31B (thinking mode).")
+    (:plan . "Strategic planning, architecture design, complex multi-step reasoning.\nRecommend: Owl Alpha (free, tool use, 1M ctx) or Hermes 3 405B (strongest free reasoning).")
+    (:background . "Heartbeat summaries, delegation responses, tool output filtering. Must be small + fast.\nRecommend: Llama 3.2 3B (131K ctx, fast) or LFM 2.5 1.2B (edge-ready).")))