refactor(reload-skills): queue note for next turn, drop cache invalidation + agent tool

Salvage-follow-up to @shannonsands's /reload-skills PR. Trims the feature to
match the design: user-initiated rescan, no prompt-cache reset, no new
schema surface, no phantom user turn, and the next-turn note carries each
added/removed skill's 60-char description (not just its name).

Changes vs the original PR:

* Drop the in-process skills prompt-cache clear in reload_skills(). Skills
  are invoked at runtime via /skill-name, skills_list, or skill_view —
  they don't need to live in the system prompt for the model to use them.
  Keeping the cache intact preserves prefix caching across the reload so
  /reload-skills pays no cache-reset cost. (MCP has to break the cache
  because tool schemas must be known at conversation start; skills do not.)

* Drop the skills_reload agent tool and SKILLS_RELOAD_SCHEMA from
  tools/skills_tool.py, plus the four skills_reload enumerations in
  toolsets.py. No new schema surface — agents can already see a freshly-
  installed skill via skill_view / skills_list the moment it's on disk.

* Replace the phantom 'role: user' turn injection with a one-shot queued
  note. CLI uses self._pending_skills_reload_note (same pattern as
  _pending_model_switch_note, prepended to the next API call and cleared).
  Gateway uses self._pending_skills_reload_notes[session_key]. The note
  is prepended to the NEXT real user message in this session, so message
  alternation stays intact and nothing out-of-band is persisted to the
  transcript.

* reload_skills() now returns added/removed as
  [{'name': str, 'description': str}, ...] (description truncated to 60
  chars — matches the curator / gateway adapter budget). The injected
  next-turn note formats each entry as 'name — description' so the model
  can actually reason about which new skills to call without running
  skills_list first.

* Only emit the note when the diff is non-empty. On empty diff, print
  'No new skills detected' and do nothing else.

* Tests rewritten to cover the queue semantics, the description payload,
  and a regression guard that the prompt-cache snapshot is preserved.

toolsets.py

@@ -38,7 +38,7 @@ _HERMES_CORE_TOOLS = [
     # Vision + image generation
     "vision_analyze", "image_generate",
     # Skills
-    "skills_list", "skill_view", "skill_manage", "skills_reload",
+    "skills_list", "skill_view", "skill_manage",
     # Browser automation
     "browser_navigate", "browser_snapshot", "browser_click",
     "browser_type", "browser_scroll", "browser_back",
@@ -105,7 +105,7 @@ TOOLSETS = {
     
     "skills": {
         "description": "Access, create, edit, and manage skill documents with specialized instructions and knowledge",
-        "tools": ["skills_list", "skill_view", "skill_manage", "skills_reload"],
+        "tools": ["skills_list", "skill_view", "skill_manage"],
         "includes": []
     },
     
@@ -279,7 +279,7 @@ TOOLSETS = {
             "terminal", "process",
             "read_file", "write_file", "patch", "search_files",
             "vision_analyze",
-            "skills_list", "skill_view", "skill_manage", "skills_reload",
+            "skills_list", "skill_view", "skill_manage",
             "browser_navigate", "browser_snapshot", "browser_click",
             "browser_type", "browser_scroll", "browser_back",
             "browser_press", "browser_get_images",
@@ -303,7 +303,7 @@ TOOLSETS = {
             # Vision + image generation
             "vision_analyze", "image_generate",
             # Skills
-            "skills_list", "skill_view", "skill_manage", "skills_reload",
+            "skills_list", "skill_view", "skill_manage",
             # Browser automation
             "browser_navigate", "browser_snapshot", "browser_click",
             "browser_type", "browser_scroll", "browser_back",