feat(kanban): aggregate all toolset-name typos in skills before raising

Follow-up to the previous commit's toolset-vs-skill validation.

The contributor's fix raises ValueError on the first toolset name found
in the skills list. That works for one mistake, but agents that confuse
skills with toolsets usually pass several at once
(`skills=["web", "browser", "terminal"]`) — and serial-correcting one
per failure round-trip wastes tokens. Collect all toolset-shaped
entries first, then raise once with the full list.

The error message is also slightly clearer:

    'web', 'browser', 'terminal' are toolset names, not skill name(s).
    Put toolsets in the assignee profile's `toolsets:` config instead of
    per-task skills. Skills are named skill bundles (e.g. `kanban-worker`,
    `blogwatcher`); toolsets are runtime capabilities (e.g. `web`,
    `browser`, `terminal`).

vs. the previous "the assignee profile's toolsets" — explicitly naming
the YAML key (`toolsets:`) and giving concrete examples in both
categories closes the conceptual gap that produced the bug to begin
with.

Adds one regression test (test_create_task_skills_lists_all_toolset_typos)
covering the multi-name aggregation path. The single-typo test from
the original PR still passes (the loose `match="toolset name"` matches
both singular and plural forms).

tests/hermes_cli/test_kanban_core_functionality.py

@@ -2706,6 +2706,33 @@ def test_create_task_skills_rejects_toolset_names(kanban_home):
         conn.close()
 
 
+def test_create_task_skills_lists_all_toolset_typos(kanban_home):
+    """When several toolset names are passed, the error names every one.
+
+    Agents that confuse skills with toolsets usually pass several at once
+    (``skills=["web", "browser", "terminal"]``). Listing only the first
+    mistake forces serial fix-then-retry; listing all of them lets the
+    caller correct in one round-trip.
+    """
+    conn = kb.connect()
+    try:
+        with pytest.raises(ValueError) as exc_info:
+            kb.create_task(
+                conn,
+                title="three bad",
+                assignee="x",
+                skills=["web", "browser", "terminal"],
+            )
+        msg = str(exc_info.value)
+        assert "'web'" in msg
+        assert "'browser'" in msg
+        assert "'terminal'" in msg
+        # Plural noun form when multiple toolsets are flagged.
+        assert "are toolset names" in msg
+    finally:
+        conn.close()
+
+
 def test_default_spawn_appends_per_task_skills(kanban_home, monkeypatch):
     """Dispatcher argv must carry one `--skills X` pair per task skill,
     in addition to the built-in kanban-worker."""