fix(skills): pin protects against deletion only, not edits (#20220)

Previously, pinning a skill blocked every skill_manage write action
(edit, patch, delete, write_file, remove_file). The 'hard fence'
design conflated two concerns:

  1. Pin as deletion protection — don't let the curator archive
     or the agent delete a stable skill.
  2. Pin as content freeze — don't let the agent rewrite it mid-conversation.

In practice (1) is what users pin for: they want a skill to survive
curator passes. (2) created friction — agents finding a new pitfall
in a pinned skill had to ask the user to unpin, then the agent
patches, then the user re-pins. The dance discouraged skill
maintenance and pinned skills went stale.

This narrows the _pinned_guard to skill_manage(action='delete') only.
Patches, edits, and supporting-file writes go through on pinned
skills so the agent can keep improving them. The curator's own
pinned-skip behavior (agent/curator.py:271 for auto-archive,
line 349 for the LLM review prompt) is unchanged — curator still
never touches pinned skills.

Changes:
- tools/skill_manager_tool.py: remove _pinned_guard calls from
  _edit_skill, _patch_skill, _write_file, _remove_file; keep on
  _delete_skill. Updated _pinned_guard docstring and error message.
- tools/skill_manager_tool.py: updated skill_manage model-facing tool
  description to reflect the new semantic.
- website/docs/user-guide/features/curator.md: updated pinning
  section.
- tests/tools/test_skill_manager_tool.py: flipped refuses-pinned
  tests for edit/patch/write_file/remove_file into allowed-when-pinned;
  kept test_delete_refuses_pinned (strengthened assertion to check the
  'cannot be deleted' wording).

Closes #18354

website/docs/user-guide/features/curator.md

@@ -157,10 +157,10 @@ If you want to protect a specific skill from ever being touched — for example
 
 ## Pinning a skill
 
-Pinning is a hard fence against both automated and agent-driven changes. Once a skill is pinned:
+Pinning protects a skill from deletion — both the curator's automated archive passes and the agent's `skill_manage(action="delete")` tool call. Once a skill is pinned:
 
 - The **curator** skips it during auto-transitions (`active → stale → archived`), and its LLM review pass is instructed to leave it alone.
-- The **agent's `skill_manage` tool** refuses every write action on it. Calls to `edit`, `patch`, `delete`, `write_file`, and `remove_file` return a refusal that tells the model to ask the user to run `hermes curator unpin <name>`. This prevents the agent from silently rewriting a skill mid-conversation.
+- The **agent's `skill_manage` tool** refuses `delete` on it, pointing the user at `hermes curator unpin <name>`. Patches and edits still go through, so the agent can improve a pinned skill's content as pitfalls come up without a pin/unpin/re-pin dance.
 
 Pin and unpin with:
 
@@ -173,7 +173,7 @@ The flag is stored as `"pinned": true` on the skill's entry in `~/.hermes/skills
 
 Only **agent-created** skills can be pinned — bundled and hub-installed skills are never subject to curator mutation in the first place, and `hermes curator pin` will refuse with an explanatory message if you try.
 
-If you need to update a pinned skill yourself, edit `~/.hermes/skills/<name>/SKILL.md` directly with your editor. The pin only guards the agent's tool path, not your own filesystem access.
+If you want a stronger guarantee than "no deletion" — for instance, freezing a skill's content entirely while the agent still reads it — edit `~/.hermes/skills/<name>/SKILL.md` directly with your editor. The pin guards tool-driven deletion, not your own filesystem access.
 
 ## Usage telemetry