diff --git a/hermes_cli/sessions_cmd.py b/hermes_cli/sessions_cmd.py
index ba4d004bf7..c27cbf92f7 100644
--- a/hermes_cli/sessions_cmd.py
+++ b/hermes_cli/sessions_cmd.py
@@ -974,8 +974,6 @@ def _cmd_repair_routing(db, args):
     print(f"\nRepaired {repaired} of {len(adoptable)} session(s).")
 
 
-_SKILL_TOOL_NAMES = frozenset({"skills_list", "skill_view", "skill_manage"})
-_SKILLS_INDEX_MARKER = "<available_skills>"
 _SKILLS_GUIDANCE_MARKER = "## Skill Safety"
 _HYGIENE_PIN_TOOLS = frozenset({"memory"})
 
@@ -1010,26 +1008,22 @@ def _repair_prompts_pin_names(row) -> list[str] | None:
 
 
 def _repair_prompts_missing_skills_markers(row) -> bool:
+    # Only the Skill Safety guidance is a reliable marker: <available_skills> is legitimately
+    # absent when no skills are installed, but the guidance is emitted whenever skill_manage is.
     prompt = (row.get("system_prompt") or "").strip()
-    return bool(
-        prompt
-        and _SKILLS_INDEX_MARKER not in prompt
-        and _SKILLS_GUIDANCE_MARKER not in prompt
-    )
+    return bool(prompt and _SKILLS_GUIDANCE_MARKER not in prompt)
 
 
 def _repair_prompts_degraded_reason(row) -> str:
-    """Why the stored prompt is provably a reduced-toolset build; '' without sufficient evidence."""
+    """Why the stored prompt is provably a reduced-toolset build; '' without sufficient evidence.
+
+    A memory-only pin is not proof: toolsets=[memory] is also a legitimate user config whose
+    healthy prompt has no skills markers, so clearing it would repeat on every run.
+    """
     if not _repair_prompts_missing_skills_markers(row):
         return ""
-    pin = _repair_prompts_pin_names(row)
-    if pin is None:
-        return ""
-    names = set(pin)
-    if any(name in names for name in _SKILL_TOOL_NAMES):
-        return "skills index missing while the tools[] pin carries skill tools"
-    if names == _HYGIENE_PIN_TOOLS:
-        return "skills index missing and the tools[] pin is the reduced memory-only set"
+    if "skill_manage" in (_repair_prompts_pin_names(row) or ()):
+        return "Skill Safety guidance missing while the tools[] pin carries skill_manage"
     return ""
 
 
@@ -1086,10 +1080,16 @@ def _cmd_repair_prompts(db, args):
                 "prompt_chars": len(row["system_prompt"] or ""),
                 "clear_pin": set(pin or ()) == _HYGIENE_PIN_TOOLS,
             })
-        elif _repair_prompts_missing_skills_markers(row) and pin is None:
+        elif _repair_prompts_missing_skills_markers(row) and (
+            pin is None or set(pin) == _HYGIENE_PIN_TOOLS
+        ):
             unverifiable.append({
                 "id": row["id"],
-                "reason": "skills markers missing but the tools[] pin is unavailable or unreadable",
+                "reason": (
+                    "skills markers missing but the tools[] pin is unavailable or unreadable"
+                    if pin is None else
+                    "memory-only tools[] pin may be a user toolset; clear explicitly by SESSION_ID"
+                ),
                 "prompt_chars": len(row["system_prompt"] or ""),
             })
 
@@ -1118,7 +1118,7 @@ def _cmd_repair_prompts(db, args):
             suffix = " (tools[] pin cleared too)" if finding["clear_pin"] else ""
             print(f"  {finding['id']}  ({finding['prompt_chars']} chars) - {finding['reason']}{suffix}")
         if unverifiable:
-            print(f"\nSkipped {len(unverifiable)} unverifiable row(s) with no readable tools[] pin.")
+            print(f"\nSkipped {len(unverifiable)} unverifiable row(s) without enough tools[] evidence.")
 
     if not apply:
         if as_json:
diff --git a/website/docs/reference/cli-commands.md b/website/docs/reference/cli-commands.md
index 7cc34062ff..f91f098ea6 100644
--- a/website/docs/reference/cli-commands.md
+++ b/website/docs/reference/cli-commands.md
@@ -1760,7 +1760,7 @@ Subcommands:
 | `optimize-storage` | Migrate the full-text search index to the compact v23 external-content layout; on large databases this reclaims a large fraction of `state.db`. |
 | `repair` | Repair a malformed `state.db` schema (e.g. `table messages_fts already exists`) so hidden sessions reappear; a backup is made first. |
 | `repair-routing` | Re-attach gateway conversations stranded in session rows that lost their routing identity (a chat "jumping back in time" after a restart). Dry-run by default; `--apply` performs the adoptions (stop the gateway first); `--max-gap-seconds N` tunes the contiguity window. Only unambiguous cases are repaired. See [Sessions → Repair Stranded Gateway Sessions](../user-guide/sessions.md#repair-stranded-gateway-sessions). |
-| `repair-prompts` | Report stored system prompts provably degraded by the pre-#122822 maintenance-compaction bug. Report-only by default; `--apply` clears verified rows so the next turn rebuilds them, `--json` is machine-readable (and non-interactive when combined with `--apply`), and an explicit `session_id` is a destructive override that can clear even a healthy prompt. Rows without a readable tools[] pin are reported as unverifiable and never auto-repaired. See [Sessions → Repair Degraded Stored Prompts](../user-guide/sessions.md#repair-degraded-stored-prompts). |
+| `repair-prompts` | Report stored system prompts provably degraded by the pre-#122822 maintenance-compaction bug. Report-only by default; `--apply` clears verified rows so the next turn rebuilds them, `--json` is machine-readable (and non-interactive when combined with `--apply`), and an explicit `session_id` is a destructive override that can clear even a healthy prompt. Rows without a readable tools[] pin, or with a memory-only pin, are reported as unverifiable and never auto-repaired. Restart a running gateway after `--apply` so repaired rows take effect. See [Sessions → Repair Degraded Stored Prompts](../user-guide/sessions.md#repair-degraded-stored-prompts). |
 | `repair-profiles` | Settle session, routing, Telegram-topic and voice-mode state that landed under the wrong profile (rows in another profile's store, labels disagreeing with the session key, parent links crossing profiles, index rows for deleted profiles). Dry-run by default; `--apply` performs the repairs after snapshotting every store (stop the gateway first); `--legacy-main rekey\|move` decides what `agent:main` rows inside a named profile's store are; `--json` for automation. See [Sessions → Repair State Crossed Between Profiles](../user-guide/sessions.md#repair-state-crossed-between-profiles). |
 | `recover` | Offline, non-destructive recovery of a damaged `state.db` into a separate clean database. |
 | `retitle-skills` | Regenerate titles for sessions opened with a `/skill`, using what the user actually typed; lists changes unless `--apply` is passed. |
diff --git a/website/docs/user-guide/sessions.md b/website/docs/user-guide/sessions.md
index c03b7a616a..778103063d 100644
--- a/website/docs/user-guide/sessions.md
+++ b/website/docs/user-guide/sessions.md
@@ -666,10 +666,11 @@ live session. After the root fix in PR #122825 is installed, use
 `hermes sessions repair-prompts` to find rows that were already degraded.
 
 The scan is conservative: it only proposes a repair when the stored prompt is
-missing the skills markers **and** the persisted `tools[]` pin proves either
-that skill tools belonged to the session or that the pin is exactly the
-maintenance `memory`-only surface. Older or malformed rows with no readable
-pin are reported as **unverifiable** and are never changed automatically.
+missing the `## Skill Safety` guidance **and** the persisted `tools[]` pin
+contains `skill_manage` (which always emits that guidance). Rows with no
+readable pin, or with a `memory`-only pin (which is also a legitimate
+`toolsets: [memory]` setup), are reported as **unverifiable** and are never
+changed automatically; clear them explicitly by `SESSION_ID` if needed.
 
 ```bash
 # Report verified candidates and unverifiable rows; writes nothing
@@ -689,8 +690,8 @@ hermes sessions repair-prompts --apply --json
 hermes sessions repair-prompts SESSION_ID --apply
 ```
 
-A verified memory-only `tools[]` pin is cleared together with the prompt so
-the next live turn can pin the real surface again. Clearing the prompt
+With an explicit `SESSION_ID`, a memory-only `tools[]` pin is cleared together
+with the prompt so the next live turn can pin the real surface again. Clearing the prompt
 intentionally stores NULL; the next turn rebuilds and persists healthy bytes,
 which causes one expected
 `Stored system prompt ... is null; rebuilding from scratch` warning for each
@@ -700,6 +701,10 @@ evidence of a new corruption.
 Run the repair only after the #122822 root fix is present; otherwise a later
 maintenance compaction can degrade the row again.
 
+A running gateway keeps each cached session's old prompt in memory, so restart
+the gateway after `--apply` (`hermes gateway restart`) for repaired rows to
+take effect.
+
 ### Repair State Crossed Between Profiles
 
 Every profile owns one `state.db`, and every gateway session key names the