Rewrite 548 skill descriptions to the activation rubric

Each rewritten description now states both what the skill does (concrete
capability, named tools/artifacts) and an explicit when-to-use trigger,
improving agent discovery/activation. Grounded in each skill's own body;
changes confined to the `description` field only (bodies and all other
frontmatter untouched). Produced by a gated audit->rewrite->recheck loop
(548 -> 0 flagged) with a sampled anti-invention check (0 ungrounded).

Schema: 817/817 pass. Framework-ID gate: 0 defects.

skills/performing-privilege-escalation-on-linux/SKILL.md

@@ -1,8 +1,10 @@
 ---
 name: performing-privilege-escalation-on-linux
-description: Linux privilege escalation involves elevating from a low-privilege user
-  account to root access on a compromised system. Red teams exploit misconfigurations,
-  vulnerable services, kernel exploits, and w
+description: Guides manual enumeration and automated tooling to escalate from a low-privilege
+  Linux user to root by exploiting misconfigurations, vulnerable services, kernel exploits,
+  and weak permissions, mapped to MITRE ATT&CK. Use during authorized red team engagements
+  or penetration tests once initial low-privilege access on a Linux host is obtained
+  and root-level access is needed.
 domain: cybersecurity
 subdomain: red-teaming
 tags: