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/eradicating-malware-from-infected-systems/SKILL.md

@@ -1,7 +1,11 @@
 ---
 name: eradicating-malware-from-infected-systems
-description: Systematically remove malware, backdoors, and attacker persistence mechanisms
-  from infected systems while ensuring complete eradication and preventing re-infection.
+description: Systematically map and remove malware, backdoors, and attacker persistence
+  mechanisms (registry Run keys, scheduled tasks, WMI subscriptions, services, cron/init.d)
+  from infected Windows and Linux systems using Autoruns, EDR/AV, and YARA, restoring a
+  clean state while preventing re-infection. Use after containment and forensic analysis
+  have identified all compromised systems and persistence mechanisms and you are ready to
+  eradicate and recover.
 domain: cybersecurity
 subdomain: incident-response
 tags: