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/implementing-security-information-sharing-with-stix2/SKILL.md

@@ -1,8 +1,10 @@
 ---
 name: implementing-security-information-sharing-with-stix2
-description: 'Create, validate, and share STIX 2.1 threat intelligence objects using
-  the stix2 Python library. Covers indicators, malware, campaigns, relationships,
-  bundles, and TAXII 2.1 publishing.
+description: 'Create, validate, and share STIX 2.1 threat intelligence objects (indicators,
+  malware, campaigns, relationships, bundles) using the stix2 Python library, and
+  publish them over TAXII 2.1. Use when building or exchanging structured threat
+  intelligence, modeling relationships between threat objects, or publishing/consuming
+  a TAXII 2.1 feed.
 
   '
 domain: cybersecurity