{"version":"2.1.287","anchor":"strict-relay-post-added-and-skill-mention-attachment-type","canonical_anchor":"strict-relay-post-added-and-skill-mention-attachment-type","heading":"Claude is told when your message mentions a skill by name","tier":"notice","area":"Skills","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.287\/e\/strict-relay-post-added-and-skill-mention-attachment-type","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.287","markdown":"### Claude is told when your message mentions a skill by name\n\nWhen a message contains \/, Claude Code can tell the model and ask it to run the skill only if you want it run\n\n**Unclear.** It is not clear whether either change is switched on, or which setting chooses the stricter relay.\n\n**What**\n\nSkills are saved instructions Claude can run on request. Claude Code can now attach a note when your message contains `\/<skill>`, the name of a skill. The note tells the model that the message mentions the skill, and to use the Skill tool only if you are asking for the skill to be run. This sits alongside the notes for mentioning agents and other participants.\n\nClaude Code also gains a stricter way of sending requests through its relay, used in one place depending on a setting.\n\n**Why**\n\nTyping a skill's name in passing should not by itself make Claude run that skill.\n\n- Area: Skills\n- Tier: You'll notice\n- Useful: 3\/5\n- Signal: 3\/5"}