{"version":"2.1.293","anchor":"run-skill-loading-changes-how-the-prompt-is-chosen","canonical_anchor":"run-skill-loading-changes-how-the-prompt-is-chosen","heading":"\/run shows a different notice when its skill is slow to load or not loaded","tier":"notice","area":"Slash Commands","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.293\/e\/run-skill-loading-changes-how-the-prompt-is-chosen","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.293","markdown":"### \/run shows a different notice when its skill is slow to load or not loaded\n\nThe \/run skill now picks its prompt based on whether its code is loaded, slow to load or not loaded, and shows a different notice in those cases\n\n**What**\n\nHow `\/run` chooses its prompt now depends on whether the part of Claude Code that powers it has finished loading. It tells apart three cases: loaded, slow to load, and not loaded. When loading is slow or has not happened yet, a different notice is chosen. `\/run` also gains a step that runs when you type arguments after the command.\n\nBefore, when that part was not loaded, the prompt came from a single source with one default.\n\n**Why**\n\nThis changes what you are told when you start `\/run` before the skill is ready.\n\n- Area: Slash Commands\n- Names: `\/run`\n- Tier: You'll notice\n- Useful: 2\/5\n- Signal: 3\/5\n- Scope: individual\n- Heads-up: no"}