{"version":"2.1.228","anchor":"doc-and-sheet-prompts-are-trimmed-to-the-artifact-s-capabili","canonical_anchor":"doc-and-sheet-prompts-are-trimmed-to-the-artifact-s-capabili","heading":"Doc and sheet prompts are trimmed to the artifact's capabilities","tier":"soon","area":"Skills","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.228\/e\/doc-and-sheet-prompts-are-trimmed-to-the-artifact-s-capabili","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.228","markdown":"### Doc and sheet prompts are trimmed to the artifact's capabilities\n\nDoc and sheet skill instructions are assembled at run time to match what the artifact supports.\n\n**What**\n\nWhen one of the new document or spreadsheet skills runs, its instruction file is assembled at invocation rather than sent whole, so Claude is only told to do things the artifact actually supports.\n\n**Details**\n\n- A marked block instructing Claude to act on reader comments (make the edit, reply, resolve) is kept only when the artifact has a thread id, and deleted otherwise.\n- A trailing note is appended only when the artifact reports capabilities.\n- Front matter is stripped, and anything the user typed after the command is appended under a `## User Request` heading.\n- Unreachable in this build, since both skills are registered as disabled.\n\n**Evidence**\n\n`<!-- comment-verbs:begin -->`\n\n- Area: Skills\n- Tier: Nothing to try yet\n- Useful: 1\/5\n- Signal: 3\/5\n- Present in the build but not switched on"}