{"version":"2.1.319","anchor":"skill-tool-preservetooluseresultinsubagents-now-hardcoded-o","canonical_anchor":"skill-tool-preservetooluseresultinsubagents-now-hardcoded-o","heading":"Skill tool always keeps its results inside subagents","tier":"notice","area":"Skills","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.319\/e\/skill-tool-preservetooluseresultinsubagents-now-hardcoded-o","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.319","markdown":"### Skill tool always keeps its results inside subagents\n\nThe Skill tool now always keeps its results inside subagents instead of depending on a check\n\n**Unclear.** What the earlier check returned is not known, so whether this changes anything for users who already had it on is unclear.\n\n**What**\n\nThe Skill tool (which runs a skill, a packaged set of instructions Claude can follow) now always keeps its results when it runs inside a subagent, a helper copy of Claude given part of a task. Before, this depended on a check made at run time; it is now fixed on.\n\nTwo smaller changes come with it:\n\n- When a skill cannot be found, the diagnostic report now includes the command name for Claude in Chrome.\n\n- Skills whose names contain `:` can fall back to a built-in skill passed in when no other match is found.\n\n**Why**\n\nWhat the Skill tool returns inside a subagent no longer varies, so subagents always see the result of a skill they ran.\n\n- Area: Skills\n- Tier: You'll notice\n- Useful: 1\/5\n- Signal: 1\/5\n- Scope: individual\n- Heads-up: no"}