{"version":"2.1.321","anchor":"claude-api-skill-trigger-text-tightened","canonical_anchor":"claude-api-skill-trigger-text-tightened","heading":"The Claude API skill asks to be read before Claude does anything else","tier":"notice","area":"Skills","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.321\/e\/claude-api-skill-trigger-text-tightened","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.321","markdown":"### The Claude API skill asks to be read before Claude does anything else\n\nThe Claude API skill now tells Claude to read it first, before answering, running a command or opening a file\n\n**What**\n\nA skill is a packaged set of instructions Claude can load when a task calls for it. The description of the Claude API skill changed in two ways:\n\n- It now says to read it first, before Claude answers, runs a command or opens a file. Before, it said to read it before opening the target file.\n\n- It adds a fallback: if a search finds nothing, Claude should load the skill.\n\n**Why**\n\nThe skill will be picked up more often and earlier, so Claude is more likely to have its guidance before working on Claude API code.\n\n- Area: Skills\n- Tier: You'll notice\n- Useful: 2\/5\n- Signal: 2\/5\n- Scope: individual\n- Heads-up: no"}