{"version":"2.1.222","anchor":"skill-refusal-message-tells-the-model-not-to-work-around-it","canonical_anchor":"skill-refusal-message-tells-the-model-not-to-work-around-it","heading":"Skill refusal message tells the model not to work around it","tier":"notice","area":"Skills","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.222\/e\/skill-refusal-message-tells-the-model-not-to-work-around-it","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.222","markdown":"### Skill refusal message tells the model not to work around it\n\nSkills you mark as user-only now tell Claude not to reimplement them by hand.\n\n**What**\n\nWhen the model tries to invoke a skill marked as user-only, the returned error now appends an explicit instruction against achieving the same thing another way.\n\n**Details**\n\n- Applies to skills with disable-model-invocation set.\n- The added sentence closes the loophole of the model reading the skill and re-implementing its steps by hand.\n\n**Evidence**\n\n`Do not replicate this skill's workflow by other means`\n\n- Area: Skills\n- Names: `disable-model-invocation`\n- Tier: You'll notice\n- Useful: 3\/5\n- Signal: 0\/5"}