{"version":"2.1.200","anchor":"feedback-memory-skill-correction-never-create-new-skills-exc","canonical_anchor":"feedback-memory-skill-correction-never-create-new-skills-exc","heading":"Feedback Memory Skill Correction: Never Create New Skills (Except verify )","tier":null,"area":null,"scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.200\/e\/feedback-memory-skill-correction-never-create-new-skills-exc","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.200","markdown":"### Feedback Memory Skill Correction: Never Create New Skills (Except `verify`)\n\nThe guidance for the `feedback` memory (when Claude corrects a repeatable step) was tightened:\n\n- Previously: \"Edit existing skill files rather than creating new ones (a new project skill shadows a same-named built-in skill), with one exception: if the correction is about how to verify changes in this repo and `.claude\/skills\/verify\/SKILL.md` does not exist, create it.\"\n- Now: \"Edit existing skill files **only**; never create one \u2014 a new project skill silently shadows a same-named built-in skill. The single exception is verify...\"\n\nThe verify exception also gained guidance about scoping: the correction goes in the closest-scoped `verify\/SKILL.md` (repo root vs. subproject), never duplicated.\n\n**Evidence**\n\nUpdated feedback memory string (search for `\"Edit existing skill files only; never create one\"`, `\"Each correction lives in exactly one skill file\"`)"}