{"version":"2.1.198","anchor":"skill-upkeep-guidance-improvement","canonical_anchor":"skill-upkeep-guidance-improvement","heading":"Skill Upkeep Guidance Improvement","tier":null,"area":null,"scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.198\/e\/skill-upkeep-guidance-improvement","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.198","markdown":"### Skill Upkeep Guidance Improvement\n\nThe skill-upkeep hint now includes explicit instructions to fold user corrections back into the driving project skill file, so the next session inherits the fix.\n\n**Details**\n\n- The guidance is injected whenever Claude saves a `feedback`-type memory for a correction that concerns a repeatable step: verifying changes, committing, opening a PR, or running a project skill\n- The instruction text (constant `KQr`) directs Claude to also edit the corresponding `.claude\/skills\/<name>\/SKILL.md` file with a terse, general version of the same correction \u2014 so the fix is baked into the skill rather than only stored as a private memory\n- Claude is told to **edit existing** skill files rather than creating new ones, because a new project skill shadows a same-named built-in skill by that name\n- One explicit exception: if the correction concerns how to verify changes in the current repo and `.claude\/skills\/verify\/SKILL.md` does not yet exist, Claude should create it\n\n**Evidence**\n\nConstant `KQr` (search for `\"When you save a \\`feedback\\` memory because the user corrected how you ran a repeatable step\"`)"}