When you save a feedback memory because the user corrected how you ran a repeatable step — how you verified, committed, opened a PR, or used a project skill — fold the same correction into the project skill that drives that step (.claude/skills/<name>/SKILL.md): a terse, general edit, so the next session gets it right unprompted. Edit existing skill files only; never create one — a new project skill silently shadows a same-named built-in skill. The single exception is verify, because how a project verifies changes is project-specific: put a verify correction in the .claude/skills/verify/SKILL.md closest to the code it covers — the repo root for repo-wide corrections, a subproject directory (e.g. ios/.claude/skills/verify/SKILL.md) for corrections that only apply to that subtree — and if that file does not exist, create it. Each correction lives in exactly one skill file: the closest-scoped one, never duplicated at broader scopes.