knowledge-updatelisted

# Knowledge Update Extract what was learned in this session and persist it to the project's domain memory files. ## When to Use Run at the end of a session with `/knowledge-update` when: - You just completed a non-trivial task - You encountered a surprising bug, API quirk, or pattern - Something worked differently than expected - A previous hypothesis was confirmed or contradicted ## How It Works ### Step 1 — Locate the memory folder Run these two bash checks first — do not skip or infer: ```bash test -d .git && echo "git=yes" || echo "git=no" test -d .claude/memory && echo "memory=yes" || echo "memory=no" ``` Decision based on the output: | git | memory | Action | |-----|--------|--------| | yes | yes | Use `.claude/memory/` | | yes | no | Run `mkdir -p .claude/memory/` then use it | | no | — | Fall back to `~/.claude/projects/<project-slug>/memory/` | **Do not silently fall back to `~/.claude/projects/` just because `.claude/memory/` hasn't been created yet.** If it's a git repo, create the folder. The `~/.claude/projects/` path is reserved for non-repo contexts only (e.g. a scratch folder with no `.git`). **If the repo is (or is about to become) public/open-source**, keep using repo-local `.claude/memory/` — don't reroute to `~/.claude/projects/` just because the repo is public. Instead, make sure `.claude/` is listed in `.gitignore` so the memory files stay local-only and never get published. If `.gitignore` exists but doesn't already exclude `.cla