From memtomem
Set up and verify a first memtomem memory source. Use for onboarding, choosing an index path, or confirming that search works.
How this skill is triggered — by the user, by Claude, or both
Slash command
/memtomem:setupThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use `$ARGUMENTS` as the memory source path.
Use $ARGUMENTS as the memory source path.
If the request does not clearly specify the memory source path, ask before calling a tool.
mem_status and treat the default provider=none BM25-only configuration as healthy.cd <project-root> && when the setup is project-specific. Retry only after the user completes that explicit trust step.mem_index on that path with force=false and auto_tag=false. This is a one-shot index and must not silently register a watcher root.mem_search to verify retrieval.Do not install Ollama, enable automation hooks, or edit host instruction files unless the user separately requests those actions.
Before reporting results, note which memtomem tool namespaces this session
exposes. If both mcp__memtomem__mem_* and mcp__plugin_memtomem_memtomem__mem_*
tools are available, two memtomem servers are running against the same store —
a manual claude mcp add entry plus the plugin's pinned server. Tell the user,
and name both remediations: keep the plugin by removing the manual entry
(claude mcp remove memtomem, adding -s user for a user-scope entry), or keep
the manual entry by running /plugin uninstall memtomem@memtomem. Never remove
either registration yourself. If only one namespace is present, skip this check
silently.
npx claudepluginhub memtomem/memtomem --plugin memtomemCreates, edits, and verifies skills using a test-driven development approach with pressure scenarios and subagents.