From memory-bank
Add a new explicit memory fact to the GCP Reasoning Engine Memory Bank. Use when the user wants to manually add a specific fact, preference, or instruction that should persist across sessions.
How this skill is triggered — by the user, by Claude, or both
Slash command
/memory-bank:memories-addThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Add a new fact to the GCP Memory Bank.
Add a new fact to the GCP Memory Bank.
ls -d ~/.claude/scripts/memory-bank ~/.gemini/config/plugins/memory-bank/scripts ~/.claude/plugins/cache/*/memory-bank/*/scripts 2>/dev/null
Use the first that exists in the order listed above, not the order ls
prints — it sorts, which would pick a stale cached copy over the live one.
Call it <SCRIPTS>. If nothing prints, stop and report that the memory-bank
plugin is not installed.python3 <SCRIPTS>/add_memory.py "<fact>" --scope <global|project>
Default scope: global. Use project only if explicitly requested.python3 <SCRIPTS>/nudge_minion.py
global.--scope project.$CLAUDE_PLUGIN_ROOT to shortcut Step 2 — it is set for hooks only and is empty in a command you run.npx claudepluginhub mlarkin00/plugins --plugin memory-bankGuides completion of development work by verifying tests, detecting environment, and presenting structured options for merge, PR, or cleanup.
Guides creation and editing of skills using test-driven development with pressure scenarios and subagents to verify agent compliance.
Dispatches multiple subagents concurrently for independent tasks without shared state. Use when facing 2+ unrelated failures or subsystems that can be investigated in parallel.