بنقرة واحدة
membase-recall
Use Membase memory and wiki when prior user/project context may improve the answer.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
القائمة
Use Membase memory and wiki when prior user/project context may improve the answer.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Pre-release drill for the Membase plugin — package every artifact locally, install each client (claude, codex, cursor, openclaw, hermes) through its real channel, verify auth, then prove skills AND hooks actually work end-to-end. Use before tagging a release, e.g. "/release-drill" or "/release-drill codex" for one client.
Connect an AI client (claude, cursor, codex, hermes, openclaw) to Membase from this repo — first-time local install, config wiring, and a verification smoke test. Use when the user asks to install, set up, connect, or test a Membase connector locally, e.g. "/membase-connect claude" or "cursor 연동해줘".
Flush pending local captures to Membase cloud, then sweep and consolidate fragmented or duplicated memories — without deleting originals without confirmation.
Store a session-state summary in Membase, tagged so a future session (this client or another) can recall exactly where things were left off.
Correct, avoid, or delete unsafe or stale Membase context.
Capture durable repository-specific context into Membase.
| name | membase-recall |
| description | Use Membase memory and wiki when prior user/project context may improve the answer. |
Use this skill when the user asks about past context, preferences, decisions, project history, prior fixes, or anything that may have been stored in Membase.
Workflow:
search_memory first for personal context, preferences, decisions,
meetings, emails, and project memory.search_wiki for factual documents, stable project knowledge,
references, or docs.get_current_date first and pass
explicit date filters to search_memory.search_memory says the limit was reached, run another search with
offset or a different query angle before treating the result as complete.