26 个 · 按相关度排序
Extract information from a project or conversation and store it as memories in MemPalace for later retrieval. The skill follows the step-by-step mining instructions returned by the MemPalace command.
中文简介正在准备中。当前显示英语简介。
Check the current state of MemPalace, including room counts, storage usage, and overall health. The skill retrieves status instructions and follows them to present these details for a review of the palace.
中文简介正在准备中。当前显示英语简介。
Find available MemPalace commands, usage tips, and getting started guidance. This skill retrieves the help instructions and follows them step by step to guide users through the basics of using MemPalace.
中文简介正在准备中。当前显示英语简介。
Initialize a new MemPalace for AI memory through a guided setup process. The skill retrieves setup instructions for a configuration that uses ChromaDB as its data storage backend and follows the returned steps.
中文简介正在准备中。当前显示英语简介。
Answer questions about past work, people, projects, and decisions by searching stored MemPalace records first. Retrieve exact source wording, check facts at relevant dates, and maintain session continuity without guessing when records are unavailable.
中文简介正在准备中。当前显示英语简介。
Find information across memories, projects, and conversations already stored in MemPalace. Use semantic search, which looks for related meaning, by following the search instructions returned by the MemPalace command.
中文简介正在准备中。当前显示英语简介。
Assess how well a MemPalace memory palace is organized, then work through a guided repair session. The skill retrieves audit instructions and proceeds one decision at a time to address its organization.
中文简介正在准备中。当前显示英语简介。
Retrieve past decisions, recurring patterns, and unexpected issues from MemPalace before planning a phase. The skill produces a concise file with source references for the planner and falls back to GSD’s native memory when MemPalace is unavailable.
中文简介正在准备中。当前显示英语简介。
Store phase documents verbatim in MemPalace, organized as decisions, plans, or milestones. Avoid duplicate entries and mirror decision or delivery facts into a knowledge graph that records when those facts became valid.
中文简介正在准备中。当前显示英语简介。
Set up and maintain MemPalace as a searchable store of project and conversation memories. Configure a private installation, a shared hub, or a hub client, connect agent tools, and audit how stored information is organized.
中文简介正在准备中。当前显示英语简介。
Coordinate work between AI agents through MemPalace’s event log. Create tasks with clear goals and completion criteria, generate pasteable handoffs, track claims, and deliver patches for verification. Explicitly requested launches support Codex and Claude.
中文简介正在准备中。当前显示英语简介。
Store project files and conversation transcripts as searchable memories while preserving their original text. Retrieve past decisions, code, and notes by meaning, inspect stored content, and review how well memories are organized.
中文简介正在准备中。当前显示英语简介。
Store conversation history and project material locally, then search by meaning and retrieve original text. Organize memories by person or project, track dated relationships and facts, and keep diary entries that connect work across sessions.
中文简介正在准备中。当前显示英语简介。
Routes requests about a codebase to the appropriate skill for mapping its structure, generating knowledge graphs, updating documentation, extracting lessons, or storing and recalling project knowledge for future planning.
中文简介正在准备中。当前显示英语简介。
Routes memory and retrieval tasks between MemPalace and QMD. Use this skill whenever the user asks WHERE something is in the codebase (route to QMD), WHY something was built a certain way or what was decided (route to MemPalace), or needs BOTH code and historical context (combined). Trigger on phrases like: 'where is X', 'find X in the code', 'search the codebase for X', 'what did we decide about X', 'why does X work this way', 'show me X and why we built it', 'look up X', 'what's in the handoffs about X', 'pull the relevant files for X'. Use proactively whenever a question could benefit from codebase search OR project memory — don't wait for the user to explicitly ask for a search.
中文简介正在准备中。当前显示原文说明。
Help a spawned worker check which date-range helpers and external integrations are available and how to call them. The catalog explains environment settings, local broker access, and availability checks so the worker can choose tools for its task.
中文简介正在准备中。当前显示英语简介。
Makes sessions durable across `/clear`, machine reboots, and IDE switches. SessionStart catchup pulls scratch + last MemPalace recall + planning files into context. Stop promotion writes a handoff note and runs memory-keeper. Manual `/mddesign:handoff` re-runs either at any time.
中文简介正在准备中。当前显示原文说明。
Three-tier memory layer for the orchestrator. Routes scratch (file-tier), WHERE (QMD), and WHY (MemPalace) through the existing code-memory-router slash command. Never edits planning files directly. Every WHY-tier promotion goes through the HITL gate.
中文简介正在准备中。当前显示原文说明。
Answer a question from the structured wiki before searching the web — "query the wiki", "what do we know about", synthesis request, cross-project research. Returns cited synthesis with wikilinks and counter-arguments.
中文简介正在准备中。当前显示原文说明。
Cross-session memory that resumes your project where you left it, not where the base voice assumes.
中文简介正在准备中。当前显示原文说明。
Audit wiki health — "wiki health check", "audit the wiki", "find contradictions", weekly pass, before a major content release. Catches contradictions, stale pages, orphans, duplicate concepts and broken links.
中文简介正在准备中。当前显示原文说明。
Maxim L2 pack. Bundles: L1.5 Brand & Design Pro + L1.6 Behavioral Intelligence + L1.2 MemPalace Pro. Primary framework: EAST (Easy, Attractive, Social, Timely).
中文简介正在准备中。当前显示原文说明。
Maxim L2 pack. Bundles: L1.1 AI Governance + L1.2 MemPalace Pro + L1.3 Proactive Watch. Primary framework: Fogg Behavior Model.
中文简介正在准备中。当前显示原文说明。
Review and verify unverified wiki pages — "review unverified pages", "verify wiki content", verification pass, after a major ingest cycle, before content release. The gate that turns AI-generated knowledge into trusted knowledge.
中文简介正在准备中。当前显示原文说明。