← 返回 Skills 市场
77
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install shared-memory-stack
功能描述
Complete reference for the shared memory architecture connecting Claude Code, OpenClaw/Kimi, and LM Studio subagents through Obsidian vault + MemPalace (Chro...
安全使用建议
This skill is a documentation-only guide for running a local shared-memory stack; it appears coherent in purpose but the metadata omits many operational requirements. Before installing or running anything mentioned here: 1) Do not allow an agent to run these commands autonomously — the doc includes concrete commands that will read and write local directories and could transmit data. 2) Manually verify the existence and contents of the referenced paths and binaries (/Volumes/2TB_APFS/..., /opt/homebrew/bin/mempalace, capture-idea, openclaw CLI). 3) Confirm SSH keys and 'gh' config are present and intended for use; never expose or copy private keys. 4) Review any local scripts (capture-idea, mempalace wrapper) before execution to ensure they don't call out to remote endpoints or exfiltrate data. 5) Ask the skill author to update metadata to list required binaries/credentials and to clarify which actions are purely descriptive vs meant to be executed. If you cannot validate these points, treat the skill as high-risk and avoid running the documented commands.
功能分析
Type: OpenClaw Skill
Name: shared-memory-stack
Version: 1.0.0
The skill bundle defines a complex multi-agent workflow that grants an AI agent instructions for high-risk operations, specifically the automated creation of public GitHub repositories and pushing local code using a pre-configured SSH key (~/.ssh/github_nerua1). It relies on hardcoded absolute paths (/Volumes/2TB_APFS/openclaw-data/) and specific user identities (nerua1), which is highly irregular for a portable skill. While these appear to be intended features for a personal 'shared memory' architecture, the instructions to use 'gh repo create --public' and 'git push' provide a direct mechanism for accidental or coerced data exfiltration of local workspace content to a public forum.
能力标签
能力评估
Purpose & Capability
The documented purpose — coordinating a shared local memory (Obsidian vault + ChromaDB/MemPalace) between Claude Code, OpenClaw and LM Studio — is coherent with the instructions. However the registry metadata declares no required binaries, env vars, or config paths while the SKILL.md repeatedly references specific binaries (/opt/homebrew/bin/mempalace, /opt/homebrew/bin/capture-idea, openclaw CLI, python3), absolute filesystem paths (/Volumes/2TB_APFS/...), and GitHub/SSH usage. That mismatch (metadata says 'none' but the doc requires many local tools/keys) is an incoherence and should be explained by the author before use.
Instruction Scope
The SKILL.md tells operators to read/write specific local directories, run local binaries that mine and index vault contents, and communicate over a local gateway (port 18789). It also references publishing to GitHub and assumes an SSH key and gh are configured. These instructions require filesystem access and existing credentials; if an agent were allowed to execute them automatically they could read and transmit potentially sensitive local data. The instructions are not purely descriptive — they include concrete commands that would perform IO on the host.
Install Mechanism
No install specification or code files are present; the skill is instruction-only. This reduces supply-chain risk because nothing will be automatically downloaded or written by the registry install itself. All executable behavior depends on local binaries described in the documentation.
Credentials
The skill metadata lists no required environment variables or credentials, yet the documentation explicitly assumes access to an SSH key and the 'gh' CLI, a local OpenClaw gateway, and specific home/workspace directories. That gap is concerning: the skill expects privileged local artifacts (keys, repos, large data directories) but does not declare them. Users should not expose SSH keys, tokens, or allow automatic execution of the described commands without verifying what will run and what data will be read or transmitted.
Persistence & Privilege
The skill is not force-included (always: false) and is user-invocable. Autonomous invocation is permitted by default but is not by itself flagged here. The skill does not request to modify other skills or system-wide settings in the provided documentation.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install shared-memory-stack - 安装完成后，直接呼叫该 Skill 的名称或使用
/shared-memory-stack触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
- Initial release of shared-memory-stack skill: complete documentation of multi-agent shared memory architecture connecting Claude Code, OpenClaw/Kimi, and LM Studio via Obsidian vault and MemPalace (ChromaDB).
- Reference covers: vault/file structure, semantic/keyword search, idea capture pipeline, mempalace setup, and inter-agent communication.
- Details provided for key file paths, mining/searching procedures, CLI scripts, and skill publishing workflows for both Claude Code and OpenClaw.
- Outlines required Python environment, common issues, and troubleshooting tips for memory management and agent interoperability.
- Quick reference section for all major commands and daily usage scenarios.
元数据
常见问题
Shared Memory Stack 是什么？
Complete reference for the shared memory architecture connecting Claude Code, OpenClaw/Kimi, and LM Studio subagents through Obsidian vault + MemPalace (Chro... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 77 次。
如何安装 Shared Memory Stack？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install shared-memory-stack」即可一键安装，无需额外配置。
Shared Memory Stack 是免费的吗？
是的，Shared Memory Stack 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Shared Memory Stack 支持哪些平台？
Shared Memory Stack 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Shared Memory Stack？
由 nerua1（@nerua1）开发并维护，当前版本 v1.0.0。
推荐 Skills