← 返回 Skills 市场
76
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install suilight
功能描述
SuiLight知识沙龙 - 多智能体知识协作平台。拥有100位虚拟思想家，覆盖26个领域(科学、哲学、社会科学等)，支持跨域讨论、知识沉淀、共识追踪和知识图谱可视化。当用户需要(1)组织多角度知识讨论、(2)创建虚拟思想家角色、(3)构建知识胶囊系统、(4)实现知识图谱、(5)部署Streamlit应用时使用此...
安全使用建议
This skill is coherent: it teaches how to deploy a Streamlit + FastAPI project by cloning a GitHub repo and installing Python dependencies. However, cloning and running arbitrary repositories can run arbitrary code. Before installing or running: (1) review the referenced GitHub repository (owner, recent commits, issues) and inspect the code and requirements.txt for suspicious packages or network/exfiltration logic; (2) run the app in an isolated environment (container, VM) and avoid exposing secret credentials; (3) prefer pinned releases or verified sources rather than a casual git clone of a user repo; (4) verify licensing and any external links (ClawHub, docs) if you need long-term use. If you cannot review the repo, treat it as untrusted code.
功能分析
Type: OpenClaw Skill
Name: suilight
Version: 1.0.0
The skill bundle contains instructions in SKILL.md for an AI agent to perform high-risk operations, including cloning an external GitHub repository (github.com/wanyview1/SuiLight.git) and executing 'pip install' on a requirements file. While these actions are aligned with the stated purpose of deploying the SuiLight platform, they represent a significant attack surface for supply chain attacks or remote code execution via remote artifacts. No direct evidence of intentional malice, such as data exfiltration or hardcoded backdoors, was found in the provided files.
能力评估
Purpose & Capability
Name/description claim a Streamlit + FastAPI multi-agent knowledge platform; SKILL.md provides repo URL, Python/Streamlit/FastAPI instructions, example APIs and modules that align with that purpose. Registry metadata lacks a homepage/source entry but the SKILL.md points to a GitHub repo (reasonable but reduces transparency).
Instruction Scope
Runtime instructions are narrowly scoped to cloning the referenced repository, installing its Python dependencies, and running the Streamlit UI and API. They do not instruct reading unrelated local files, harvesting environment variables, or sending data to unexpected external endpoints within the SKILL.md itself.
Install Mechanism
This is an instruction-only skill (no install spec). It tells the user to git clone an external GitHub repo and pip install -r requirements.txt — a common but higher-risk pattern because it executes code pulled from the network. The SKILL does not specify pinned releases or provenance checks.
Credentials
The skill declares no required environment variables, credentials, or config paths. The examples and instructions do not request secrets or unrelated service credentials, so requested privileges are proportionate to the stated purpose.
Persistence & Privilege
The skill is not marked always:true and does not request persistent system-wide privileges. It is user-invocable and allows normal autonomous invocation (platform default). No evidence it modifies other skills or system configs.
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 suilight - 安装完成后，直接呼叫该 Skill 的名称或使用
/suilight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
SuiLight 1.0.0 – 首次发布
- 发布多智能体知识协作平台，囊括100位覆盖26个领域的虚拟思想家
- 支持跨域知识讨论、知识沉淀（胶囊）、共识追踪与知识图谱可视化
- 提供基于Python Streamlit的前端，FastAPI后端及基础API
- 包含知识胶囊系统、虚拟思想家、跨域沙龙和知识图谱核心模块
- 支持本地与Streamlit Cloud/Docker多种部署方式
元数据
常见问题
suilight 是什么？
SuiLight知识沙龙 - 多智能体知识协作平台。拥有100位虚拟思想家，覆盖26个领域(科学、哲学、社会科学等)，支持跨域讨论、知识沉淀、共识追踪和知识图谱可视化。当用户需要(1)组织多角度知识讨论、(2)创建虚拟思想家角色、(3)构建知识胶囊系统、(4)实现知识图谱、(5)部署Streamlit应用时使用此... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 76 次。
如何安装 suilight？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install suilight」即可一键安装，无需额外配置。
suilight 是免费的吗？
是的，suilight 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
suilight 支持哪些平台？
suilight 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 suilight？
由 wanyview1（@wanyview1）开发并维护，当前版本 v1.0.0。
推荐 Skills