← 返回 Skills 市场
membranedev

Nifty

作者 Membrane Dev · GitHub ↗ · v1.0.3 · MIT-0
cross-platform ⚠ suspicious
169
总下载
0
收藏
0
当前安装
4
版本数
在 OpenClaw 中安装
/install nifty
功能描述
Nifty integration. Manage Organizations. Use when the user wants to interact with Nifty data.
安全使用建议
This skill appears coherent and uses the Membrane CLI to talk to Nifty. Before installing or running anything: (1) verify the Membrane CLI package and repository (npmjs and GitHub) to ensure you trust the publisher; (2) prefer npx or an ephemeral install if you want to avoid a global npm install, because npm packages can run install-time scripts; (3) be aware the CLI will open a browser or provide an auth code and will store credentials locally—review where credentials are stored if that matters for your environment; (4) do not paste API keys or secrets into chat; follow the documented 'connect' flow so Membrane manages auth server-side as intended. If you need higher assurance, test in an isolated environment first.
功能分析
Type: OpenClaw Skill Name: nifty Version: 1.0.3 The skill requires the installation of a global NPM package (@membranehq/cli) and directs the agent to route all authentication and API interactions through a third-party platform (Membrane). While aligned with the stated purpose of Nifty integration, the instructions to perform global system installations and the use of 'membrane action create'—which generates and executes logic from a remote service—represent a high-risk operational pattern for an automated agent. These behaviors are classified as suspicious due to the significant attack surface and dependency on external infrastructure (getmembrane.com) for core logic execution.
能力评估
Purpose & Capability
The name/description (Nifty integration) matches the instructions: everything centers on using the Membrane CLI to connect to Nifty and run pre-built actions. Required capabilities (network access, Membrane account) are appropriate and expected; there are no unrelated environment variables, binaries, or config paths requested.
Instruction Scope
SKILL.md confines runtime behavior to installing/using the Membrane CLI, authenticating via the documented interactive/headless flow, creating/using connections, discovering and running actions, and letting Membrane manage credentials. The instructions do not direct the agent to read arbitrary local files, exfiltrate data to non-Membrane endpoints, or access unrelated system configuration.
Install Mechanism
The skill is instruction-only (no automatic installer). It recommends installing @membranehq/cli via 'npm install -g' or using 'npx' in examples. Asking the user to install a public npm package is reasonable for this purpose, but global npm installs can execute package install scripts—users should verify the package source (npm page and GitHub repo) or prefer npx/ephemeral install to reduce exposure.
Credentials
No environment variables, primary credential, or config paths are required by the skill. The SKILL.md explicitly instructs to let Membrane handle credentials and not to ask users for API keys, which is proportionate for a connector-based integration.
Persistence & Privilege
The skill is not marked 'always'. It is user-invocable and allows normal autonomous invocation (the platform default). It does not request persistent system-wide modifications or access to other skills' configurations.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install nifty
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /nifty 触发
  4. 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
v1.0.3
Auto sync from membranedev/application-skills
v1.0.2
Revert refresh marker
v1.0.1
Refresh update marker
v1.0.0
Auto sync from membranedev/application-skills
元数据
Slug nifty
版本 1.0.3
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 4
常见问题

Nifty 是什么?

Nifty integration. Manage Organizations. Use when the user wants to interact with Nifty data. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 169 次。

如何安装 Nifty?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install nifty」即可一键安装,无需额外配置。

Nifty 是免费的吗?

是的,Nifty 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Nifty 支持哪些平台?

Nifty 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 Nifty?

由 Membrane Dev(@membranedev)开发并维护,当前版本 v1.0.3。

💬 留言讨论