← 返回 Skills 市场
Oracle Cloud Hcm
作者
Membrane Dev
· GitHub ↗
· v1.0.1
· MIT-0
112
总下载
0
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install oracle-cloud-hcm
功能描述
Oracle Cloud HCM integration. Manage data, records, and automate workflows. Use when the user wants to interact with Oracle Cloud HCM data.
安全使用建议
This skill appears to do what it says: it uses the Membrane service/CLI to connect to Oracle Cloud HCM rather than asking for raw API keys. Before installing: 1) Verify you trust Membrane (review getmembrane.com and the @membranehq/cli npm package owner and versions). 2) Prefer installing a specific vetted CLI version instead of always 'latest' to reduce supply-chain risk. 3) Confirm the connection you create to Oracle Cloud HCM uses least-privilege credentials and that you’re comfortable with Membrane handling auth and HCM data. 4) Ask the skill author/registry maintainer to update metadata to list the Membrane CLI and the Membrane account/network requirement so the registry and runtime instructions match.
功能分析
Type: OpenClaw Skill
Name: oracle-cloud-hcm
Version: 1.0.1
The skill bundle provides instructions for an AI agent to interact with Oracle Cloud HCM using the Membrane CLI. It focuses on legitimate integration patterns, such as installing the '@membranehq/cli' npm package, authenticating via OAuth flows, and discovering/executing actions through the Membrane platform. No evidence of data exfiltration, malicious execution, or harmful prompt injection was found; the instructions explicitly advise against asking users for sensitive credentials, favoring managed connections instead.
能力评估
Purpose & Capability
The SKILL.md describes using the Membrane CLI to connect to Oracle Cloud HCM, discover and run actions — this matches the skill name and description. However, the registry metadata lists no required binaries while the runtime instructions explicitly require installing the @membranehq/cli (npm). That metadata mismatch should be corrected.
Instruction Scope
Instructions stay within the stated purpose: they instruct installing Membrane CLI, logging in, creating a connection to oracle-cloud-hcm, discovering and running actions. The skill does not tell the agent to read unrelated files, request unrelated credentials, or exfiltrate data to third-party endpoints beyond Membrane. It explicitly advises not to ask users for API keys.
Install Mechanism
This is an instruction-only skill (no automated install). It tells the user to install the Membrane CLI from npm (global, latest). That is a reasonable approach, but installing an unpinned global npm package has normal supply-chain risks; verify the package and publisher before installing.
Credentials
The skill declares no required env vars or credentials and the instructions rely on Membrane's interactive auth flow rather than asking for Oracle API keys locally. This is proportionate. Note: the SKILL.md requires a Membrane account and network access (not expressed in registry env fields).
Persistence & Privilege
The skill is not always-included and does not request elevated platform privileges. It's instruction-only and does not modify other skills or system-wide agent settings. Agent autonomous invocation remains allowed (the platform default).
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 oracle-cloud-hcm - 安装完成后，直接呼叫该 Skill 的名称或使用
/oracle-cloud-hcm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
v1.0.1
Auto sync from membranedev/application-skills
v1.0.0
Auto sync from membranedev/application-skills
元数据
常见问题
Oracle Cloud Hcm 是什么？
Oracle Cloud HCM integration. Manage data, records, and automate workflows. Use when the user wants to interact with Oracle Cloud HCM data. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 112 次。
如何安装 Oracle Cloud Hcm？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install oracle-cloud-hcm」即可一键安装，无需额外配置。
Oracle Cloud Hcm 是免费的吗？
是的，Oracle Cloud Hcm 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Oracle Cloud Hcm 支持哪些平台？
Oracle Cloud Hcm 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 Oracle Cloud Hcm？
由 Membrane Dev（@membranedev）开发并维护，当前版本 v1.0.1。
推荐 Skills