← 返回 Skills 市场
Switchyard Runtime Check
作者
Yifeng[Terry] Yu
· GitHub ↗
· v1.0.0
· MIT-0
100
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install switchyard-runtime-check
功能描述
Verify the optional local Switchyard runtime path without changing Campus-owned response semantics.
安全使用建议
This skill is narrowly scoped and coherent: it only instructs the agent to query local Campus endpoints and to preserve Campus response semantics. Before installing, confirm the agent is intended to access your internal /api endpoints and that that network access is acceptable. Because the skill has no source/homepage listed, verify the publisher/owner is trusted in your environment. If you want stricter control, run it in a sandbox or disable autonomous invocation for the agent until you’ve tested it.
功能分析
Type: OpenClaw Skill
Name: switchyard-runtime-check
Version: 1.0.0
The skill bundle provides standard instructions for an AI agent to interact with a specific API framework (Switchyard/Campus) to verify runtime status and handle chat responses. The instructions in SKILL.md focus on API endpoint consumption and response formatting without any indicators of malicious intent, data exfiltration, or unauthorized command execution.
能力评估
Purpose & Capability
Name/description describe verifying a local Switchyard runtime; the SKILL.md only directs calls to local Campus endpoints and to preserve Campus response semantics. There are no unrelated env vars, binaries, or installs requested.
Instruction Scope
Runtime instructions are narrow and specific: GET /api/providers/status, check switchyard.ready, then use consumer seam or /api/providers/switchyard/chat while preserving response semantics. They do not ask the agent to read unrelated files, secrets, or to transmit data to external endpoints.
Install Mechanism
No install spec and no code files; instruction-only skills have minimal disk footprint and no dependencies to fetch.
Credentials
The skill requires no environment variables, credentials, or config paths. The declared requirements are minimal and proportional to the stated purpose.
Persistence & Privilege
always:false (normal). disable-model-invocation:false (agent may invoke autonomously) — this is the platform default; combine with no extra privileges, it is acceptable but you may restrict autonomous invocation if you prefer tighter control.
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 switchyard-runtime-check - 安装完成后，直接呼叫该 Skill 的名称或使用
/switchyard-runtime-check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 switchyard-runtime-check skill.
- Allows verification of the local Switchyard runtime path without altering Campus-owned response semantics.
- Confirms `switchyard.ready` status via `GET /api/providers/status`.
- Ensures use of the Campus consumer seam while preserving required response fields.
- Enforces strict boundaries to prevent exposure of raw upstream payloads or misrepresentation of runtime capabilities.
元数据
常见问题
Switchyard Runtime Check 是什么？
Verify the optional local Switchyard runtime path without changing Campus-owned response semantics. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 100 次。
如何安装 Switchyard Runtime Check？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install switchyard-runtime-check」即可一键安装，无需额外配置。
Switchyard Runtime Check 是免费的吗？
是的，Switchyard Runtime Check 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Switchyard Runtime Check 支持哪些平台？
Switchyard Runtime Check 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 Switchyard Runtime Check？
由 Yifeng[Terry] Yu（@xiaojiou176）开发并维护，当前版本 v1.0.0。
推荐 Skills