← 返回 Skills 市场
🔌

Runpod

作者 OOMOL · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
27
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install oo-runpod
功能描述
Runpod (runpod.io). Use this skill for ANY Runpod request — reading, creating, updating, and deleting data. Whenever a task involves Runpod, use this skill i...
使用说明 (SKILL.md)

Runpod

Operate Runpod through your OOMOL-connected account. This skill calls the runpod connector with the oo CLI; OOMOL injects credentials server-side, so you never handle raw tokens.

Category: AI, Developer Tools. Exposes 7 action(s).

Running an action

Assume the user has already installed the oo CLI, signed in, and connected Runpod. Do not run oo auth login or open the connection URL proactively — just run the action. Fall back to First-time setup only when a command actually fails with an auth or connection error.

1. Inspect the contract to get the authoritative input/output schema before building a payload:

oo connector schema "runpod" --action "\x3Caction_name>"

2. Run the action with a JSON payload that matches the input schema:

oo connector run "runpod" --action "\x3Caction_name>" --data '\x3Cjson>' --json
  • --data takes a JSON object string or @path/to/file.json; omit it to send {}.
  • The response is { "data": ..., "meta": { "executionId": "..." } }; the execution id lives under meta.executionId.

Each action below links to a reference file with its purpose and exact commands. Read the linked file, then fetch the live schema with oo connector schema before constructing --data.

Available actions

Safety

  • Read actions (get / list / search) are safe to run directly.
  • Create, update, send, or post actions change Runpod state — confirm the exact payload and effect with the user before running.
  • Delete or remove actions are destructive — always confirm the target and get explicit approval first.

First-time setup

These are one-time steps — do not repeat them on every call. Run a step only when a command fails for the matching reason.

  • oo: command not found — install the oo CLI (other platforms: \x3Chttps://cli.oomol.com/install-guide.md>):

    curl -fsSL https://cli.oomol.com/install.sh | bash    # macOS / Linux
    
    irm https://cli.oomol.com/install.ps1 | iex           # Windows PowerShell
    
  • Not signed in / authentication error — sign in to your OOMOL account once:

    oo auth login
    
  • scope_missing / credential_expired / app_not_ready / app_not_found — Runpod is not connected, or the connection expired or lacks a scope. Connect once (auth type: API key) at:

    https://console.oomol.com/app-connections?provider=runpod
    
  • HTTP 402 / OOMOL_INSUFFICIENT_CREDIT — billing stop. Recharge at https://console.oomol.com/billing/token-recharge before retrying.

Resources

安全使用建议
Install only if you trust OOMOL and intend to let the agent operate your Runpod account. Confirm exact pod IDs and intended effects before stop, reset, restart, or delete actions, and review the oo CLI installer source or use a safer verified install path instead of letting an agent run remote install scripts automatically.
能力标签
requires-sensitive-credentials
能力评估
Purpose & Capability
The stated purpose matches the capability: it operates Runpod pods through the OOMOL oo connector, including list/get/start/stop/restart/reset/delete actions.
Instruction Scope
The skill discloses state-changing and destructive Runpod actions, but stop_pod and reset_pod action pages do not clearly warn about downtime or transient state loss, and confirmation guidance is explicit for delete/remove but less clear for stop/reset/restart.
Install Mechanism
First-time setup tells the agent to install the oo CLI by piping remote scripts directly into a shell or PowerShell when oo is missing, without an explicit user confirmation step in that fallback.
Credentials
Use of Runpod credentials is purpose-aligned and described as server-side OOMOL credential injection, but this still grants meaningful cloud infrastructure control.
Persistence & Privilege
The artifact does not show hidden persistence, background workers, local credential harvesting, or unrelated privilege use; authority is mainly via the oo connector and connected Runpod account.
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 oo-runpod
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /oo-runpod 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
v1.0.0
- Introduces `oo-runpod`, a Runpod skill for operating Pods through the OOMOL-connected `runpod` connector. - Supports reading Pod state with `list_pods` and `get_pod`, including schema inspection before each action. - Adds Pod lifecycle controls: `start_pod`, `stop_pod`, `restart_pod`, and `reset_pod`. - Adds destructive Pod deletion via `delete_pod`, with explicit confirmation required before use. - Uses the `oo` CLI with server-side credential injection, avoiding direct handling of raw Runpod API tokens.
元数据
Slug oo-runpod
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Runpod 是什么?

Runpod (runpod.io). Use this skill for ANY Runpod request — reading, creating, updating, and deleting data. Whenever a task involves Runpod, use this skill i... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 27 次。

如何安装 Runpod?

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

Runpod 是免费的吗?

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

Runpod 支持哪些平台?

Runpod 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 Runpod?

由 OOMOL(@oomol)开发并维护,当前版本 v1.0.0。

💬 留言讨论