Token导航 LogoToken导航

Agent Skill · 研究检索

ovrapay(ovrapay 搜索)

ovrapay 用于查找、检索和筛选相关信息,适合在 OpenClaw 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

ovrapay 是研究检索类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为接触敏感数据;许可证为 MIT-0,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 30,240。

总安装 2,913周安装 119GitHub Stars 公开资料未说明下载 933核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT-0
版本
1.0.0

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:ovrapay(ovrapay 搜索)
来源仓库:https://github.com/ovra/ovrapay
安装命令:
openclaw skills install ovrapay
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install ovrapay

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

帮助客服人员在线购买商品、支付费用及管理支出预算。适用于电商平台售后、服务采购或差旅报销等场景。启用秒级支付流程,支持多种支付方式与交易记录追踪。需绑定有效支付账户并设置消费限额以控制风险。ovrapay 属于研究检索类 Skill,可作为该场景下的辅助能力补充。注意核对订单详情,防止因自动扣款引发财务纠纷。

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 OpenClaw;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 openclaw skills install ovrapay;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

ovrapay 怎么安装?

在终端执行 openclaw skills install ovrapay。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

ovrapay 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

ovrapay 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

ovrapay 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

ovrapay 用的人多吗?

公开数据是累计安装 2,913 次,近一周安装 119 次,下载 933 次。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

ovrapay 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 OpenClaw,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
ovrapay

ovrapay 搜索 · 本页

2,913—接触敏感数据MIT-0通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

name
ovra-agentic-payments
description
>
homepage
https://getovra.com
license
MIT
compatibility
>
requires
env
metadata
version
2.3.0
author
Ovra Labs
website
https://getovra.com
docs
https://docs.getovra.com
mcp-endpoint
https://api.getovra.com/api/mcp
data-residency
EU (Germany)
compliance
GDPR, PSD2

Ovra Agentic Payments

Secure, EU-native payments for AI agents. The agent never touches card data.

Prerequisites

  1. Ovra API Key — sign up at getovra.com and get a key from Dashboard > Keys
  2. MCP Server Connection — this skill communicates with Ovra via MCP at https://api.getovra.com/api/mcp

Sandbox keys (sk_test_*) are free and have no spending limits. Production keys (sk_live_*) require account verification.

Setup

Add the Ovra MCP server to your agent configuration:

{
  "mcpServers": {
    "ovra": {
      "url": "https://api.getovra.com/api/mcp",
      "headers": { "Authorization": "Bearer YOUR_OVRA_API_KEY" }
    }
  }
}

Replace YOUR_OVRA_API_KEY with your key from getovra.com/dashboard/keys.

What this skill sends externally

All tool calls (ovra_pay, ovra_card, etc.) are sent to https://api.getovra.com/api/mcp via the MCP protocol. Receipt uploads (ovra_receipt) transmit base64-encoded PDF or PNG files (max 5MB) to the same endpoint — only upload invoices/receipts from the current transaction, never arbitrary files. No data is sent to any other external service. All data is stored in the EU (Germany) per GDPR.

Quick Start — One-Step Payment

For most payments, use ovra_pay which handles the entire flow:

ovra_pay({
  action: "checkout",
  agentId: "ag_xxx",
  purpose: "Notion Team Plan",
  amount: 79,
  merchant: "Notion"
})

Returns tokenized card data (DPAN + cryptogram). The real card number is never exposed.

Handle HTTP 402 Paywalls

When a web API returns HTTP 402 Payment Required:

ovra_pay({
  action: "handle_402",
  agentId: "ag_xxx",
  url: "https://api.example.com/data",
  merchant: "Example API",
  amount: 0.05
})

Available Tools (12)

Payment Flow

ToolActionsDescription
ovra_paycheckout, status, handle_402, discoverPrimary tool. Complete payment in one step.
ovra_intentlist, declare, get, cancel, verifyFine-grained intent management.
ovra_credentialobtain, grant, issue, redeem, revoke, statusAdvanced credential control.

Cards & Policy

ToolActionsDescription
ovra_cardissue, list, freeze, unfreeze, close, rotateVirtual Visa card management.
ovra_policygetView spending policy (read-only).

Records & Compliance

ToolActionsDescription
ovra_transactionlist, get, memoPayment history and notes.
ovra_receiptupload, getReceipt management. Upload only PDF/PNG invoices from the current transaction. Max 5MB.
ovra_disputelist, get, fileFile disputes on transactions.

Admin

ToolActionsDescription
ovra_agentlist, provision, get, update, issue_card, token_list, token_create, token_revokeProvision and manage agents.
ovra_customerget, update, gdpr_export, gdpr_consent, gdpr_deleteAccount and GDPR compliance.
ovra_merchantresolve, explain, list_mcc, suggestMerchant intelligence.
ovra_config(varies)System configuration.

Step-by-Step Flow (when you need fine control)

For cases where ovra_pay is too opaque:

1. ovra_policy     → get: check spending rules
2. ovra_intent     → declare: state what to buy
3. ovra_credential → obtain: get DPAN + cryptogram
4. ovra_receipt    → upload: attach proof
5. ovra_intent     → verify: confirm actual vs expected

Step 1: Check policy

ovra_policy({ action: "get", agentId: "ag_xxx" })

Step 2: Declare intent

ovra_intent({
  action: "declare",
  agentId: "ag_xxx",
  purpose: "Buy wireless keyboard",
  expectedAmount: 49.99,
  expectedMerchant: "amazon.de"
})

If status is pending_approval: stop and wait. Tell the user approval is needed in the dashboard.

Step 3: Get credentials

ovra_credential({ action: "obtain", intentId: "in_xxx" })

Returns DPAN + cryptogram. The agent never sees the real card number.

Step 4: Attach receipt

Only upload the invoice/receipt PDF or PNG from this specific transaction. Never upload unrelated files.

ovra_receipt({
  action: "upload",
  intentId: "in_xxx",
  fileBase64: "JVBER...",
  fileName: "invoice.pdf"
})

Step 5: Verify

ovra_intent({
  action: "verify",
  intentId: "in_xxx",
  actualAmountEuros: 49.99,
  actualMerchant: "amazon.de"
})

Gotchas

  • Use ovra_pay for most payments. Step-by-step is for edge cases.
  • Intents expire (default 24h). If expired, create a new one.
  • pending_approval means a human must approve. The agent cannot bypass this.
  • Card data must never appear in output, logs, or context.
  • ovra_card close is irreversible.
  • ovra_customer gdpr_delete permanently erases ALL data per GDPR Art. 17.

Agent vs Human boundaries

Agent does autonomously: checkout via ovra_pay, declare intents, obtain credentials, upload receipts, verify transactions, list transactions, file disputes, check balances, handle 402 paywalls.

Agent asks human first: provision/delete agents, fund wallets, change policies, freeze/unfreeze cards, manage API keys, approve high-value intents, GDPR deletion.

Checking balance and status

ovra_agent({ action: "get", agentId: "ag_xxx" })
ovra_policy({ action: "get", agentId: "ag_xxx" })
ovra_transaction({ action: "list", agentId: "ag_xxx", limit: 5 })
ovra_intent({ action: "list", status: "pending_approval" })

Filing a dispute

ovra_dispute({
  action: "file",
  transactionId: "tx_xxx",
  reason: "not_received",
  description: "Package not delivered after 14 days"
})

Reasons: unauthorized, fraud, not_received, duplicate, incorrect_amount, canceled.

Merchant intelligence

ovra_merchant({ action: "suggest", query: "cloud hosting" })
ovra_merchant({ action: "resolve", query: "hetzner.com" })

平台分布

OpenClaw

87.93%
按下载量换算820

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills