Token导航 LogoToken导航

Agent Skill · 研究检索

vigilath-shopping(维吉拉斯购物)

vigilath-shopping 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。

vigilath-shopping 是研究检索类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为操作浏览器;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 28,556。

总安装 3,195周安装 128GitHub Stars 公开资料未说明下载 1,034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:vigilath-shopping(维吉拉斯购物)
来源仓库:https://github.com/gt-oliver/vigilath-shopping
安装命令:
openclaw skills install vigilath-shopping
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 vigilath-shopping

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。

在 Vigilath.com 上搜索、讨价还价、订购和支付宠物用品——Vigilath.com 是一个具有多轮价格协商功能的人工智能宠物商务平台。

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 vigilath-shopping;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

    它需要操作浏览器,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

vigilath-shopping 怎么安装?

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

vigilath-shopping 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。

vigilath-shopping 需要什么权限?

权限级别是操作浏览器。该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

vigilath-shopping 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。

vigilath-shopping 用的人多吗?

公开数据是累计安装 3,195 次,近一周安装 128 次,下载 1,034 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。

vigilath-shopping 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

  • 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

  • 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
vigilath-shopping

维吉拉斯购物 · 本页

3,195—操作浏览器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
vigilath-shopping
description
Search, bargain, order, and pay for pet supplies on Vigilath.com — an AI-powered pet commerce platform with multi-round price negotiation.
version
1.0.0
metadata
openclaw
requires
env
bins
primaryEnv
VIGILATH_TOKEN

Vigilath.com Pet Commerce

You can search products, negotiate prices, place orders, and pay on Vigilath.com (an AI pet supplies marketplace).

Base URL

All endpoints use: https://www.vigilath.com

Authentication

Every API call (except auth endpoints) requires:

Authorization: Bearer $VIGILATH_TOKEN

Getting a token

If VIGILATH_TOKEN is not set, use Device Flow to obtain one:

  1. Create session:
curl -s -X POST https://www.vigilath.com/api/agent/auth/session \
  -H "Content-Type: application/json" -d '{}'

Response: {"sessionId": "...", "authUrl": "https://www.vigilath.com/api/agent/auth/page?code=XXX-123", "code": "XXX-123", "expiresIn": 600}

  1. Show the authUrl to the user and ask them to open it in a browser to log in.
  1. Poll for token (every 5 seconds, up to 10 minutes):
curl -s -X POST https://www.vigilath.com/api/agent/auth/token \
  -H "Content-Type: application/json" -d '{"sessionId": "SESSION_ID"}'
  • HTTP 428: user hasn't logged in yet, keep polling
  • HTTP 200: {"accessToken": "eyJ...", "expiresIn": 2592000} — save this as VIGILATH_TOKEN
  • HTTP 410: session expired, start over

Token is valid for 30 days.

Capabilities

1. Smart Shopping (search + AI selection)

curl -s -X POST https://www.vigilath.com/api/agent/shopping \
  -H "Authorization: Bearer $VIGILATH_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"query": "organic dog food for small breeds", "language": "English"}'

Response contains selected_products (array) and natural_message (AI recommendation).

Each product includes: spuId, spuName, priceFee (cents CNY), mainImgUrl, selling_point, categoryName, skuId, shopId, shopName, stock, bargain_enabled.

Products with bargain_enabled: true support price negotiation (see Bargain below).

2. Bargain (multi-round price negotiation)

For products with bargain_enabled: true, you can negotiate a lower price.

Step 1 — Search with bargain mode:

curl -s -X POST https://www.vigilath.com/api/agent/shopping \
  -H "Authorization: Bearer $VIGILATH_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"query": "dog food", "bargain": true}'

Response includes bargain_sessions with sessionId for each bargain-enabled product.

Step 2 — Send counter-offers:

curl -s -X POST https://www.vigilath.com/api/agent/bargain \
  -H "Authorization: Bearer $VIGILATH_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"sessionId": "SESSION_ID", "message": "I offer 25 yuan"}'

Response:

{
  "sessionId": "...",
  "productName": "Premium Dog Food",
  "originalPrice": 35.0,
  "currentPrice": 30.0,
  "message": "25 is too low! How about 30?",
  "round": 2,
  "dealReached": false,
  "isActive": true,
  "quote": null
}

Step 3 — Repeat until dealReached: true. The response will include a quote:

{
  "dealReached": true,
  "quote": {
    "quoteId": "q_xyz789",
    "bargainPrice": 30.0,
    "discount": 5.0,
    "expiresAt": "2026-04-02T12:00:00"
  }
}

Step 4 — Place order with quoteId to apply bargain price (see Order below).

Supported messages: counter-offer ("25块", "I'll pay 80"), accept ("deal", "成交"), quit ("算了", "quit"), leverage ("competitor is cheaper", "I'm a loyal customer").

3. Place Order

curl -s -X POST https://www.vigilath.com/api/agent/order \
  -H "Authorization: Bearer $VIGILATH_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"items": [{"spuId": 12345, "quantity": 1}], "addrId": null, "quoteId": null}'
  • items: array of {spuId, quantity} — skuId/shopId auto-resolved from spuId
  • addrId: shipping address ID, or null to use user's default address
  • quoteId: bargain quote ID from a successful negotiation (optional)

Response: {"data": {"order_number": "...", "total": 2999, "status": "UNPAID"}}

4. Pay

curl -s -X POST https://www.vigilath.com/api/agent/pay \
  -H "Authorization: Bearer $VIGILATH_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"orderNumber": "ORDER_NUMBER", "method": "points"}'

Methods:

  • points — instant settlement, fully automated
  • stripe — returns paymentUrl, show to user to complete card payment
  • coinbase — returns paymentUrl, show to user to complete crypto payment

After stripe/coinbase, poll order status to confirm payment.

5. Query Orders

List orders:

curl -s https://www.vigilath.com/api/agent/orders \
  -H "Authorization: Bearer $VIGILATH_TOKEN"

Optional query params: status (1=pending_payment, 2=pending_shipment, 3=shipped, 5=completed, 6=cancelled), page, page_size.

Single order detail:

curl -s https://www.vigilath.com/api/agent/orders/ORDER_NUMBER \
  -H "Authorization: Bearer $VIGILATH_TOKEN"

6. Addresses

List addresses:

curl -s https://www.vigilath.com/api/agent/addresses \
  -H "Authorization: Bearer $VIGILATH_TOKEN"

Create address:

curl -s -X POST https://www.vigilath.com/api/agent/addresses \
  -H "Authorization: Bearer $VIGILATH_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"receiver": "John", "mobile": "1234567890", "province": "CA", "city": "LA", "area": "Downtown", "addr": "123 Main St"}'

Common Workflows

Quick buy (no bargain)

  1. Search: POST /api/agent/shopping with query
  2. Show products to user, let them pick
  3. Order: POST /api/agent/order with selected spuId(s)
  4. Pay: POST /api/agent/pay with orderNumber

Quick buy (autonomous — one call)

  1. POST /api/agent/shopping with autonomous: true — AI picks and orders automatically
  2. Pay: POST /api/agent/pay with orderNumber from response

Bargain then buy

  1. Search: POST /api/agent/shopping with bargain: true
  2. For each bargain session, negotiate: POST /api/agent/bargain with counter-offers
  3. On deal: POST /api/agent/order with quoteId from quote
  4. Pay: POST /api/agent/pay

Error Handling

  • 401: Token expired or invalid — re-authenticate via Device Flow
  • 404: Resource not found (order, session, address)
  • 422: Validation error — check request body
  • 429: Rate limited — wait and retry

Discovery

For machine-readable capability metadata:

  • GET /.well-known/agent.json — structured service discovery
  • GET /llms.txt — LLM-readable summary
  • GET /llms-full.txt — full API documentation

平台分布

OpenClaw

96.79%
按下载量换算1,001

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

操作浏览器

该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

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