Token导航 LogoToken导航

Agent Skill · 研究检索

product-reviews-ratings(product reviews ratings 搜索)

product-reviews-ratings 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 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。

product-reviews-ratings 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为需要联网;许可证信息还不明确,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 53,927。

总安装 519周安装 21GitHub Stars 19下载 163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
unknown

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:product-reviews-ratings(product reviews ratings 搜索)
来源仓库:https://github.com/finsilabs/awesome-ecommerce-skills
仓库路径:skills/product-reviews-ratings
安装命令:
npx skills add https://github.com/finsilabs/awesome-ecommerce-skills --skill product-reviews-ratings
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 npx skills 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。

skills.shnpx skills
npx skills add https://github.com/finsilabs/awesome-ecommerce-skills --skill product-reviews-ratings

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。

product-reviews-ratings 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中基于用户评价、评分分布或 NPS 数据等关键词获取市场反馈资料。它服务于产品口碑分析与用户体验改进,适用于差评归因、情感倾向挖掘与客服响应优化等场景。

通过 npx skills add https://github.com/finsilabs/awesome-ecommerce-skills --skill product-reviews-ratings 安装,建议查看是否集成 Amazon/App Store API。

使用前请确认是否爬取公开评论,遵守各平台速率限制。适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

来源仓库内路径:skills/product-reviews-ratings

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 Codex、Claude、Cursor、Gemini CLI;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 npx skills add https://github.com/finsilabs/awesome-ecommerce-skills --skill pro…;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

    它需要需要联网,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

product-reviews-ratings 怎么安装?

在终端执行 npx skills add https://github.com/finsilabs/awesome-ecommerce-skills --skill product-revie…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

product-reviews-ratings 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。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。

product-reviews-ratings 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

product-reviews-ratings 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

product-reviews-ratings 用的人多吗?

公开数据是累计安装 519 次,近一周安装 21 次,下载 163 次,GitHub 19 星。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。

product-reviews-ratings 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 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 Codex,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。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 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
product-reviews-ratings

product reviews ratings 搜索 · 本页

51919需要联网未明确有提醒

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

Product Reviews & Ratings

Overview

Product reviews are the strongest social proof signal in e-commerce — products with 5+ reviews convert at 270% higher rates than products with none. Every major platform has review apps that handle collection, moderation, schema.org markup for Google star ratings, and verified purchase badging without custom code. Only build a custom review system if you need proprietary moderation logic, deep API integration, or review data in your own database.

When to Use This Skill

  • When launching a new store and needing a review collection and display system
  • When implementing schema.org AggregateRating markup to enable star ratings in Google Search results
  • When building a moderation workflow to prevent fake or spam reviews
  • When displaying verified purchase badges to increase review credibility
  • When triggering post-purchase review request emails automatically after delivery
  • When importing reviews from one platform or app to another

Core Instructions

Step 1: Determine platform and choose the right review tool

PlatformRecommended ToolWhy
ShopifyJudge.meFree plan includes unlimited reviews, photo reviews, verified purchase badges, schema.org markup, and post-purchase email requests
ShopifyYotpoMore advanced features: Q&A, loyalty integration, Google Shopping reviews syndication — best for mid-market+ stores
WooCommerceWooCommerce built-in reviews + WP Product Review pluginWooCommerce has built-in star ratings; add WP Product Review for schema.org markup and verified purchase gating
WooCommerceJudge.me for WooCommerceSame feature set as the Shopify version; available as a WooCommerce integration
BigCommerceJudge.me or YotpoBoth available on the BigCommerce App Marketplace with full feature parity
Custom / HeadlessBuild review APIRequired when reviews need to live in your own database with custom moderation logic

Step 2: Platform-specific setup


Shopify

Option A: Judge.me (recommended — free, full-featured)

  1. Install Judge.me Product Reviews from the Shopify App Store
  2. Judge.me automatically sends a post-purchase review request email after a configurable delay:

- Go to Judge.me → Settings → Review Request Emails - Set delay to 5–7 days after fulfillment (gives customers time to receive and use the product) - Customize the email template with your brand colors and product images

  1. Configure review display:

- Go to Judge.me → Widgets → Install Widgets - Enable the review widget on your product template (Judge.me provides a one-click install) - Enable the star rating snippet in product listings

  1. Enable schema.org markup:

- Go to Judge.me → Settings → SEO - Ensure "Add aggregate rating schema" is enabled — this is what enables star ratings in Google search results

  1. Configure verification and moderation:

- Go to Settings → Review Settings - Enable Verified Purchase Only: only customers who bought the product can leave a review - Enable Auto-publish verified reviews, manual moderation for unverified reviews - Set profanity filter to "Medium" or higher

Option B: Yotpo (mid-market and enterprise)

  1. Install Yotpo Reviews from the App Store
  2. Configure review request timing in Yotpo → Settings → Review Request
  3. Enable Google Shopping Reviews syndication if you run Google Shopping campaigns — Yotpo sends review data directly to Google
  4. Use Yotpo Q&A to add a question-and-answer section below reviews on the PDP

Testing schema.org markup: After enabling Judge.me or Yotpo schema output, validate with Google's Rich Results Test using your product page URL. Star ratings appear in Google Search within 1–2 weeks of indexing.


WooCommerce

WooCommerce built-in reviews (free, basic):

  1. Go to WooCommerce → Settings → Products → Reviews
  2. Enable Enable product reviews
  3. Enable Show "verified owner" label on customer reviews — this restricts reviews to customers who purchased the product
  4. Enable Reviews can only be left by "verified owners" to gate unverified submissions

Adding schema.org markup and enhanced display:

  1. Install WP Product Review from the WordPress plugin directory
  2. WP Product Review adds:

- Aggregate star rating schema.org markup (required for Google rich results) - Star rating display in product listings - Review pros/cons fields

  1. Configure in WP Product Review → Settings

Automating review request emails:

  1. Install Klaviyo or AutomateWoo for post-purchase email automation
  2. In Klaviyo: create a Flow triggered by the "Placed Order" event with a 7-day delay, containing a review request link
  3. In AutomateWoo: go to AutomateWoo → Workflows → Add → trigger: "Order Status Changed to Completed" with a 7-day delay

Judge.me for WooCommerce:

  • Install Judge.me for WooCommerce (available at judge.me)
  • Provides the same review request emails, verified purchase gating, and schema markup as the Shopify version

BigCommerce

Judge.me for BigCommerce:

  1. Go to Apps → Search "Judge.me" and install
  2. Same configuration as the Shopify version — review request emails, schema markup, and verified purchase gating work identically

BigCommerce built-in product reviews:

  1. Go to Products → [Product] → Reviews tab to manually moderate reviews
  2. Go to Settings → Store Settings → Miscellaneous → enable Product Reviews
  3. Built-in reviews do not include schema.org markup — install Judge.me or Yotpo to get Google star ratings in search results

Yotpo for BigCommerce:

  1. Install from the BigCommerce App Marketplace
  2. Includes Google Shopping Reviews syndication and SMS review requests alongside email

Custom / Headless

For headless storefronts, build a review pipeline with post-purchase trigger, moderation, Bayesian aggregate scoring, and schema.org output:

// lib/reviews.ts

// POST /api/reviews — accept review submission with signed token verification
export async function submitReview(req: Request, res: Response) {
  const { token, productId, rating, title, body, authorName } = req.body;

  // Validate signed token (generated in post-purchase email, prevents spam)
  const tokenData = await verifyReviewToken(token);
  if (!tokenData) return res.status(401).json({ error: 'Invalid or expired review token' });

  const verifiedPurchase = await db.orderItems.exists({ orderId: tokenData.orderId, productId });

  // Auto-moderation: spam score + profanity check
  const spamScore = await checkSpam({ body, authorName, ip: req.ip });
  const hasProfanity = await checkProfanity(body + ' ' + title);

  const status =
    spamScore > 0.8 ? 'spam' :
    hasProfanity ? 'pending' :
    verifiedPurchase ? 'approved' : 'pending';

  const review = await db.reviews.create({
    productId, orderId: tokenData.orderId, customerId: tokenData.customerId,
    authorName, authorEmail: tokenData.email, rating, title, body,
    verifiedPurchase, status, approvedAt: status === 'approved' ? new Date() : null,
  });

  if (status === 'approved') await updateProductRatingSummary(productId);

  res.json({ reviewId: review.id, status });
}

// Bayesian aggregate: prevents a 2-review product with 5.0 outranking a 200-review product with 4.7
export async function updateProductRatingSummary(productId: string) {
  const reviews = await db.reviews.findMany({ where: { productId, status: 'approved' } });

  const rawAverage = reviews.length > 0
    ? reviews.reduce((sum, r) => sum + r.rating, 0) / reviews.length : 0;

  const globalMean = await db.reviews.globalAverageRating();
  const C = 5; // confidence weight — trust product's own average after 5+ reviews
  const bayesianAverage = (C * globalMean + reviews.reduce((s, r) => s + r.rating, 0)) / (C + reviews.length);

  await db.productRatingSummaries.upsert({ productId }, {
    productId, reviewCount: reviews.length,
    averageRating: Math.round(bayesianAverage * 10) / 10,
    rawAverageRating: Math.round(rawAverage * 10) / 10,
  });
}

// Emit schema.org AggregateRating JSON-LD — required for Google star ratings in search
export function buildProductSchema(product: Product, ratingSummary: { reviewCount: number; averageRating: number }) {
  return {
    '@context': 'https://schema.org',
    '@type': 'Product',
    name: product.name,
    image: product.images.map(i => i.url),
    description: product.description,
    sku: product.sku,
    offers: {
      '@type': 'Offer',
      price: (product.priceInCents / 100).toFixed(2),
      priceCurrency: 'USD',
      availability: product.inventoryQuantity > 0 ? 'https://schema.org/InStock' : 'https://schema.org/OutOfStock',
    },
    ...(ratingSummary.reviewCount > 0 && {
      aggregateRating: {
        '@type': 'AggregateRating',
        ratingValue: ratingSummary.averageRating.toFixed(1),
        reviewCount: ratingSummary.reviewCount,
        bestRating: '5',
        worstRating: '1',
      },
    }),
  };
}

// Trigger review request email 5 days after delivery
export async function triggerReviewRequest(orderId: string) {
  const order = await db.orders.findById(orderId, { include: ['lineItems.product', 'customer'] });
  const token = await createSignedReviewToken(orderId, order.customerEmail);

  await reviewQueue.add(
    'send-review-request',
    { orderId, email: order.customerEmail, token, products: order.lineItems.map(i => ({ productId: i.productId, name: i.product.name })) },
    { delay: 5 * 86400000, jobId: `review-request-${orderId}` }
  );
}

Step 3: Configure moderation workflow

All review apps need a moderation strategy before go-live:

In Judge.me:

  • Go to Settings → Review Settings → Moderation
  • Set verified reviews to auto-publish; unverified reviews to manual review queue
  • Enable the profanity filter
  • Check the moderation queue weekly at Judge.me → Reviews → Pending

In Yotpo:

  • Go to Yotpo → Moderation → Settings
  • Configure auto-approve rules (e.g., star rating ≥ 3 and verified purchase → auto-approve)
  • Yotpo sends a daily moderation digest email to your configured team email

For custom builds: auto-approve verified purchase reviews that pass spam and profanity checks; queue all others. Never skip moderation entirely — process the pending queue daily.


Step 4: Measure review impact

MetricBenchmarkWhere to Find
Review collection rate3–8% of delivered ordersJudge.me Analytics → Email Performance
Products with 5+ reviewsTrack % of active productsJudge.me → Insights
Average rating4.2–4.7 is healthyPlatform product listing page
Click-through rate from Google star ratingsMonitor in Google Search Console after schema is liveSearch Console → Search Appearance → Rich Results

Best Practices

  • Use Judge.me or Yotpo before building from scratch — they handle schema markup, email timing, verified purchase logic, and moderation queues out of the box
  • Send review requests 5–7 days after delivery, not after shipment — the customer needs time to receive and use the product
  • Never delete negative reviews — suppressing them erodes trust and may violate FTC guidelines; respond to them publicly instead
  • Show verified purchase badges — they increase review trust and help customers distinguish genuine reviews
  • Cap carousels at 5–10 reviews on initial load — lazy load additional reviews to avoid blocking page LCP
  • Validate schema.org markup with Google's Rich Results Test before launching — star ratings appear in search only when the JSON-LD is correct

Common Pitfalls

ProblemSolution
Star ratings not showing in Google SearchEnsure AggregateRating.reviewCount is ≥ 1 and schema is in the <head> as JSON-LD; test with Google's Rich Results Test
Review request sent before product deliveredTrigger the review email from the delivery webhook, not the ship event; add 5-day buffer after delivery
Spam reviews flood the moderation queueEnable Akismet integration in WooCommerce or use Judge.me's built-in spam filter; auto-reject submissions with high spam scores
Duplicate reviews from the same customerJudge.me and Yotpo enforce one review per verified purchase; for custom builds add a unique constraint on (customerId, productId)
Review photos slow the pageJudge.me and Yotpo automatically resize and serve photos via CDN; for custom builds resize to 200px thumbnails at upload time

Related Skills

  • @user-generated-content
  • @customer-segmentation
  • @personalization-engine
  • @conversion-rate-optimization

平台分布

Codex

38.25%
按下载量换算62

Claude

27.72%
按下载量换算45

Cursor

18.68%
按下载量换算30

Gemini CLI

10.02%
按下载量换算16

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

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。来源安全扫描存在提醒或未通过项,安装前请自行复核。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