Token导航 LogoToken导航

Agent Skill · 研究检索

phone-specs-scraper(手机规格刮刀)

phone-specs-scraper 用于处理浏览器自动化、网页检查和页面信息提取,适合在 Codex、Claude、Cursor、Gemini CLI 中需要让 Agent 打开页面、读取网页或验证前端流程时使用。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。

phone-specs-scraper 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,权限为操作浏览器;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 65,084。

总安装 288周安装 12GitHub Stars 111下载 96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:phone-specs-scraper(手机规格刮刀)
来源仓库:https://github.com/besoeasy/open-skills
仓库路径:skills/phone-specs-scraper
安装命令:
npx skills add https://github.com/besoeasy/open-skills --skill phone-specs-scraper
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/besoeasy/open-skills --skill phone-specs-scraper

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。

用于处理浏览器自动化、网页检查和页面信息提取。适合让 Agent 打开页面、读取网页或验证前端流程。通过 npx 命令从指定 GitHub 仓库安装,需确认权限范围和维护状态。使用前建议核实是否会触发联网、命令执行或文件读写操作。

phone-specs-scraper 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/phone-specs-scraper

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/besoeasy/open-skills --skill phone-specs-scrap…;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

phone-specs-scraper 怎么安装?

在终端执行 npx skills add https://github.com/besoeasy/open-skills --skill phone-specs-scraper。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

phone-specs-scraper 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。

phone-specs-scraper 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。

phone-specs-scraper 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。

phone-specs-scraper 用的人多吗?

公开数据是累计安装 288 次,近一周安装 12 次,下载 96 次,GitHub 111 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。

phone-specs-scraper 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
phone-specs-scraper

手机规格刮刀 · 本页

288111操作浏览器未明确有提醒

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

Phone Specifications Scraper

Extract detailed smartphone specs from popular phone database websites for comparison and research.

When to use

  • User asks to compare phone specifications
  • Researching device features before purchase
  • Building phone comparison tools or databases
  • Finding detailed technical specifications

Required tools / APIs

  • No external API required
  • Web scraping tools: curl, wget, or Playwright/Puppeteer
  • HTML parsing: BeautifulSoup (Python), cheerio (Node.js), or grep/sed (bash)

Phone Spec Websites

Primary Sources

1. GSM Arena (gsmarena.com)

  • Largest phone database with detailed specs
  • URL pattern: https://www.gsmarena.com/[brand]_[model]-[id].php
  • Example: https://www.gsmarena.com/google_pixel_9-13242.php

2. PhoneDB (phonedb.net)

  • Detailed device specifications database
  • URL pattern: https://phonedb.net/index.php?m=device&s=query&d=[device-name]

3. PhoneArena (phonearena.com)

  • Phone reviews and comparisons
  • URL pattern: https://www.phonearena.com/phones/[brand]-[model]

4. MK Mobile Arena (mkmobilearena.com)

  • Side-by-side phone comparisons
  • URL pattern: https://mkmobilearena.com/phone-compare/[phone1]-vs-[phone2]

5. TechRadar (techradar.com)

  • Phone reviews with spec comparisons
  • URL pattern: https://www.techradar.com/phones/[brand]-[model]

6. DeviceBeast (devicebeast.com)

  • Comprehensive device specs
  • URL pattern: https://devicebeast.com/phones/[brand]-[model]

7. Comparigon (comparigon.com)

  • Side-by-side comparisons
  • URL pattern: https://comparigon.com/phones/[brand]-[model]

8. SpecsBattle (specsbattle.com)

  • Detailed phone comparisons
  • URL pattern: https://specsbattle.com/phones/[brand]-[model]

Skills

scrape_gsmarena_specs

Scrape phone specs from GSM Arena using curl and grep.

# Get phone specs from GSM Arena
PHONE_URL="https://www.gsmarena.com/google_pixel_9-13242.php"

# Download page and extract key specs
curl -s "$PHONE_URL" | grep -oP '(?<=<td class="ttl">)[^<]+' | head -20

# Extract specifications table
curl -s "$PHONE_URL" | grep -A2 'class="specs-cp"' | grep -oP '(?<=<td>)[^<]+'

Node.js with cheerio:

const cheerio = require('cheerio');

async function scrapeGSMArenaSpecs(url) {
  const response = await fetch(url);
  const html = await response.text();
  const $ = cheerio.load(html);

  const specs = {};

  // Extract basic info
  specs.name = $('h1.specs-phone-name').text().trim();
  specs.released = $('.specs-cp .specs-cp-release').text().trim();
  specs.weight = $('.specs-cp .specs-cp-weight').text().trim();

  // Extract all specification tables
  $('.specs-cp table').each((i, table) => {
    const category = $(table).find('th').text().trim();
    specs[category] = {};

    $(table).find('tr').each((j, row) => {
      const key = $(row).find('td.ttl').text().trim();
      const value = $(row).find('td.nfo').text().trim();
      if (key && value) {
        specs[category][key] = value;
      }
    });
  });

  return specs;
}

// Usage
// scrapeGSMArenaSpecs('https://www.gsmarena.com/google_pixel_9-13242.php').then(console.log);

search_phone_specs

Search for phone specs across multiple sources.

# Search using SearXNG for phone comparison pages
QUERY="Google Pixel 9 vs Pixel 10 specs comparison"
INSTANCE="https://searx.party"

curl -s "${INSTANCE}/search?q=${QUERY}&format=json" | jq -r '.results[] | select(.url | contains("gsmarena\|phonedb\|mkmobilearena")) | {title, url}'

Node.js:

async function searchPhoneSpecs(phone1, phone2) {
  const query = `${phone1} vs ${phone2} specs comparison`;
  const searxInstances = [
    'https://searx.party',
    'https://searx.tiekoetter.com',
    'https://searx.ninja'
  ];

  for (const instance of searxInstances) {
    try {
      const params = new URLSearchParams({
        q: query,
        format: 'json',
        language: 'en'
      });

      const res = await fetch(`${instance}/search?${params}`, { timeout: 10000 });
      const data = await res.json();

      // Filter for phone spec sites
      const specSites = data.results.filter(r =>
        r.url.includes('gsmarena.com') ||
        r.url.includes('mkmobilearena.com') ||
        r.url.includes('techradar.com') ||
        r.url.includes('phonedb.net')
      );

      if (specSites.length > 0) {
        return specSites;
      }
    } catch (err) {
      console.warn(`Instance ${instance} failed: ${err.message}`);
    }
  }

  throw new Error('No working search instances found');
}

// Usage
// searchPhoneSpecs('Google Pixel 9', 'Google Pixel 10').then(console.log);

compare_two_phones

Compare specifications between two phones with highlighted differences.

async function comparePhones(phone1Specs, phone2Specs) {
  const comparison = {
    matches: [],
    differences: [],
    upgrades: [],
    downgrades: []
  };

  // Compare key specs
  const keyFields = [
    'chipset', 'display', 'battery', 'mainCamera',
    'ram', 'storage', 'weight', 'releaseDate'
  ];

  for (const field of keyFields) {
    const val1 = phone1Specs[field];
    const val2 = phone2Specs[field];

    if (val1 === val2) {
      comparison.matches.push({ field, value: val1 });
    } else {
      comparison.differences.push({
        field,
        phone1: val1,
        phone2: val2
      });

      // Detect upgrades (simplified logic)
      if (field === 'battery' || field === 'ram' || field === 'storage') {
        const num1 = parseInt(val1);
        const num2 = parseInt(val2);
        if (!isNaN(num1) && !isNaN(num2) && num2 > num1) {
          comparison.upgrades.push({ field, from: val1, to: val2 });
        }
      }
    }
  }

  return comparison;
}

// Usage example with formatted output
function formatComparison(comparison) {
  let output = '## Phone Comparison\n\n';

  output += '### ✅ Same Specs\n';
  comparison.matches.forEach(m => {
    output += `- ${m.field}: ${m.value}\n`;
  });

  output += '\n### 🔄 Differences\n';
  comparison.differences.forEach(d => {
    output += `- **${d.field}**:\n`;
    output += `  - Phone 1: ${d.phone1}\n`;
    output += `  - Phone 2: ${d.phone2}\n`;
  });

  output += '\n### ⬆️ Upgrades\n';
  comparison.upgrades.forEach(u => {
    output += `- ${u.field}: ${u.from} → ${u.to}\n`;
  });

  return output;
}

scrape_comparison_site

Scrape pre-formatted comparison from sites like MK Mobile Arena.

# Get comparison from MK Mobile Arena
COMPARISON_URL="https://mkmobilearena.com/phone-compare/google-pixel-9-vs-google-pixel-10"

# Extract comparison table
curl -s "$COMPARISON_URL" | grep -oP '(?<=<td[^>]*>)[^<]+' | head -50

Node.js:

async function scrapeComparisonSite(url) {
  const response = await fetch(url);
  const html = await response.text();
  const $ = cheerio.load(html);

  const comparison = {
    phone1: {},
    phone2: {},
    differences: []
  };

  // Extract phone names
  comparison.phone1.name = $('table tr:first-child td:nth-child(2) h3').text().trim();
  comparison.phone2.name = $('table tr:first-child td:nth-child(3) h3').text().trim();

  // Extract specs row by row
  $('table tr').each((i, row) => {
    const specName = $(row).find('td:first-child').text().trim();
    const phone1Value = $(row).find('td:nth-child(2)').text().trim();
    const phone2Value = $(row).find('td:nth-child(3)').text().trim();

    if (specName && phone1Value && phone2Value) {
      comparison.phone1[specName] = phone1Value;
      comparison.phone2[specName] = phone2Value;

      if (phone1Value !== phone2Value) {
        comparison.differences.push({
          spec: specName,
          phone1: phone1Value,
          phone2: phone2Value
        });
      }
    }
  });

  return comparison;
}

Rate limits / Best practices

  • Respect robots.txt - check /robots.txt before scraping
  • Rate limit: 1 request per second maximum
  • Cache results for at least 1 hour to avoid redundant requests
  • Use rotating User-Agent strings
  • Handle JavaScript-rendered sites with Playwright/Puppeteer when needed
  • Some sites block scrapers - use fallback sources

Agent prompt

You can scrape phone specifications from GSM Arena and other sources. When a user asks to compare phones:

1. First try MK Mobile Arena or similar comparison sites that show side-by-side specs
2. If not available, scrape individual phone pages from GSM Arena
3. Extract key specs: display, chipset, battery, cameras, RAM, storage, release date
4. Highlight differences and upgrades between models
5. Format output with clear sections: Same Specs, Differences, Upgrades

Always cite the source URL and respect site terms of service.

Troubleshooting

Error: "403 Forbidden"

  • Site is blocking scrapers
  • Solution: Try alternative sources (PhoneDB, PhoneArena, TechRadar)

Error: "Empty results"

  • Page structure changed or phone not found
  • Solution: Verify phone name spelling and model number

Error: "JavaScript required"

  • Site uses client-side rendering
  • Solution: Use Playwright/Puppeteer instead of curl

Rate limited

  • Too many requests to the site
  • Solution: Add delays (sleep 2) between requests

See also

平台分布

Codex

37.29%
按下载量换算36

Claude

29.81%
按下载量换算29

Cursor

19.39%
按下载量换算19

Gemini CLI

8.72%
按下载量换算8

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

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。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