‹ 首页

social-media-finder-skill

@browser-act · 收录于 1 周前 · 上游提交 2 天前

This skill helps users automatically find social media profiles across platforms like Facebook, Twitter, Instagram, LinkedIn, etc. using the BrowserAct API. Agent should proactively apply this skill when users express needs like finding someone's social media accounts, discovering a brand's social media presence, tracking down social profiles of job candidates, finding contact info for sales prospects, researching a person's digital footprint, verifying the identity of someone met online, monitoring the social media reach of influencers, checking social accounts of business competitors, gathering public profiles for background research, locating official customer service accounts across platforms, or compiling contact databases for networking.

适合你,如果需要批量获取个人或品牌的社交账号信息。

/ 下载安装
social-media-finder-skill.skill双击,或拖进 Claude 桌面版 / Cowork,即完成安装↓ .skill↓ .zip
用别的 agent?下载 .zip 解压,把文件夹放进它的技能目录
Claude Code~/.claude/skills/(项目级 .claude/skills/)
Codex CLI~/.codex/skills/
Cursor自动读取上面两处目录
其他工具见其文档的「skills」目录;两个下载是同一份文件,只是名字不同
/ 通过 npx 安装 校验哈希
npx oh-my-skill add browser-act/skills/social-media-finder-skill
/ 通过 bash 安装
curl -fsSL https://oh-my-skill.com/install.sh | bash -s -- browser-act/skills/social-media-finder-skill
/ 已经装过?验证本机副本,不用重装
npx oh-my-skill verify browser-act/skills/social-media-finder-skill
安装目标可用 --agent / --scope 或 --to 明确指定;省略时只会在唯一已存在的 agent 目录上自动选择,零命中或多命中会停止并提示。content_hash 缺失或不一致均拒装。
4386GitHub stars
~1.2K最小装载
~2K含声明引用
~2K文本包总量
镜像托管

怎么用

商店整理自技能原文 · 版本 51daea1 · 表述以原文为准
它做什么

装上后,Claude 能根据你提供的姓名或品牌名,自动搜索 Facebook、Twitter、Instagram、LinkedIn 等多个平台的社交账号,并返回包含个人主页链接、用户名、粉丝数和简介的 CSV 文件。

什么时候触发

当你需要查找某人的社交媒体账号、了解品牌的社交存在、收集销售线索或进行背景调查时,Claude 会自动触发此技能。

装好后可以这样说
Claude 会搜索并返回 CSV 文件。
Claude 会搜索品牌并返回结果。
Claude 会执行搜索并返回相关平台信息。
技能原文 SKILL.md作者撰写 · MIT · 51daea1

Social Media Finder Skill

📖 Brief

This skill automates the discovery of social media accounts associated with individuals, brands, or businesses across multiple platforms. By providing a name, it searches across Facebook, Twitter, Instagram, LinkedIn, TikTok, and more — extracting profile URLs, usernames, follower counts, and bio snippets in one go. The results are returned as a downloadable CSV file.

✨ Features
  1. No Hallucinations: Pre-set workflows avoid AI generative hallucinations, ensuring stable and precise data extraction.
  2. No Captcha Issues: No need to handle reCAPTCHA or other verification challenges.
  3. No IP Restrictions: No need to handle regional IP restrictions or geofencing.
  4. Faster Execution: Tasks execute faster compared to pure AI-driven browser automation solutions.
  5. Cost-Effective: Significantly lowers data acquisition costs compared to high-token-consuming AI solutions.
🔑 API Key Setup

Before running, check the BROWSERACT_API_KEY environment variable. If not set, do not take other measures; ask and wait for the user to provide it. Agent must inform the user:

"Since you haven't configured the BrowserAct API Key yet, please visit the BrowserAct Console to get your Key."
🛠️ Input Parameters

The agent should configure the following parameter based on user requirements:

  1. People_Name
  2. Required: Yes
  3. Type: string
  4. Description: The name of the person or brand to search for. Use + between words for better results.
  5. Example: John+Smith, Tesla, Bill+Gates
  6. Default: Mike+Smith
🚀 Invocation Method

Agent should execute the following command to invoke the skill:

# Example invocation
python -u ./scripts/social_media_finder.py "John+Smith"
⏳ Execution Monitoring

Since this task involves automated browser operations, it may take several minutes. The script outputs timestamped status logs continuously (e.g., [14:30:05] Task Status: running). Agent guidelines:

  • Monitor the terminal output while waiting.
  • As long as new status logs appear, the task is running normally; do not misjudge it as frozen.
  • Only consider triggering retry if the status remains unchanged for a long time or output stops without a final result.
📊 Data Output

Upon successful execution, the script retrieves a JSON object containing a files array with a download link to a CSV file. The CSV includes the following structured profile data:

  • Platform name: The social media platform (e.g., LinkedIn, Twitter).
  • Followers count: The number of followers.
  • Page title: The title of the profile page.
  • Description snippet: The bio or description snippet.
  • Profile URL: The direct link to the social media profile.
⚠️ Error Handling & Retry

If an error occurs during script execution (e.g., network fluctuations or task failure), the Agent should follow this logic:

  1. Check Output Content:
  2. If the output contains "Invalid authorization", it means the API Key is invalid or expired. Do not retry; guide the user to re-check and provide the correct API Key.
  3. If the output contains "concurrent" or "too many running tasks", it means the concurrent task limit has been reached. Do not retry; guide the user to upgrade their plan. Agent must inform the user: > "The current task cannot be executed because your BrowserAct account has reached the concurrent task limit. Please visit the BrowserAct Plan Upgrade Page to upgrade your plan."
  4. If the output does not contain the above error keywords but the task failed (e.g., output starts with Error: or returns empty results), the Agent should automatically re-execute the script once.
  1. Retry Limit:
  2. Automatic retry is limited to one time. If the second attempt fails, stop retrying and report the specific error to the user.
🌟 Typical Use Cases
  1. Background Research: Find social media profiles of job candidates or new connections.
  2. Lead Generation: Gather contact information and social profiles for sales prospects.
  3. Competitive Intelligence: Discover the social media footprint of competitors.
  4. Influencer Discovery: Locate content creators across various platforms.
  5. Brand Monitoring: Check a brand's presence across different social networks.
  6. Reconnecting: Find old friends or colleagues online.
  7. Identity Verification: Cross-reference profiles of people met online.
  8. Customer Support: Find official brand accounts for reaching out.
  9. Networking: Research event attendees or potential business partners.
  10. Digital Footprint Audit: Monitor one's own public social media presence.
按 MIT 许可原样转载,未经改动 · 在 GitHub 查看 →

评论

登录即可评论;带「已验证安装」的,是发布者名下有本店的安装或持有记录。