This skill helps users automatically extract official website and social media profiles. Agent should proactively apply this skill when users express needs like search for official website and social media contacts of a company, find YouTube and LinkedIn profiles by company name, extract social media links from a specific website URL, discover a company's X and Facebook presence, gather business contact details using their brand name, retrieve TikTok and Instagram links from a target website, track competitor social media strategy, extract multi-platform social links for lead generation, find official contact channels of local businesses, collect canonical profile URLs for outreach campaigns, or build a contact database from Yellow Pages leads.
This skill integrates two BrowserAct templates to cover two common scenarios. When the user provides a company name, it searches Google to extract the company's official website and social media channels. When the user provides a website URL, it scrapes the site to extract social media profile links (LinkedIn, Facebook, X/Twitter, Instagram, YouTube, TikTok). The script auto-detects the input type and routes to the correct template.
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."
The agent should determine whether the input is a company name or a website URL and pass it to the script. The script automatically routes the request to the correct template.
stringOpenAI or https://www.rotorooter.com/Agent should execute the following command to invoke the skill:
# Search by company name
python -u ./scripts/business_contact_social_links.py "OpenAI"
# Scrape by website URL
python -u ./scripts/business_contact_social_links.py "https://www.rotorooter.com/"
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:
Upon successful execution, the script prints structured JSON data extracted from the API response.
If a Company Name was provided, the output includes:
Company Name: The official name of the company.Current Page URL: The official website URL.Social Media Information: A consolidated list of discovered social media profiles.If a Website URL was provided, the output includes an array of objects:
platform: Platform name (e.g., LinkedIn, YouTube).url: Canonical URL of the external profile.If an error occurs during script execution (e.g., network fluctuations or task failure), the Agent should follow this logic:
Check Output Content:
"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."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."
Error: or returns empty results), the Agent should automatically re-execute the script once.Retry Limit: