This skill helps users automatically extract structured news data from Google News via BrowserAct API. Agent should proactively apply this skill when users express needs like searching for news about a specific topic, tracking industry trends, monitoring public relations or sentiment, collecting competitor updates, getting latest reports on specific keywords, monitoring brand exposure in media, researching market hot topics, summarizing daily industry news, tracking media activities of specific
SkillScore86Maintained
Automatic
◆Research pack
Last verified 8/9/2026
What it changes
Passed 16 of 18 test cases with the skill, and 7 of 18 without it.
Without skill36%
With skill86%
Checks it passed that the model alone missed
Uses 30 as the default numerical item limit.
Selects `past year` as the time range argument.
Supplies `past hours` as the time range argument.
and 11 more in the full report
11 fixed8 passed either way3 still failing0 broke
Pass-rate lift
+50 pp
Tokens
+23%
Agent turns
0%
Response time
-57%
Model gemini-3.6-flashMeasured 8/9/2026v119 of 22 cases passed with skill · 18 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 10
Prompt
What is the exact single-line bash command structure used to run the Google News API Python script with unbuffered output for keyword 'Robotics', time range 'past week', and quantity 15?
What was checked, without and with the skill
Checked
Without skill
With skill
Formats the execution invocation starting with `python -u ./scripts/google_news_api.py`.
Missed
Passed
Orders the positional parameters sequentially as search keyword, publish date filter, and item quantity.
Missed
Passed
case-13 · gemini-3.6-flash · 8/9/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md86 lines2 filesincludes scripts
Google News Automation Skill
📖 Introduction
This skill provides a one-stop news collection service using BrowserAct's Google News API template. It directly extracts structured news results from Google News, including headlines, sources, publication times, and article links. Simply input search keywords and time filters to get clean, usable news data.
✨ Features
No Hallucinations: Pre-set workflows avoid AI generative hallucinations, ensuring stable and precise data extraction.
No Captcha Issues: No need to handle reCAPTCHA or other verification challenges.
No IP Restrictions: No need to handle regional IP restrictions or geofencing.
Faster Execution: Tasks execute faster compared to pure AI-driven browser automation solutions.
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, please visit the BrowserAct Console to get your Key."
🛠️ Input Parameters
Agent should flexibly configure the following parameters based on user needs:
Search_Keywords (Search Keywords)
Type: string
Description: The content to search on Google News. Can be company names, industry terms, competitor names, etc.
Example: AI Startup, Tesla, SpaceX
Publish_date (Time Range)
Type: string
Description: Filter news by publication time.
Options:
any time: No restriction
past hours: Past few hours (breaking news)
past 24 hours: Past 24 hours (daily monitoring)
past week: Past week (short-term trends)
past year: Past year (long-term research)
Default: past week
Datelimit (Max Items)
Type: number
Description: Maximum number of news items to extract per task.
Fetches comments from an Instagram post including comment text, username, timestamp, like count and reply count. Use when user mentions Instagram comments scraping, get comments from Instagram post, Instagram comment list, pull Instagram comments, read Instagram comments, Instagram post discussion, extract Instagram comments, comment data from Instagram, IG post replies, who commented on Instagram.