About this skill

Problem

When reviewing WeChat public account content, teams often need a concrete answer: which articles actually gained traction in the last few days? Manually checking dashboards, third-party rankings, or exporting tables can turn a simple audit into a time sink, especially when “viral” has no shared definition.

How It Works

The skill filters articles using two default criteria: days set to 7 and min_read set to 100000. The input schema also includes fields such as source, keyword, and api_key, allowing the skill to pull eligible articles from available data sources.

Time window: extracts articles published within the last 7 days by default, configurable via days.
Read-count threshold: keeps articles with at least 100,000 reads by default, configurable via min_read.
Data sources: supports Newrank API, GSData API, Sogou WeChat Search as fallback, and custom databases.
Output goal: aggregates articles that match “recent + high reads” for follow-up review, topic comparison, or content analysis.

Boundaries

This skill focuses on hot-article extraction, not full sentiment analysis, comment collection, or rights management. Results depend on the availability and field coverage of the selected source. keyword can narrow scope, but it is not equivalent to semantic search. Use it only when API access and read-count definitions are consistent.

Screenshots

Use Cases

Editors reviewing weekly topics extract WeChat articles from the last 7 days with over 100k reads.
Operations teams monitoring competitors pull recent high-read articles by keyword and read-count threshold.
Analysts preparing industry heat reviews filter last-7-day viral articles from Newrank or GSData.
Content strategists aggregate recent high-read articles from multiple sources into a candidate list.

Best For

Content editors responsible for topic review and weekly extraction of high-read WeChat articles.
Operations staff monitoring competitor accounts and filtering recent viral articles by read threshold.
Analysts doing industry content analysis and extracting hot articles from multiple data sources.
Data engineers maintaining content databases and filtering articles by date and read count.