Skip to content
TrustedSkillsbeta
Back to all skills

Weibo_Hotspot_Analyzer

Listed
violin86318·vlatest·other

Analyzes trending Weibo topics to identify popular discussions and sentiment, providing valuable insights for market research & social listening.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add beyond-motion/weibo-hotspot-analyzer --skill weibo_hotspot_analyzer -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

violin86318

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill failed 1 of 6 checks. A failure is not proof of bad intent; it means something in the code needs a human to look at it before you run it.

  • No undeclared network calls: failed

    Contacts 4 hosts that are neither well-known infrastructure nor declared in the skill's frontmatter: console.anthropic.com, newapi.cpolar.top, repo1.maven.org, www.tianapi.com.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

    Hosts contacted

    newapi.cpolar.topundeclaredrepo1.maven.orgundeclaredwww.tianapi.comundeclaredconsole.anthropic.comundeclaredgithub.comsource host

    What it found (3 of 4)

    • .github/workflows/weibo-daily.yml:42contacts newapi.cpolar.top
      API_ENDPOINT: https://newapi.cpolar.top/v1/chat/completions
    • SECURITY_FIX.md:57contacts repo1.maven.org
      wget https://repo1.maven.org/maven2/com/madgag/bfg/1.14.0/bfg-1.14.0.jar
    • migrate_to_github.sh:156contacts www.tianapi.com
      | `TIANAPI_KEY` | `your-tianapi-key` | [tianapi.com](https://www.tianapi.com/) |

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned violin86318/weibo-hotspot-analyzer at eddc78327c.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
eddc78327c
Manifest
SKILL.md
Scanned
60 files, 3,260 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

The Weibo Hotspot Analyzer skill helps users discover market opportunities and generate product ideas by analyzing trending topics on China's popular microblogging platform, Weibo. It automatically scrapes the top 50 Weibo trends, researches their background information, uses AI to extract creative product concepts based on a "fun factor (80%) + usefulness (20%)" scoring system, and generates a visual HTML report summarizing its findings. This skill is designed for product managers, entrepreneurs, and developers seeking actionable insights from real-time social media trends.

When to use it

  • Identify potential new product ideas based on current popular discussions in China.
  • Gain an understanding of the context and background behind trending Weibo topics.
  • Generate multiple creative concepts quickly for products related to specific viral events.
  • Create a visually appealing report summarizing key findings for stakeholders.
  • Stay informed about emerging trends and potential market opportunities on Weibo.

Key capabilities

  • Real-time Hotspot Scraping: Automatically fetches the top 50 trending topics from Weibo using the Tianji Data Row API, including keywords, popularity scores, and tags.
  • Intelligent Background Search: Uses web search to gather news articles, event timelines, and social context related to each trending topic.
  • AI-Powered Creative Analysis: Generates product ideas based on background information, scoring them based on "fun" (80%) and "usefulness" (20%).
  • Multiple Idea Generation: Creates several product concept proposals for each trending topic, including name suggestions, core features, and target user descriptions.
  • Visualized HTML Reporting: Generates responsive HTML reports with a vibrant orange theme, suitable for viewing on mobile devices, highlighting top-scoring ideas.

Example prompts

  • "Analyze the current Weibo hotspots and suggest product ideas."
  • "What are the trending topics on Weibo right now, and what's the background of each?"
  • "Generate creative product concepts based on the top 5 Weibo trends today."

Tips & gotchas

  • Requires access to the Tianji Data Row API for fetching Weibo data.
  • The skill prioritizes "fun" (80%) over "usefulness" (20%) when generating ideas, so expect some unconventional suggestions.
  • The generated HTML reports are saved locally with a date-based filename and directory structure.