Public Opinion Insights
Paste the following prompt into your AI chat to install this skill:
Follow https://skillhub.cn/install/skillhub.md to install @user_830fe0f8/public-opinion-insights.
About this skill
Problem Space
When public-opinion analysis requires focus on a specific object and a subset of dimensions, a full report can be too long, while manual decomposition can miss context. public-opinion-insights addresses the need for conclusion-level output around an event, topic, or subject, returning structured insights rather than a complete long-form report.
How It Works
The skill calls the internal public-opinion analysis service via /api/chat. The main input is message, which should describe the analysis target and, where possible, name the dimensions to inspect, such as those listed in references/analysis_dimension.md. The response is usually Markdown or similar text, making it easy to embed in downstream analysis flows. It requires MIDU_API_KEY in OpenClaw, using the same authentication model as public-opinion-report.
Boundaries
Use this skill for on-demand insights on a specific metric or module, not for generating a full public-opinion report. Complex analyses may take several minutes, so callers should allow enough wait time. Do not send repeated or concurrent requests before a response returns.
Use Cases
- Extract conclusions for a specified analysis dimension during a single-event review.
- Focus on one analysis dimension when screening a named topic for risk.
- Prepare meeting materials by retrieving structured conclusions for a subject dimension.
- Compare events on the same analysis dimension and produce short conclusions.
Best For
- Public-opinion ops analysts: need conclusion-level output for one event and one dimension, not a full report.
- Risk brief writers: need dimension-based conclusions extracted for meeting materials.
- Brand PR reviewers: need structured conclusions for a named subject on a single topic.
- Internal service engineers: need to call the dimension-insight API in OpenClaw and surface results.
Related Skills
Fetches Baidu Hot Search Top 10 titles using web_fetch first, validates same-day data, and falls back to browser automation when stale.
Generates an evening A-share policy and trading opportunity daily report by collecting same-day index, policy, and capital data, then applying a fixed template to highlight beneficiary sectors, drivers, and price directions.
Maps natural-language TikTok requests to KeyAPI REST scenarios, validates endpoints against docs, and executes data queries and analysis.
Extract city-specified AI jobs from BOSS Zhipin, save CSV/table data, mark new postings, and summarize salary trends, application advice, and HTML reports.