This one scrapes Weibo's trending topics via an API, searches for background context on each trend, then uses AI to generate product ideas weighted 80% for virality and 20% for utility. It outputs an HTML report with scores, user personas, and feature lists for each concept. The workflow is pretty opinionated: it hits the Tianjushu API for top 50 trends, does web searches for event context, generates 3-5 product ideas per trend with structured breakdowns, then saves everything to a dated HTML file organized by year and month. Use this if you're hunting for product opportunities in Chinese social trends and want the grunt work automated. Fair warning that API rate limits apply and same-day reruns will overwrite your previous report.

skills.sh installs
312
last updated
Jun 3, 2026

Install

$ npx -y skills add violin86318/weibo-hotspot-analyzer --skill weibo_hotspot_analyzer --agent claude-code

Installs into .claude/skills of the current project.

Files

[技能说明] 自动化分析微博热搜并转化为产品创意的智能助手。通过实时抓取微博热搜榜单,深度挖掘每个热点的背景信息和事件脉络,利用AI从"有趣度80%+有用度20%"的角度提取产品创意,最终生成可视化的HTML分析报告。帮助产品经理、创业者、开发者快速发现市场机会,将热点转化为可执行的产品方案。

[核心能力] - 实时热搜抓取:通过天聚数行API自动获取微博热搜TOP50榜单,包含热搜词、热度指数、标签 - 智能背景搜索:对每个热搜话题使用Web Search工具搜索相关新闻、事件脉络、社会背景 - AI创意分析:基于热点信息,从"有趣度80分+有用度20分"的多维度评分体系提取产品创意 - 多创意生成:为每个热搜生成多个产品创意方案,包含名称、核心功能、目标用户描述 - 可视化报告:生成响应式HTML报告,活力橙主题,支持手机/平板查看,高亮展示高分创意 - 智能评分分级:自动计算综合评分,>80分标注为优秀,60-80分标注为良好

[执行流程] 第一步:抓取微博热搜榜单 - 运行 python scripts/fetch_weibo_hot.py 调用天聚数行API - 获取热搜TOP50数据:热搜词、热度指数、热搜标签 - 解析JSON格式返回结果,验证数据完整性

Sponsors

Details

Repository
github.com/violin86318/weibo-hotspot-analyzer
First seen
Jun 3, 2026

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
2mattpocock avatargrill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.5Mskills.sh installs
3shadcn avatarimproveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
5forrestchang avatarkarpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
6vercel-labs avatarfind-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs