Movers
独生子女不一定能继承父母全部遗产: #14 → #5 → #5, heat +81% — rising AI短剧持械入宋剧情太牛: #2 → #2 → #2, 975,639 → 951,149 — peaking 波司登AREAL这阵容是天花板级吧: #28 → #18 → #47 — spiked, then fading
Tell which Weibo hot-search topics are rising, peaking or fading by comparing repeated snapshots.
v0.1.1
View example draft · How to useExample draft
Three snapshots from 15:31 to 16:10 Beijing time on 2026-11-05.
独生子女不一定能继承父母全部遗产: #14 → #5 → #5, heat +81% — rising AI短剧持械入宋剧情太牛: #2 → #2 → #2, 975,639 → 951,149 — peaking 波司登AREAL这阵容是天花板级吧: #28 → #18 → #47 — spiked, then fading
AI短剧持械入宋: about 10 on-topic posts a minute at 15:33, 3–5 at 16:13; the first media wave is over and ordinary viewers carry it now.
Excerpt from an actual run. Political topics are reported as data only.
An Agent that can read the complete Skill folder. Live research also needs a SandBase connection; supplied material can be used without a lookup. It needs about 20–40 minutes for repeated snapshots.
Download and unpack the complete Skill folder, keep its references, and use it with a local Agent that supports Skills.
Use weibo-hot-lifecycle to take three Weibo hot-search snapshots 20 minutes apart. Tell me what is taking off, what is fading, and whether the AI micro-drama topic is still climbing.
Save the hot list at a fixed interval, at least three times; drop ads.
Match topics, compute position and heat change, and classify each stage.
Read the newest posts for chosen topics twice and compare the flow.
Download and unpack the whole Skill folder, including references, into your Agent’s supported Skill directory. You can also ask the Agent to read its SKILL.md and follow the instructions. Run it locally with your own material.
One list shows what is hot. Change over time shows what is moving, which a single list cannot.