Trend Monitor

trend-monitor

Multi-platform hotspot sweep. Pulls the latest crawl batch from the trendradar MCP, runs preset-focus and emergent keyword extraction in parallel, then summarizes either by platform or by topic.

When to activate

Trigger on phrases like:

• 今日热点 / 今天有什么热点 / 今天热搜
• 各平台热搜 / 看一下当前热搜 / 全网热点 / 全网在聊什么
• 现在在火什么 / 最近在聊什么
• what's trending / what's trending now / multi-platform sweep / hotspot snapshot
• 给我看一下 zhihu / weibo / douyin / bilibili / toutiao / baidu / thepaper / ifeng / tieba / cls-hot / wallstreetcn-hot 的热搜

If the user names a single article, a specific topic deep-dive, or a date in the past, this is not the right skill — defer to a search/topic-analysis skill instead. This skill is for the live cross-platform snapshot.

Workflow

1. Resolve the time window. If the user mentions any date that isn't "now / 现在 / 今天 / today", call mcp__trendradar__resolve_date_range first and reuse that range in the next steps. For "今天 / now / latest", skip this step.

1. Pull the latest news batch. Call mcp__trendradar__get_latest_news with limit=80 and include_url=False. Set include_url=True only if the user explicitly asked for links. If the user named specific platforms, pass platforms=[...] (e.g. ["weibo", "zhihu"]); otherwise let the tool return the full set.

1. Run keyword extraction in parallel. Issue both calls in the same response:

• mcp__trendradar__get_trending_topics with extract_mode="keywords", top_n=20 — preset focus list (curated themes the project tracks).
• mcp__trendradar__get_trending_topics with extract_mode="auto_extract", top_n=20 — emergent terms surfaced from this batch only.

1. Cross-reference. Build two buckets before drafting the output:

• 全网共振: keywords that appear on ≥3 platforms in this batch (pulled from either extraction mode).
• 新冒头: terms present in auto_extract results but absent from the keywords preset list — these are the emergent signals worth flagging.

1. Pick the output template based on user intent (see "Output templates" below). Default to 平台分组视图 unless the user asked for themes / topics / "what's everyone talking about across platforms".

Output templates

Pick one. Both end with the same closing block.

平台分组视图 (default)

# 今日全网热点 · 

## 微博 (weibo)
1.  · 热度 
2. ...
(top 5)

## 知乎 (zhihu)
1. ...
(top 5)

## 抖音 (douyin)
...

## B站 (bilibili)
...

(只列出本批次实际有数据的平台，每个平台 top 5)

---

### 全网共振
- **** — 出现在 weibo / zhihu / toutiao（3 个平台）
- **** — 出现在 weibo / douyin / bilibili / baidu（4 个平台）

### 新冒头 (auto-extract only)
- **** — 首次在本批次浮现，主要源自 
- **** — ...

主题分组视图 (when user asks for cross-platform themes)

# 今日热点主题 · 

## 
- 微博 #2: 
- 知乎 #5: 
- 抖音 #1: 

## 
- 头条 #3: ...
- 百度 #7: ...

(每个主题列出实际证据：哪个平台、第几名、标题片段)

---

### 全网共振
- **** — 出现在 X / Y / Z（N 个平台）

### 新冒头 (auto-extract only)
- **** — 首次在本批次浮现，主要源自 

Both templates: keep each platform / theme block to top 5, no pagination, no link dumps.

Edge cases

• get_latest_news returns empty / very stale. Call mcp__trendradar__get_system_status to check crawl freshness. If the latest crawl is clearly stale, fall back to mcp__trendradar__get_latest_rss and tell the user the snapshot is from RSS feeds, not the platform crawl. Don't silently substitute.
• User asks for a platform not in the supported list. Supported set: zhihu, weibo, douyin, bilibili, toutiao, baidu, thepaper, ifeng, tieba, cls-hot, wallstreetcn-hot. If they ask for something else (e.g. xiaohongshu, twitter), say so explicitly, list what is available, and ask whether to proceed with the closest covered platforms.
• One of the two extraction calls fails. Render the output with whatever succeeded and note which bucket (preset / emergent) is missing. Don't block the whole response on a single failure.
• User asks for a date in the past. Resolve via mcp__trendradar__resolve_date_range, then use mcp__trendradar__get_news_by_date instead of get_latest_news. Same extraction + cross-reference flow afterwards.
• Ambiguous "今天" near midnight. Trust get_latest_news — it returns the most recent crawl batch regardless of wall-clock date.

Don'ts

• Don't paginate huge lists. Cap at top 5 per platform / per theme. The user wants a snapshot, not a dump.
• Don't include URLs unless the user explicitly asked for them. include_url=False is the default for a reason — links blow up the output.
• Don't fabricate trend data when MCP fails. If get_latest_news errors out and the RSS fallback also fails, say so plainly and stop — never invent platform rankings.
• Don't merge preset-keyword and auto-extract output into one undifferentiated list. The 全网共振 / 新冒头 split is the whole point of running both extraction modes.
• Don't issue the two get_trending_topics calls sequentially. They are independent — fire them in parallel.

See also

• [../docs/mcp-tools.md](../docs/mcp-tools.md) — full mcp__trendradar__* tool catalog (parameters, return shapes, rate-limit notes).

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: asoiso
• Source: asoiso/trend-radar
• License: Apache-2.0
• Homepage: https://agentskills.io

Install and usage instructions live in the source repository linked above.