agentleFS
wdhorizonwdhorizon/skills/hot-monitor/SKILL.md

hot-monitor

Skill1 starsChanged 6 months agoMITView on GitHub

AI hotspot monitoring and trending topic discovery across multiple sources (Bing, Google, DuckDuckGo, HackerNews, Sogou, Bilibili, Weibo, Twitter). Use when users ask about: trending news, hot topics, latest developments in a field, monitoring keywords, tech/AI news discovery, generating hotspot reports, "最近有什么热点", "帮我关注XX动态", "查一下XX最新消息", "生成热点报告", "monitor XX", "what's trending in XX", or any request to search/track/discover current events and trending content across Chinese and international platforms.

  • Reads credentials
  • Installs packages

1 other project uses a version of this, 1 of them edited.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 1

    1. liyupi/yupi-hot-monitor★ 71799% same

    Wrote their own version · 0

    None found.

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository11 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 5 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Search and analyze trending topics across 8+ sources without any server or database.

    line 13
  2. Very specific:

    All scripts are in scripts/.

    line 17
  3. Very specific:

    If you must run on a Python pre-release, install the pure Python charset-normalizer wheel:

    line 27
  4. Distinctive:

    Run search scripts based on scope.

    line 49
  5. Distinctive:

    All scripts output JSON to stdout.

    line 66
  6. Distinctive:

    After collecting search results, apply the analysis framework yourself (no external AI API needed).

    line 70
  7. Distinctive:

    All search scripts support:

    line 115
  8. Very specific:

    If a script exits with Segmentation fault (core dumped) / exit code 139 before printing a Python traceback, check the Python and …

    line 124

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Hot Monitor — AI 热点监控技能

Search and analyze trending topics across 8+ sources without any server or database. Scripts handle data collection; use your own AI capabilities for analysis.

Quick Start

All scripts are in scripts/. Install dependencies first:

pip install requests beautifulsoup4

Recommended runtime: Python 3.12 or 3.13. Avoid Python alpha/beta builds for this skill because requests loads charset-normalizer, and some pre-built charset-normalizer speedup wheels can crash the interpreter on pre-release Python builds before Python can raise an exception.

If you must run on a Python pre-release, install the pure Python charset-normalizer wheel:

pip install requests beautifulsoup4 --no-binary charset-normalizer

Set optional env vars for Twitter (other sources need no keys):

export TWITTER_API_KEY=your_key   # optional, for Twitter search

Core Workflow

1. Understand User Intent

Determine what the user needs:

  • Broad discovery: "最近AI有什么热点" → search multiple sources with broad keywords
  • Specific tracking: "帮我关注GPT-5动态" → targeted search with specific keyword
  • Report generation: "生成今日热点报告" → full pipeline + formatted output

2. Execute Search

Run search scripts based on scope. Always combine international + Chinese sources for comprehensive coverage.

International sources (no API keys needed):

python scripts/search_web.py "AI programming" --sources bing,hackernews,duckduckgo

Chinese sources (no API keys needed):

python scripts/search_china.py "AI编程" --sources sogou,bilibili,weibo

Twitter (requires TWITTER_API_KEY):

python scripts/search_twitter.py "AI programming"

All scripts output JSON to stdout. Combine results for multi-source analysis.

3. Analyze Results

After collecting search results, apply the analysis framework yourself (no external AI API needed). For each result, evaluate:

  1. Authenticity (isReal): Is this genuine news or clickbait/rumor?
  2. Relevance (0-100): How related is this to the user's interest area?
  3. Importance (low/medium/high/urgent): How significant is this development?
  4. Summary: One-sentence Chinese summary of the core information

See references/analysis-guide.md for detailed evaluation criteria.

4. Present Results

Format output as structured report, sorted by importance. Use this template:

## 🔥 热点监控报告 — {keyword}
> 扫描时间: {timestamp} | 数据源: {sources_used}

### 🚨 紧急 (Urgent)
- **{title}** — {summary}
  来源: {source} | 相关性: {relevance}% | [原文链接]({url})

### 🔴 重要 (High)
...

### 🟡 一般 (Medium)
...

### 🟢 低优先级 (Low)
...

---
共发现 {total} 条热点,其中紧急 {urgent} 条,重要 {high} 条

Script Reference

ScriptSourcesAPI KeyOutput
search_web.pyBing, Google, DuckDuckGo, HackerNewsNoneJSON array of {title, content, url, source, publishedAt?}
search_china.pySogou, Bilibili, WeiboNoneJSON array (same schema + engagement metrics)
search_twitter.pyTwitter/XTWITTER_API_KEYJSON array (same schema + author info)
generate_report.py—NoneReads JSON from stdin, outputs Markdown report

Common Options

All search scripts support:

  • --sources: Comma-separated list of sources to use (default: all)
  • --limit: Max results per source (default: 20)
  • --json: Output raw JSON (default, always JSON to stdout)

Error Handling

Scripts output [] (empty JSON array) on failure and print errors to stderr. Always check for empty results and inform the user which sources failed.

If a script exits with Segmentation fault (core dumped) / exit code 139 before printing a Python traceback, check the Python and charset-normalizer versions first:

python3 --version
python3 -m pip show requests charset-normalizer

This is usually a native extension load failure from charset-normalizer, not an application-level exception in the search scripts. Fix it by using Python 3.12/3.13 or reinstalling dependencies with pip install requests beautifulsoup4 --no-binary charset-normalizer.

Advanced Patterns

Keyword Expansion

For better coverage, expand the user's keyword into variants before searching:

  • English/Chinese translations (e.g., "人工智能" ↔ "AI" ↔ "Artificial Intelligence")
  • Abbreviations (e.g., "GPT-5" → also search "GPT5", "OpenAI GPT")
  • Related terms (e.g., "Claude" → also search "Anthropic", "Claude 4")

Bilibili Account Detection

search_china.py supports --detect-account flag. If the keyword matches a Bilibili creator's name, it fetches their latest videos instead of doing a generic search:

python scripts/search_china.py "程序员鱼皮" --detect-account

Multi-keyword Batch

For monitoring multiple keywords, run searches sequentially with a 3-second delay between keywords to respect rate limits.

Reference Files

  • references/search-sources.md — Detailed info about each data source, rate limits, and quirks
  • references/analysis-guide.md — Hotspot analysis framework: authenticity, relevance, importance criteria

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.