hot-monitor

Name: hot-monitor
Author: liyupi

662stars132forks

How to install hot-monitor?

liyupi/yupi-hot-monitor/hot-monitor

$npx -y skills add liyupi/yupi-hot-monitor --skill hot-monitor

Installs into the current project.

Summary

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, ge

Files · 1

View on GitHub

SKILL.md

1	# Hot Monitor — AI 热点监控技能
2
3	Search and analyze trending topics across 8+ sources without any server or database. Scripts handle data collection; use your own AI capabilities for analysis.
4
5	## Quick Start
6
7	All scripts are in `scripts/`. Install dependencies first:
8
9	```bash
10	pip install requests beautifulsoup4
11	```
12
13	Set optional env vars for Twitter (other sources need no keys):
14	```bash
15	export TWITTER_API_KEY=your_key # optional, for Twitter search
16	```
17
18	## Core Workflow
19
20	### 1. Understand User Intent
21
22	Determine what the user needs:
23	- Broad discovery: "最近AI有什么热点" → search multiple sources with broad keywords
24	- Specific tracking: "帮我关注GPT-5动态" → targeted search with specific keyword
25	- Report generation: "生成今日热点报告" → full pipeline + formatted output
26
27	### 2. Execute Search
28
29	Run search scripts based on scope. Always combine international + Chinese sources for comprehensive coverage.
30
31	International sources (no API keys needed):
32	```bash
33	python scripts/search_web.py "AI programming" --sources bing,hackernews,duckduckgo
34	```
35
36	Chinese sources (no API keys needed):
37	```bash
38	python scripts/search_china.py "AI编程" --sources sogou,bilibili,weibo
39	```
40
41	Twitter (requires `TWITTER_API_KEY`):
42	```bash
43	python scripts/search_twitter.py "AI programming"
44	```
45
46	All scripts output JSON to stdout. Combine results for multi-source analysis.
47
48	### 3. Analyze Results
49
50	After collecting search results, apply the analysis framework yourself (no external AI API needed). For each result, evaluate:
51
52	1. Authenticity (`isReal`): Is this genuine news or clickbait/rumor?
53	2. Relevance (0-100): How related is this to the user's interest area?
54	3. Importance (low/medium/high/urgent): How significant is this development?
55	4. Summary: One-sentence Chinese summary of the core information
56
57	See [references/analysis-guide.md](references/analysis-guide.md) for detailed evaluation criteria.
58
59	### 4. Present Results
60
61	Format output as structured report, sorted by importance. Use this template:
62
63	```markdown
64	## 🔥 热点监控报告 — {keyword}
65	> 扫描时间: {timestamp} \| 数据源: {sources_used}
66
67	### 🚨 紧急 (Urgent)
68	- {title} — {summary}
69	来源: {source} \| 相关性: {relevance}% \| [原文链接]({url})
70
71	### 🔴 重要 (High)
72	...
73
74	### 🟡 一般 (Medium)
75	...
76
77	### 🟢 低优先级 (Low)
78	...
79
80	---
81	共发现 {total} 条热点，其中紧急 {urgent} 条，重要 {high} 条
82	```
83
84	## Script Reference
85
86	\| Script \| Sources \| API Key \| Output \|
87	\|--------\|---------\|---------\|--------\|
88	\| `search_web.py` \| Bing, Google, DuckDuckGo, HackerNews \| None \| JSON array of `{title, content, url, source, publishedAt?}` \|
89	\| `search_china.py` \| Sogou, Bilibili, Weibo \| None \| JSON array (same schema + engagement metrics) \|
90	\| `search_twitter.py` \| Twitter/X \| `TWITTER_API_KEY` \| JSON array (same schema + author info) \|
91	\| `generate_report.py` \| — \| None \| Reads JSON from stdin, outputs Markdown report \|
92
93	### Common Options
94
95	All search scripts support:
96	- `--sources`: Comma-separated list of sources to use (default: all)
97	- `--limit`: Max results per source (default: 20)
98	- `--json`: Output raw JSON (default, always JSON to stdout)
99
100	### Error Handling
101
102	Scripts output `[]` (empty JSON array) on failure and print errors to stderr. Always check for empty results and inform the user which sources failed.
103
104	## Advanced Patterns
105
106	### Keyword Expansion
107
108	For better coverage, expand the user's keyword into variants before searching:
109	- English/Chinese translations (e.g., "人工智能" ↔ "AI" ↔ "Artificial Intelligence")
110	- Abbreviations (e.g., "GPT-5" → also search "GPT5", "OpenAI GPT")
111	- Related terms (e.g., "Claude" → also search "Anthropic", "Claude 4")
112
113	### Bilibili Account Detection
114
115	`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:
116
117	```bash
118	python scripts/search_china.py "程序员鱼皮" --detect-account
119	```
120
121	### Multi-keyword Batch
122
123	For monitoring multiple keywords, run searches sequentially with a 3-second delay between keywords to respect rate limits.
124
125	## Reference Files
126
127	- [references/search-sources.md](references/search-sources.md) — Detailed info about each data source, rate limits, and quirks
128	- [references/analysis-guide.md](references/analysis-guide.md) — Hotspot analysis framework: authenticity, relevance, importance criteria

People who liked this also viewed

6 picks

Type

hot-monitor

662stars132forks

View on GitHub

How to install hot-monitor?

liyupi/yupi-hot-monitor/hot-monitor

$npx -y skills add liyupi/yupi-hot-monitor --skill hot-monitor

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Hot Monitor — AI 热点监控技能
2
3	Search and analyze trending topics across 8+ sources without any server or database. Scripts handle data collection; use your own AI capabilities for analysis.
4
5	## Quick Start
6
7	All scripts are in `scripts/`. Install dependencies first:
8
9	```bash
10	pip install requests beautifulsoup4
11	```
12
13	Set optional env vars for Twitter (other sources need no keys):
14	```bash
15	export TWITTER_API_KEY=your_key # optional, for Twitter search
16	```
17
18	## Core Workflow
19
20	### 1. Understand User Intent
21
22	Determine what the user needs:
23	- Broad discovery: "最近AI有什么热点" → search multiple sources with broad keywords
24	- Specific tracking: "帮我关注GPT-5动态" → targeted search with specific keyword
25	- Report generation: "生成今日热点报告" → full pipeline + formatted output
26
27	### 2. Execute Search
28
29	Run search scripts based on scope. Always combine international + Chinese sources for comprehensive coverage.
30
31	International sources (no API keys needed):
32	```bash
33	python scripts/search_web.py "AI programming" --sources bing,hackernews,duckduckgo
34	```
35
36	Chinese sources (no API keys needed):
37	```bash
38	python scripts/search_china.py "AI编程" --sources sogou,bilibili,weibo
39	```
40
41	Twitter (requires `TWITTER_API_KEY`):
42	```bash
43	python scripts/search_twitter.py "AI programming"
44	```
45
46	All scripts output JSON to stdout. Combine results for multi-source analysis.
47
48	### 3. Analyze Results
49
50	After collecting search results, apply the analysis framework yourself (no external AI API needed). For each result, evaluate:
51
52	1. Authenticity (`isReal`): Is this genuine news or clickbait/rumor?
53	2. Relevance (0-100): How related is this to the user's interest area?
54	3. Importance (low/medium/high/urgent): How significant is this development?
55	4. Summary: One-sentence Chinese summary of the core information
56
57	See [references/analysis-guide.md](references/analysis-guide.md) for detailed evaluation criteria.
58
59	### 4. Present Results
60
61	Format output as structured report, sorted by importance. Use this template:
62
63	```markdown
64	## 🔥 热点监控报告 — {keyword}
65	> 扫描时间: {timestamp} \| 数据源: {sources_used}
66
67	### 🚨 紧急 (Urgent)
68	- {title} — {summary}
69	来源: {source} \| 相关性: {relevance}% \| [原文链接]({url})
70
71	### 🔴 重要 (High)
72	...
73
74	### 🟡 一般 (Medium)
75	...
76
77	### 🟢 低优先级 (Low)
78	...
79
80	---
81	共发现 {total} 条热点，其中紧急 {urgent} 条，重要 {high} 条
82	```
83
84	## Script Reference
85
86	\| Script \| Sources \| API Key \| Output \|
87	\|--------\|---------\|---------\|--------\|
88	\| `search_web.py` \| Bing, Google, DuckDuckGo, HackerNews \| None \| JSON array of `{title, content, url, source, publishedAt?}` \|
89	\| `search_china.py` \| Sogou, Bilibili, Weibo \| None \| JSON array (same schema + engagement metrics) \|
90	\| `search_twitter.py` \| Twitter/X \| `TWITTER_API_KEY` \| JSON array (same schema + author info) \|
91	\| `generate_report.py` \| — \| None \| Reads JSON from stdin, outputs Markdown report \|
92
93	### Common Options
94
95	All search scripts support:
96	- `--sources`: Comma-separated list of sources to use (default: all)
97	- `--limit`: Max results per source (default: 20)
98	- `--json`: Output raw JSON (default, always JSON to stdout)
99
100	### Error Handling
101
102	Scripts output `[]` (empty JSON array) on failure and print errors to stderr. Always check for empty results and inform the user which sources failed.
103
104	## Advanced Patterns
105
106	### Keyword Expansion
107
108	For better coverage, expand the user's keyword into variants before searching:
109	- English/Chinese translations (e.g., "人工智能" ↔ "AI" ↔ "Artificial Intelligence")
110	- Abbreviations (e.g., "GPT-5" → also search "GPT5", "OpenAI GPT")
111	- Related terms (e.g., "Claude" → also search "Anthropic", "Claude 4")
112
113	### Bilibili Account Detection
114
115	`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:
116
117	```bash
118	python scripts/search_china.py "程序员鱼皮" --detect-account
119	```
120
121	### Multi-keyword Batch
122
123	For monitoring multiple keywords, run searches sequentially with a 3-second delay between keywords to respect rate limits.
124
125	## Reference Files
126
127	- [references/search-sources.md](references/search-sources.md) — Detailed info about each data source, rate limits, and quirks
128	- [references/analysis-guide.md](references/analysis-guide.md) — Hotspot analysis framework: authenticity, relevance, importance criteria

People who liked this also viewed

6 picks

Type