daily-news-60s
Skill46 starsChanged 9 months agoMITView on GitHub
获取每天60秒读懂世界的每日新闻,包含15条精选国内外新闻和每日微语。Use when users need daily news summaries, current events, or want to stay informed about world news in Chinese.
In this repository6 other files it gives its agents.
- data-querySkill
- entertainmentSkill
- hot-topicsSkill
- media-infoSkill
- utility-toolsSkill
- weather-querySkill
The file
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 7 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 22
Use this skill when users:
- Distinctive: line 23
Ask for today's news or current events
- Distinctive: line 38
If not provided, returns the latest available news
- Distinctive: line 143
Error Handling: Always check response status and handle errors gracefully
- Distinctive: line 144
Format Selection: Use JSON for structured data, markdown for formatted output, text for simple presentation
- Distinctive: line 145
Date Validation: When requesting specific dates, ensure the date format is YYYY-MM-DD
- Very specific: line 186
Solution: Use encoding=image-proxy instead of encoding=image
- Distinctive: line 191
Check the response status code
≈ “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.
Files
每天60秒读懂世界 - Daily News Skill
This skill helps AI agents fetch and present daily curated news from the 60s API, which provides 15 selected news items plus a daily quote, updated every 30 minutes.
When to Use This Skill
Use this skill when users:
- Ask for today's news or current events
- Want a quick daily briefing
- Request news summaries in Chinese
- Need historical news from a specific date
- Want news in different formats (text, markdown, image)
API Endpoint
Base URL: https://60s.viki.moe/v2/60s
Method: GET
Parameters
date(optional): Date in YYYY-MM-DD format (e.g., "2024-01-15")- If not provided, returns the latest available news
encoding(optional): Output formatjson(default): Structured JSON datatext: Plain text formatmarkdown: Formatted markdownimage: Redirect to image URLimage-proxy: Returns image binary data
How to Use
Basic Usage - Get Latest News
curl "https://60s.viki.moe/v2/60s"import requests
response = requests.get('https://60s.viki.moe/v2/60s')
news = response.json()
print(f"📰 {news['date']} 新闻简报")
print(f"农历:{news['lunar_date']} {news['day_of_week']}\n")
for i, item in enumerate(news['news'], 1):
print(f"{i}. {item['title']}")
print(f"\n💭 微语:{news['tip']}")Get News for Specific Date
response = requests.get('https://60s.viki.moe/v2/60s', params={'date': '2024-01-15'})Get News as Markdown
response = requests.get('https://60s.viki.moe/v2/60s', params={'encoding': 'markdown'})
markdown_content = response.textGet News as Plain Text
response = requests.get('https://60s.viki.moe/v2/60s', params={'encoding': 'text'})
text_content = response.textResponse Format (JSON)
{
"date": "2024-01-15",
"day_of_week": "星期一",
"lunar_date": "腊月初五",
"news": [
{
"title": "新闻标题1",
"link": "https://example.com/news1"
},
...
],
"tip": "每日微语内容",
"image": "https://..../image.png",
"updated": "2024-01-15 09:00:00",
"updated_at": 1705280400000,
"api_updated": "2024-01-15 09:00:00",
"api_updated_at": 1705280400000
}Example Interactions
User Request: "今天有什么新闻?"
Agent Response:
📰 2024年1月15日 星期一 农历腊月初五
【今日要闻】
1. 新闻标题1
2. 新闻标题2
3. 新闻标题3
...
💭 微语:[每日微语内容]User Request: "Get yesterday's news"
from datetime import datetime, timedelta
yesterday = (datetime.now() - timedelta(days=1)).strftime('%Y-%m-%d')
response = requests.get('https://60s.viki.moe/v2/60s', params={'date': yesterday})Best Practices
- Caching: The API has built-in caching, responses are very fast
- Update Frequency: News updates every 30 minutes, typically by 10 AM
- Error Handling: Always check response status and handle errors gracefully
- Format Selection: Use JSON for structured data, markdown for formatted output, text for simple presentation
- Date Validation: When requesting specific dates, ensure the date format is YYYY-MM-DD
Common Use Cases
1. Daily News Bot
def send_morning_news():
news = requests.get('https://60s.viki.moe/v2/60s').json()
message = f"早安!今天是 {news['date']} {news['day_of_week']}\n\n"
message += "\n".join([f"{i}. {item['title']}" for i, item in enumerate(news['news'][:5], 1)])
message += f"\n\n{news['tip']}"
return message2. News Summary for Chatbots
def get_news_summary(count=5):
news = requests.get('https://60s.viki.moe/v2/60s').json()
return {
'date': news['date'],
'headlines': [item['title'] for item in news['news'][:count]],
'quote': news['tip']
}3. Historical News Lookup
def get_historical_news(date_str):
response = requests.get('https://60s.viki.moe/v2/60s', params={'date': date_str})
if response.ok:
return response.json()
return NoneTroubleshooting
Issue: No data returned
- Solution: Try requesting previous dates (yesterday or the day before)
- The service tries latest 3 days automatically
Issue: Image not loading
- Solution: Use
encoding=image-proxyinstead ofencoding=image - The proxy endpoint directly returns image binary data
Issue: Old date requested
- Solution: Data is only available for recent dates
- Check the response status code
API Characteristics
- ✅ Free: No authentication required
- ✅ Fast: Millisecond-level cached responses
- ✅ Reliable: Global CDN acceleration
- ✅ Updated: Every 30 minutes
- ✅ Quality: 15 curated news items from authoritative sources
Related Resources
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
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.

