AI News Radar
Objective
Searches and summarizes the main recent Artificial Intelligence news from curated sources.
The skill:
- searches recent news
- removes duplicates
- categorizes the topics
- translates/summarizes in English
- returns:
- title
- link
- category
- short summary
Usage
Invoke with:
/ai-news-radar
- “latest AI news”
- “AI summary”
- “what happened in AI today”
- “AI briefing”
Optionally, the user can specify the number of items:
- “show me 5 AI news items”
- “top 10 AI news stories”
Preferred sources
Use these sources:
Primary sources
- Anthropic News — Company announcements
- Claude Blog — Product updates and guides
- Google AI — Gemini/DeepMind
Curation sources
- TLDR AI — Daily AI industry digest
- The Decoder — AI-focused site
- Last Week in AI — Weekly roundup
Instructions
Determine quantity
If the user specifies a quantity:
- use the requested quantity
Otherwise:
- use 10 news items by default
Maximum:
Selection criteria
Prioritize news items that are:
- Recent, maximum 72 hours old
- Relevant to generative AI, models, products, research, agents, tools, or the market
- Published or highlighted in the preferred sources
- Potentially impactful for professionals, creators, developers, or companies
Duplicate removal
If the same news item appears in more than one source:
- keep only one entry
- choose the most original or most direct source as the main link
- mention additional sources in the “Also appeared in” field
- do not repeat the news item in the list
Possible categories
Classify each news item into one of these categories:
- Launch — launch, release, announcement, GPT, Claude, Gemini, model
- Research — paper, benchmark, study, research
- Developer tool
- Product — feature, API, update, tool
- Market — funding, startup, acquisition
- AI safety — safety, alignment, red team
- Opinion — opinion, future, prediction
- Other
Output format
Return the list in English using the following format:
Latest AI News
## 1. [News title](link)
**Category:** Product launch
**Main source:** Source name
**Also appeared in:** Source 2, Source 3
**Date:** MM/DD/YYYY, if available
Short paragraph explaining what happened, why it matters, and the potential impact. Do not write more than 4 lines.
---
## 2. [News title](link)
**Category:** Research
**Main source:** Source name
**Also appeared in:** —
**Date:** MM/DD/YYYY, if available
Short paragraph explaining what happened, why it matters, and the potential impact.
Error handling
If any feed fails:
- continue normally
- ignore the unavailable feed
Never interrupt the full briefing because of a partial failure.
Important rules
Always respond in English.
Never copy the full text of an article.
Always summarize.
Always include the original link.
Do not invent information.
Do not repeat duplicate news items.
Prioritize clarity.
Prioritize original sources whenever possible.
1---2name: ai-news-radar3description: Searches and summarizes the latest AI news in English from selected sources. Removes duplicates and categorizes the topics.4---5
6# AI News Radar
7
8## Objective
9
10Searches and summarizes the main recent Artificial Intelligence news from curated sources.
11
12The skill:
13
14- searches recent news
15- removes duplicates
16- categorizes the topics
17- translates/summarizes in English
18- returns:
19 - title
20 - link
21 - category
22 - short summary
23
24## Usage
25
26Invoke with:
27
28- `/ai-news-radar`
29- “latest AI news”
30- “AI summary”
31- “what happened in AI today”
32- “AI briefing”
33
34Optionally, the user can specify the number of items:
35
36- “show me 5 AI news items”
37- “top 10 AI news stories”
38
39## Preferred sources
40
41Use these sources:
42
43### Primary sources
44
45- Anthropic News — Company announcements
46- Claude Blog — Product updates and guides
47- Google AI — Gemini/DeepMind
48
49### Curation sources
50
51- TLDR AI — Daily AI industry digest
52- The Decoder — AI-focused site
53- Last Week in AI — Weekly roundup
54
55## Instructions
56
57### Determine quantity
58
59If the user specifies a quantity:
60
61- use the requested quantity
62
63Otherwise:
64
65- use 10 news items by default
66
67Maximum:
68
69- 20 news items
70
71## Selection criteria
72
73Prioritize news items that are:
74
751. Recent, maximum 72 hours old
762. Relevant to generative AI, models, products, research, agents, tools, or the market
773. Published or highlighted in the preferred sources
784. Potentially impactful for professionals, creators, developers, or companies
79
80## Duplicate removal
81
82If the same news item appears in more than one source:
83
84- keep only one entry
85- choose the most original or most direct source as the main link
86- mention additional sources in the “Also appeared in” field
87- do not repeat the news item in the list
88
89## Possible categories
90
91Classify each news item into one of these categories:
92
93- Launch — launch, release, announcement, GPT, Claude, Gemini, model
94- Research — paper, benchmark, study, research
95- Developer tool
96- Product — feature, API, update, tool
97- Market — funding, startup, acquisition
98- AI safety — safety, alignment, red team
99- Opinion — opinion, future, prediction
100- Other
101
102## Output format
103
104Return the list in English using the following format:
105
106# Latest AI News
107```markdown
108## 1. [News title](link)
109
110**Category:** Product launch
111**Main source:** Source name
112**Also appeared in:** Source 2, Source 3
113**Date:** MM/DD/YYYY, if available
114
115Short paragraph explaining what happened, why it matters, and the potential impact. Do not write more than 4 lines.
116
117---
118
119## 2. [News title](link)
120
121**Category:** Research
122**Main source:** Source name
123**Also appeared in:** —
124**Date:** MM/DD/YYYY, if available
125
126Short paragraph explaining what happened, why it matters, and the potential impact.
127```
128# Error handling
129
130If any feed fails:
131
132- continue normally
133- ignore the unavailable feed
134
135Never interrupt the full briefing because of a partial failure.
136
137# Important rules
138
139Always respond in English.
140Never copy the full text of an article.
141Always summarize.
142Always include the original link.
143Do not invent information.
144Do not repeat duplicate news items.
145Prioritize clarity.
146Prioritize original sources whenever possible.