AI News Radar is an automated service that collects AI and technology updates, evaluates source quality, combines reports about the same event, and presents selected news in a web interface. It is for people who want a daily view of AI news and for developers who want to run a customized radar with their own sources. The catalogue add-ons help coding agents assess sources, maintain collection logic, and deploy the radar.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add LearnPrompt/ai-news-radar --skill radargit clone --depth 1 https://github.com/LearnPrompt/ai-news-radarWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/learnprompt/ai-news-radar/radar)<a href="https://agentmods.dev/skills/learnprompt/ai-news-radar/radar"><img src="https://agentmods.dev/badge/skills/learnprompt/ai-news-radar/radar/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/learnprompt/ai-news-radar/radar"><img src="https://agentmods.dev/badge/skills/learnprompt/ai-news-radar/radar.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00291 | $0.04083 |
| Opus 5 | $0.00146 | $0.02041 |
| Sonnet 5 | $0.00058 | $0.00817 |
| Haiku 4.5 | $0.00029 | $0.00408 |
Grade A, and why
ai-radar scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
数据是静态 JSON：**没有 API Key，没有 UA 黑名单，没有限流，curl 就行**。如果上游页面消失了，任何人 fork 仓库就能在自己的 GitHub Pages 上长出一份一模一样的数据——这是本 Skill 和依赖中心化 API 的资讯 Skill 的根本区别。 How it starts
The opening of the file, as written. The whole thing — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.
雷达Skill | AI Radar
你在帮用户从 AI News Radar 的公开数据里取出最近 24 小时的 AI 信号，整理成中文简报。
第一件事：确定数据源地址。所有请求都基于这一行——
BASE_URL=https://news.learnprompt.pro/data
fork / 自部署用户只需要改这一行，换成 https://<用户名>.github.io/ai-news-radar/data。GitHub Pages 是数据的 canonical 源，不要换成其他镜像域名。第一次发现用户有自己的部署时问一次，之后记住。
数据是静态 JSON：没有 API Key，没有 UA 黑名单，没有限流，curl 就行。如果上游页面消失了，任何人 fork 仓库就能在自己的 GitHub Pages 上长出一份一模一样的数据——这是本 Skill 和依赖中心化 API 的资讯 Skill 的根本区别。
通用启发：用户问的是"现在的 AI 行业事实"，不要凭训练数据脑补，永远先拉数据。即使你"觉得"知道答案，也要查——雷达数据比你的训练截止日新得多。
数据文件一览
| 文件 | 大小 | 内容 | 什么时候用 |
|---|---|---|---|
daily-brief.json |
~60KB | 精选20条日报成品，含 persona 点评字段 | 默认主入口，先查新鲜度 |
latest-24h.json |
~2MB | 24小时AI强相关全部条目（AI标签、分数、双语标题、信源分层） | 追问细节、要更多条目、按类别/关键词过滤 |
top3-personas.json |
~4KB | 每日TOP3的三种口味点评并排 | 用户要"毒舌一点/换个口味/三种口味对比" |
stories-merged.json |
~1.4MB | 多源合并后的故事线（importance分层） | 用户问"今天的大事/故事线"，先查新鲜度 |
source-status.json |
~8KB | 每个信源的健康状态、抓取量、耗时 | 用户问"信源健康/哪些源有料" |
latest-24h-all.json |
~12MB | 含非AI的全量条目 | 仅用户明确说"全部/包括非AI"才拉，先提醒体积 |
archive.json |
~56MB | 全部历史存档 | 默认禁止。确需历史数据时先告知体积并征得同意 |
第一步永远是新鲜度检查
任何回答之前，先看 generated_at：
curl -fsSL "$BASE_URL/daily-brief.json" -o /tmp/radar-brief.json
python3 -c "import json;d=json.load(open('/tmp/radar-brief.json'));print(d['generated_at'],d['total_items'])"
daily-brief.json超过 48 小时未更新：不要用它回答"今天"类问题，降级到latest-24h.json，并说明降级原因。latest-24h.json超过 36 小时未更新：照常回答，但开头如实告知"数据停在 X 月 X 日，上游 Actions 可能挂了"，并建议用户（如果是维护者）用伯乐Skill排查。- 绝不把过期数据当新鲜数据报给用户。诚实标注数据时间永远是简报的一部分。
路由表
| 用户在说 | 走哪 |
|---|---|
| 默认宽问题："今天AI圈有什么"、"AI日报"、"过去24小时AI新闻"、"最近AI有啥" | daily-brief.json（新鲜度通过时）——精选20条，自带排序和 persona 点评 |
| 追问细节、"再多来点"、"还有别的吗" | 升级到 latest-24h.json，取头部更多条目 |
| "模型发布"、"AI产品"、"Agent工具"、"论文"、"机器人" | latest-24h.json 按 ai_label 过滤（映射见下） |
| "OpenAI最近发了什么"、"Sora相关" | latest-24h.json 按关键词在 title/title_en/ai_signals 里匹配 |
| "毒舌一点"、"锐评"、"换个口味"、"三种口味对比" | top3-personas.json——TOP3 三种口味并排 |
| "今天的大事"、"故事线"、"有什么值得关注的事件" | stories-merged.json（新鲜度通过时）按 importance_score 取头部 |
| "哪些信源健康/有料"、"源状态" | source-status.json |
| "全部动态/包括非AI的" | latest-24h-all.json（先提醒 ~12MB） |
| "上周/上个月的AI新闻" | 如实说明：公开数据滚动窗口为24小时，历史需 archive.json（56MB），先征得同意再拉 |
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday Changed 944618857d57
- 11d ago First seen · 270 lines · 291 tokens per session scan A 7b9502c0c7cc
ai-radar is a skill published in the GitHub repository LearnPrompt/ai-news-radar (1,711 stars, last pushed today), licensed MIT. It adds 291 tokens to every session and 4,083 once invoked, about $0.0015 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…