agentleFS
Red-empty-potatoRed-empty-potato/ai-agent-skills/skills/ai-news-digest/SKILL.md

ai-news-digest

Skill0 starsChanged 3 months agoMITView on GitHub

Compile a categorized bilingual digest of the latest AI news (past ~7 days) with source links. 检索近一周 AI 新闻并输出分类、带来源链接的中英双语摘要。

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Keep each item to 1–2 sentences.

    line 33
  2. Distinctive:

    Always cite the source URL for every item — a digest without links is not a digest.

    line 55
  3. Distinctive:

    If a category has nothing significant this week, write 「本周暂无重大更新 / no major updates」.

    line 56
  4. Distinctive:

    Never invent news; if you cannot find real stories, say so honestly.

    line 57
  5. Distinctive:

    Keep it scannable: bullets, bold names, no long paragraphs.

    line 58

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

AI News Digest | AI 新闻速递

Gather the freshest AI news from the past ~7 days and turn it into a clean, categorized, bilingual (中文 / English) digest that readers can skim and click through.

检索过去约一周的 AI 新闻,整理成分类清晰、中英双语、可直接点击跳转的速递。

When to use | 适用场景

  • The user asks: 「整理本周 AI 新闻」「这周 AI 圈发生了什么」「what's new in AI this week」
  • The user wants a curated, verifiable roundup rather than a single answer

Workflow | 工作流程

  1. Determine the date window — use today's date as the anchor; focus on the last ~7 days.
  2. Search each category (in parallel when possible) using web search:
    • 🤖 大模型发布 LLM / model releases
    • 🧩 AI Agent 与工具链 AI agents & tooling
    • 🎨 多模态 Multimodal (vision / audio / video)
    • 📱 AI 应用与产品 AI apps & products
    • 🏛️ 政策与伦理 Policy, safety & regulation
    • 🇨🇳 国内动态 China AI scene (e.g. Chinese model releases, open-source news)
  3. Verify before including — prefer primary sources (official blog, repo, arXiv). Use WebFetch to confirm a headline if the search snippet is thin. Exclude rumors and unconfirmed announcements; say "传闻/rumored" explicitly when a story is not official.
  4. Compile the digest in this structure:
    • One-line summary per item: 标题 / Title + 一句话要点 / one-line takeaway + source link
    • Keep each item to 1–2 sentences; include the date of the news where available.
  5. Output bilingual — English line and Chinese line side by side, source link after each item.

Output format | 输出格式

# AI News Digest | AI 新闻速递
*Coverage: 2026-08-22 ~ 2026-08-29 | by ai-news-digest*

## 🤖 大模型与开源模型 LLM & open models
- **<Model/Event name>** | 一句话要点 / one-line takeaway
  - 🔗 source: https://...  (2026-08-28)

## 🧩 AI Agents & Tooling
...

## 📌 本周重点 Highlights
1. ... (top 3 stories with brief reasoning)

Tips | 提示

  • Always cite the source URL for every item — a digest without links is not a digest.
  • If a category has nothing significant this week, write 「本周暂无重大更新 / no major updates」.
  • Never invent news; if you cannot find real stories, say so honestly.
  • Keep it scannable: bullets, bold names, no long paragraphs.

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.