karpathy-rss-daily-briefing

Original🇨🇳 Chinese
Translated

Fetches Andrej Karpathy's curated RSS feed, reads ALL original articles, and generates a themed daily briefing document with citation links. This skill should be used when the user asks to generate a Karpathy RSS daily report, fetch Karpathy's curated RSS updates, or create an AI/tech daily briefing based on Karpathy's sources. Trigger phrases include "Karpathy Daily Report", "Karpathy RSS", "Generate Daily Report", "RSS Briefing", "Karpathy Daily".

8installs

NPX Install

npx skill4agent add psylch/karpathy-rss-daily-briefing-skill karpathy-rss-daily-briefing

SKILL.md Content (Chinese)

View Translation Comparison →

Karpathy Curated RSS Daily Report Generation

Based on Andrej Karpathy's curated RSS sources, automatically fetch all entries, read the original articles, merge and sort them by topic, and generate a structured daily report in Chinese.

Language

Match user's language: Respond in the same language the user uses.

Data Source

RSS Pack URL:
https://youmind.com/rss/pack/andrej-karpathy-curated-rss

How It Works

Execute in the following order, check the corresponding item after completing each step, then proceed to the next step.
Progress:
  • Step 1: Fetch RSS Content
  • Step 2: Create Material Group
  • Step 3: Full-scale In-depth Reading
  • Step 4: Topic Merging, Sorting and Daily Report Generation

Step 1: Fetch RSS Content

Use the WebFetch tool to fetch the RSS feed:
URL: https://youmind.com/rss/pack/andrej-karpathy-curated-rss
Parse the returned RSS XML/JSON and extract all entries from the past 24 hours. Record the following for each entry:
  • Title (title)
  • Link (link)
  • Publication Date (pubDate)
  • Source Name (source/feed name)
  • Summary (description/summary)

Step 2: Create Material Group

Create a material group file with the naming format:
YYYY-MM-DD - Karpathy Curated RSS Daily Report Materials
Group all RSS entries obtained in Step 1 by source into this material group without any filtering.

Step 3: Full-scale In-depth Reading

For each RSS entry, use the WebFetch tool to access the original article link and obtain the full text or core paragraphs. Read all entries without filtering. Record:
  • Core viewpoints of the article
  • Key data/findings
  • Citation links
If the original link returns 404 or is inaccessible, use the RSS summary as a substitute and mark it accordingly.
Multiple WebFetch requests can be initiated in parallel to improve efficiency.

Step 4: Topic Merging, Sorting and Daily Report Generation

Aggregate all entries by topic:
  1. Merge: Combine multiple articles on the same or highly related topics into the same section
  2. Sort: Arrange by relevance and importance, with core AI/technology topics first, followed by less relevant topics (book reviews, historical retrospectives, non-technical content, etc.)
  3. Generate: Output the daily report document with the naming format:
YYYY-MM-DD - Karpathy Curated RSS Daily Report

Daily Report Template

Strictly follow the following template structure to generate the daily report content:
markdown
> Summary of curated sources by Andrej Karpathy | Total [N] updates

---

## 🔥 Core Topic: [Topic Title]

[Combined description based on reading the original articles, including key viewpoints, data and findings]

- Source: [Article Title 1](Original Link 1)
- Source: [Article Title 2](Original Link 2)

## {emoji} [Topic 2]: [Subtitle]

[Combined Description]

- Source: [Article Title](Original Link)

... (More topics, sorted in descending order of relevance)

---

## 📊 Today's Data

- **XX** RSS updates
- **XX** in-depth readings
- **XX** topics: AA, BB, CC

## 💡 Editor's Observation

[Brief comment on today's overall trends, 2-3 sentences]

---

*This daily report is automatically generated by AI | Data Source:* [Andrej Karpathy Curated RSS](https://youmind.com/rss/pack/andrej-karpathy-curated-rss)

Template Rules

  • Full Coverage: Every RSS update must be included in the daily report without omission
  • Merge multiple articles on the same topic into the same section and list their citation links separately
  • Sort by Relevance: Core AI/ML/technology topics first, followed by general technology topics, and non-technical content (book reviews, history, culture, etc.) last
  • Start each topic with an appropriate emoji (🔥 for the most core topic, others optional)
  • The numbers in "Today's Data" must match the actual content
  • All citations must include the original link
  • The daily report should be in Chinese, with proper nouns retained in English

Completion Report

After generating the daily report, output the following structured report:
[Karpathy RSS Daily Report] Completed!
Date: YYYY-MM-DD
RSS Entries: XX
In-depth Readings: XX
Merged Topics: XX
Output Document: YYYY-MM-DD - Karpathy Curated RSS Daily Report