Daily Tech News - In-depth Daily Technical News Gathering

Automatically search and summarize the day's technical news, using a multi-source cross-verification + in-depth research + importance scoring mechanism to generate high-quality Markdown blog articles.

⚠️ Required Parameters

When calling this skill, you must specify the target date in the prompt:

TARGET_DATE: Date in YYYY-MM-DD format
Example: 2026-02-02

Correct Calling Methods:

✅ "Execute /daily-tech-news to collect tech news for 2026-02-02"
✅ "Run the daily-tech-news skill, date: 2026-02-02"
❌ "Execute /daily-tech-news" (missing date parameter)

All dates used during execution (file name, frontmatter, title, search keywords) must use this TARGET_DATE.

Core Principles

Accuracy First → Multi-source cross-verification + in-depth reading of original texts Quality Over Quantity → Importance scoring screening + deduplication and noise reduction Depth Over Breadth → In-depth analysis and technical interpretation of Top 3 news items

Phase 1: Preparation Stage

Step 1.1: Determine Search Date

Important: The date must be obtained from the calling parameters, not calculated independently.

When GitHub Actions or users call this skill, the target date will be specified in the prompt. You must:

Extract the date from the prompt: Find the explicitly specified date in the prompt (format: YYYY-MM-DD)
Use this date as
TARGET_DATE
: All subsequent operations are based on this date
Prohibit self-calculation of dates: Do not use relative dates such as "yesterday" or "today"

TARGET_DATE = Date extracted from prompt parameters
Format: YYYY-MM-DD
Example: 2026-02-02

Date Usage Rules:

File name:
```
daily-tech-news-{TARGET_DATE}.mdx
```
frontmatter date:
```
{TARGET_DATE}
```
Title date: Convert TARGET_DATE to Chinese format (e.g., February 02, 2026)
Search keywords: Use TARGET_DATE

Step 1.2: Initialize Deduplication Cache

Check the news published in the last 7 days to avoid duplicate reports:

Read the latest 7 articles from content/blog/daily-tech-news-*.mdx
Extract reported: project names, company names, event keywords
Establish a deduplication list

Phase 2: Multi-source In-depth Search

Step 2.1: Tier 1 - Authoritative Official Sources (Highest Priority)

Must-access authoritative sources:

Source	URL	Description
Hacker News	https://news.ycombinator.com/	Bellwether of technical communities
GitHub Trending	https://github.com/trending	Open-source project trends
Trendshift	https://trendshift.io/	GitHub trend analysis
Product Hunt	https://www.producthunt.com/	New product launches

Use WebFetch to directly retrieve and extract the day's popular content (Top 10).

Step 2.2: Tier 2 - Professional Media Sources

Search 2-3 professional keyword combinations for each field:

AI / LLM Field

Search Strategy (by priority):
1. site:techcrunch.com AI {date}
2. site:theverge.com artificial intelligence {date}
3. "OpenAI" OR "Anthropic" OR "Google AI" announcement {date}
4. "LLM" OR "GPT" OR "Claude" release {date}
5. machine learning breakthrough research {date}

GitHub / Open-source Field

Search Strategy:
1. site:github.blog {date}
2. "open source" major release {date}
3. GitHub "stars" trending repository {date}

Frontend Development

Search Strategy:
1. site:reactjs.org OR site:vuejs.org blog {date}
2. "React" OR "Vue" OR "Next.js" OR "Svelte" release {date}
3. frontend framework update {date}
4. JavaScript TypeScript major update {date}

Backend / Infrastructure

Search Strategy:
1. site:kubernetes.io blog {date}
2. "Rust" OR "Go" programming release {date}
3. "Docker" OR "Kubernetes" announcement {date}
4. cloud infrastructure AWS Azure GCP {date}

Tech Industry Trends

Search Strategy:
1. site:crunchbase.com funding {date}
2. tech startup Series A B C funding {date}
3. developer tools company announcement {date}

Step 2.3: Tier 3 - Chinese Technical Communities

Supplement Chinese original content:

Search Strategy:
1. site:juejin.cn trending {date}
2. site:infoq.cn {date}
3. site:segmentfault.com headline {date}

Phase 3: In-depth Research and Verification

Step 3.1: Information Cross-verification

For each candidate news item:

1. Core Fact Extraction:
   - WHO: Involved companies/individuals/projects
   - WHAT: What exactly happened
   - WHEN: Exact time
   - WHERE: Location/platform of occurrence
   - WHY: Why it matters

2. Multi-source Verification (at least 2 independent sources):
   - Source A report → Retrieve original text using WebFetch
   - Source B verification → Search for the same event using WebSearch
   - Compare whether core facts are consistent

3. Confidence Marking:
   ✓ Verified (confirmed by 2+ sources)
   ? Pending verification (only single source)
   ⚠️ Controversial (conflicts between sources)

Step 3.2: In-depth Reading of Original Texts

For the Top 10 candidate news items, use WebFetch to obtain complete content:

WebFetch extracts key points:
1. Core argument of the article
2. Key data and facts
3. Expert quotes and comments
4. Technical details and implementation methods
5. Practical impact on developers

Step 3.3: Importance Scoring

Score each news item (full score 100 points):

Dimension	Weight	Scoring Criteria
Scope of Impact	25%	How many developers are affected? Global vs local
Practicality	25%	Can developers apply it immediately? What problems does it solve?
Novelty	20%	First announcement vs duplicate report? Breakthrough vs incremental?
Information Depth	15%	With technical details vs only title?
Authority	15%	Official release vs rumor? Reliability of source?

Scoring Example:

Kubernetes 1.33 natively supports Sidecar
- Scope of Impact: 24/25 (Global K8s users)
- Practicality: 23/25 (Directly changes deployment methods)
- Novelty: 18/20 (First official release)
- Information Depth: 14/15 (With technical implementation details)
- Authority: 15/15 (Official release)
= Total Score: 94/100 ⭐⭐⭐⭐⭐

Step 3.4: Deduplication and Noise Reduction

Exclude the following content:

❌ Clickbait Detection:
- Title contains "shocking", "blockbuster", "exposed" but no substantive content
- Severe mismatch between title and body keywords
- Excessive exclamation marks and question marks

❌ Low-quality Content Filtering:
- General tech news irrelevant to developers
- Vague reports with no specific information (e.g., "AI continues to develop")
- Duplicate events reported in the last 7 days
- Unverifiable news from a single source

❌ Content Deduplication:
- For multiple reports on the same event, only retain the one with the most comprehensive information
- Priority: Official sources > Professional media > General media

Phase 4: Top 3 In-depth Analysis

Step 4.1: Select the 3 Most Important News Items of the Day

Select the top 3 news items with the highest importance scores for in-depth analysis.

Step 4.2: In-depth Analysis Template

Write in-depth analysis for each Top 3 news item:

### [Title] ⭐⭐⭐⭐⭐

**Core Points:**
- Point 1: [Specific Fact]
- Point 2: [Specific Fact]
- Point 3: [Specific Fact]

**Technical Interpretation:**
[What does this mean? What impact does it have on developers? How is it technically implemented?]

**Background Context:**
[What is the historical background of this event? Why is it happening now?]

**Action Recommendations for Developers:**
- Recommendation 1: [Specific actionable step]
- Recommendation 2: [Specific actionable step]

**Related Links:**
- Official Announcement: [Link]
- Technical Documentation: [Link]
- Community Discussion: [Link]

Phase 5: Generate Blog Article

Step 5.1: File Structure

Create an MDX file in the

content/blog/

directory.

Important: Must use the
TARGET_DATE
extracted from the prompt in Phase 1

File Name:

daily-tech-news-{TARGET_DATE}.mdx

Step 5.2: Content Template

Date Format Conversion:

```
TARGET_DATE
```
format:
```
2026-02-02
```
Chinese date format:
```
February 02, 2026
```
frontmatter date format:
```
2026-02-02
```
(same as TARGET_DATE)

mdx

---
title: Daily Tech News - {TARGET_DATE converted to Chinese format}
description: {Summary of the day's news highlights, 50-100 words, highlighting Top 3. Add "Today, a total of N important technical news items verified by multiple sources are included." at the end.}
date: {TARGET_DATE}
---

## 🔥 Today's Focus

{In-depth analysis of Top 3 news items, using the in-depth analysis template from Phase 4}

---

## AI / Artificial Intelligence

### {Title} ⭐⭐⭐⭐

{Summary content, 3-5 sentences, including core facts}

**Why It Matters:** {One sentence explaining the impact on developers}

- Source: [{Source Name}]({URL})
- Verification: ✓ Multi-source confirmed

### {Title2}
...

## GitHub / Open-source

### GitHub Trending Projects

Today's GitHub Trending popular projects:

- **[owner/repo-name](https://github.com/owner/repo-name)** (TypeScript, 12.5k ⭐) ⭐⭐⭐⭐
  AI-powered code editor plugin supporting multiple IDEs.
  **Highlights:** {Why this project is worth attention}

- **[owner/another-repo](https://github.com/owner/another-repo)** (Python, 8.2k ⭐) ⭐⭐⭐
  Lightweight machine learning framework focused on edge device deployment.

- Source: [GitHub Trending](https://github.com/trending), [Trendshift](https://trendshift.io/)

### {Other Open-source News}
...

## Frontend Development

...

## Backend / Infrastructure

...

## Tech Trends

...

---

## 📊 Today's Data

| Metric | Value |
|------|------|
| Number of Search Sources | {N} |
| Candidate News Items | {N} |
| After Deduplication | {N} |
| Finally Included | {N} |
| Multi-source Verification Rate | {N}% |

---

> This article is automatically generated by Claude, using a multi-source cross-verification mechanism. If errors are found, feedback is welcome.

Phase 6: Quality Check and Submission

Step 6.1: Final Quality Check

□ All news items have source links
□ Top 3 news items have in-depth analysis
□ Importance scoring markers are complete
□ No duplicate content
□ No obvious factual errors
□ MDX Security Check (must confirm item by item):
  □ No bare < symbols in the body (except in code blocks), replaced with &lt;
  □ All code block language identifiers are Shiki-supported languages (use text if unsure)
  □ No bare {} curly braces in the body (except in code blocks)
□ Chinese expression is smooth

Step 6.2: Submit Changes

bash

git add content/blog/daily-tech-news-{date}.mdx
git commit -m "docs: add daily tech news for {date}"

Output Requirements

Requirement	Description
Language	All in Chinese
Format	MDX file, compatible with Next.js blog
Length of Regular News	50-150 word summary
In-depth Analysis for Top 3	200-400 words per item
Source Labeling	Must label original link + verification status
Number of Categories	At least 3 categories
Total Number of News Items	10-20 items (quality first)
Importance Scoring	Label 1-5 stars for each news item

Information Source Priority

First Priority (Authoritative Official)

GitHub official blog, Trending
Official blogs of various frameworks/languages (React, Vue, Rust, Go, etc.)
Official announcements from companies (Google, Microsoft, AWS, etc.)

Second Priority (Professional Media)

Hacker News (community bellwether)
TechCrunch, The Verge (in-depth tech reports)
InfoQ, Juejin (Chinese technical communities)

Third Priority (General Media)

General tech news websites
Social media hotspots
Personal blogs

Clickbait Identification Rules

Automatic demotion or exclusion:

❌ Excessive emotional words: shocking, blockbuster, exposed, earth-shattering, subversive
❌ Over-exaggeration: strongest in history, completely change, completely crush
❌ Vague expressions: a certain company, allegedly, may, might
❌ No substantive content: AI continues to develop, technology is advancing
❌ Title-content mismatch: title says major breakthrough, content is just a small update

⚠️ MDX Security Rules (Must Be Strictly Followed)

MDX is not ordinary Markdown; it parses content as JSX. The following rules must be followed when generating content, otherwise Vercel build failures will occur:

Rule 1: Escape Bare

Symbols

MDX parses

as the start of a JSX tag.

in non-HTML/JSX contexts must be replaced with

&lt;

Common Trigger Scenarios and Fixes:

❌ Users affected by versions <1.123.17    → Error: Unexpected character `1`
✅ Users affected by versions &lt;1.123.17

❌ When x < 10               → Error: Unexpected character `1`
✅ When x &lt; 10

❌ Array<string>              → Error: Parsed as JSX
✅ `Array<string>`            → Wrap with inline code
✅ Array&lt;string&gt;         → Or use HTML entity

Note:

inside code blocks (```) does not need to be escaped; code blocks are safe.

Rule 2: Code Block Language Identifiers Must Be Shiki-supported Languages

The language identifier of a code block (```language) must use a language name known to Shiki, otherwise a

ShikiError: Language "xxx" is not included in this bundle

error will occur during build.

Safe Language Identifiers (Common):

text, plaintext, txt, bash, shell, sh, javascript, js, typescript, ts,
python, py, json, yaml, yml, html, css, sql, go, rust, java, c, cpp,
markdown, md, diff, toml, xml, graphql, docker, dockerfile, ini, csv

Non-existent/Unsafe Language Identifiers:

❌ ```td        → Shiki does not support this language, use ```text instead
❌ ```nushell   → Shiki does not support this language, use ```shell or ```text instead
❌ ```hcl       → Use ```text instead

Principle: If you are unsure whether a language is supported by Shiki, use
text
in all cases.

Rule 3: Curly Braces

{}

Will Be Parsed as JSX Expressions

and

in MDX body will be treated as JSX expressions for evaluation.

❌ Format: {Name}    → Error: Name is not defined
✅ Format: \{Name\}  → Escape
✅ Format: `{Name}`  → Wrap with inline code