agentleFS
AtmoskunAtmoskun/claude-skills/skills/wechat-hao/SKILL.md

wechat-hao

Skill0 starsChanged 9 months agoMITView on GitHub

Export WeChat articles to Notion and Obsidian with AI-powered analysis. ~/wechat-exporter Format: YYYY-MM-DD_公众号_标题.md Example: 2026-02-05_Rome_Capital_关于估值的思考.md The Obsidian note includes: 1. Original article content (Markdown) 2. AI Analysis section with: - Content type - Key topics - ChatGPT deep analysis prompt 在 ticker 检测之后,自动标注内容属于分析框架的哪些维度: 将结果添加到 frontmatter extra dict: 如果 framework_tagger 不可用或返回空列表,跳过(不报错)。 自动执行: 完成所有处理后,立即对输出文件夹执行 link 扫描(等同于 /link 收件箱/),为新增笔记添加 [[wikilinks]]。 用户说"跳过 link"时跳过此步。

  • Installs packages

The file

Files
SKILL.md

微信公众号文章导出 (WeChat Article Exporter)

Export WeChat articles to Notion and Obsidian with AI-powered analysis.

Project Location

~/wechat-exporter

When to Use This Skill

  • User sends a WeChat article URL (mp.weixin.qq.com)
  • User wants to export/save a WeChat article
  • User mentions "微信文章", "公众号", or "wechat article"

Features

  1. Article Export: Fetch, parse, and convert WeChat articles to Markdown
  2. Multi-destination Sync: Notion + Obsidian + Local canonical storage
  3. Deduplication: Three-layer dedup (URL hash, content hash, weak key)
  4. AI Analysis: Auto-detect content type and generate tailored ChatGPT prompts
  5. Telegram Integration: Works via Telegram bot with inline analysis

Content Types Detected

  • investment_thesis - Investment research and analysis
  • market_commentary - Market views and macro analysis
  • company_analysis - Company/earnings analysis
  • opinion_essay - Thought pieces and reflections
  • news_update - News and announcements
  • tutorial - Guides and how-tos
  • interview - Interviews and dialogues

Commands

Basic Export (CLI)

cd "~/wechat-exporter"
python process_article.py "https://mp.weixin.qq.com/s/xxx"

Export with Analysis

# Generate ChatGPT prompt
python process_article.py "URL" --analyze

# Run Claude analysis directly
python process_article.py "URL" --claude

# Save analysis to Obsidian note
python process_article.py "URL" --save-analysis

Telegram Bot

Just send a WeChat article URL to the Telegram bot. Analysis is automatic:

  • Exports article to Notion/Obsidian
  • Detects content type
  • Generates ChatGPT prompt (sent as reply)
  • Saves analysis to Obsidian note

Output Locations

DestinationPath
Canonicalwechat-exporter/data/canonical/
ObsidianDocuments/Obsidian Vault/收件箱/
NotionWeekly Inbox database

File Naming

Format: YYYY-MM-DD_公众号_标题.md

Example: 2026-02-05_Rome_Capital_关于估值的思考.md

Analysis Output

The Obsidian note includes:

  1. Original article content (Markdown)
  2. AI Analysis section with:
    • Content type
    • Key topics
    • ChatGPT deep analysis prompt

Dependencies

pip install -r requirements.txt
playwright install chromium

Framework Tagging (after ticker detection)

在 ticker 检测之后,自动标注内容属于分析框架的哪些维度:

from shared.framework_tagger import tag_content
sections = tag_content(text, mode="hybrid")  # e.g. ["S1", "S4.2"]

将结果添加到 frontmatter extra dict:

framework_sections: [S1, S4.2, S7]

如果 framework_tagger 不可用或返回空列表,跳过(不报错)。

Post-Export

自动执行: 完成所有处理后,立即对输出文件夹执行 link 扫描(等同于 /link 收件箱/),为新增笔记添加 [[wikilinks]]。 用户说"跳过 link"时跳过此步。

Related

  • /telegram - Photo bot that also handles WeChat URLs
  • /notebooklm - Query articles in NotebookLM
  • /link - Auto-link new notes after export

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.