The answer
All three were saved with every image: 86 image references, all pointing to local files, 53 MB in total, none failed.
Save a 公众号’s articles as local Markdown with their images, so they still read offline or after deletion.
v0.1.1
View example draft · How to useExample draft
The three newest articles from the WeChat account 丁香医生 (DXY Doctor), saved as Markdown with their images.
All three were saved with every image: 86 image references, all pointing to local files, 53 MB in total, none failed.
An article on exercise and depression (3,488 characters, 18 images), one on the dirtiest spot in a gym (4,098 characters, 19 images) and one on rich face creams (6,680 characters, 49 image references).
Looking the account up by its id failed, so the Skill finds articles through search. One search page reached back about three days for an account that posts several times a day.
From a real run on 2026-11-05. The articles belong to their authors and are not shown.
An Agent that can read the complete Skill folder. Live research also needs a SandBase connection; supplied material can be used without a lookup. The converter needs Node.js 18+.
Download and unpack the complete Skill folder, keep its references, and use it with a local Agent that supports Skills.
Use wechat-account-archive to save the latest articles from the 公众号 丁香医生 as Markdown with images, and give me the index.
Search the account’s recent articles through SandBase and confirm the list.
Save each article’s full HTML response.
Run the bundled converter, then open a few articles and images to check them.
Download and unpack the whole Skill folder, including references, into your Agent’s supported Skill directory. You can also ask the Agent to read its SKILL.md and follow the instructions. Run it locally with your own material.
WeChat images can stop loading outside WeChat or after an article is removed; local copies keep the archive readable.