Download public Substack articles and convert them to Markdown with local assets.
npx skills add https://github.com/beatai-org/beatai --skill substack-fetch
Please help me install this Agent Skill. Skill: substack-fetch Source: https://github.com/beatai-org/beatai/tree/main/.claude/skills/substack-fetch Command: npx skills add https://github.com/beatai-org/beatai --skill substack-fetch
This Skill lets you quickly grab a public Substack article by URL and convert it into clean, offline-friendly Markdown with locally stored images, so you can plug it into your pipeline without manual copying.
Ask for: fetch this Substack article from the given URL and save the cleaned Markdown plus local images under RAW_DIR (absolute path) using this skill.
High-intent search queries and answers about installing and using this skill.
You can download a Substack article as Markdown by providing the public URL and an absolute RAW_DIR path. The Skill fetches the HTML via plain HTTP and outputs Readability-cleaned Markdown with images stored locally in an assets folder.
No, you cannot fetch paywalled Substack posts. The Skill uses plain HTTP fetching without login capabilities, meaning it only processes public articles that do not require a subscription to access.
Yes, this tool works with both standard *.substack.com URLs and Substack custom domains. It uses plain HTTP fetching and DOM parsing to extract content from any public Substack article.
Readability extracts the main article body from the raw HTML, and Turndown converts that DOM structure into Markdown. This combination normalizes elements like figures and captions to produce clean, offline-friendly text.
When converting a Substack post, the tool writes YAML frontmatter containing the article title, author, URL, and fetched date. It also includes optional published date, tags, and excerpt if available in the source HTML.
No, you do not need a headless browser like Chrome to scrape Substack content. The Skill relies on plain HTTP fetch requests and DOM parsing to retrieve the article, avoiding the overhead of browser automation.
beatai-orgConverts X posts and long-form articles to Markdown with local image assets.
lbliiiMigrates static site and Markdown content to Bengal format.
badlogicAutomate Chrome browser control and content extraction via the Chrome DevTools Protocol.
Quill-AgentAutomate web scraping with anti-bot bypass and JavaScript-rendered content.
