substack-fetch
OfficialDownload Substack posts into clean Markdown.
Content & Communication#markdown#readability#web scraping#substack#image localization#article ingestion
Authorbeatai-org
Version1.0.0
Installs0
System Documentation
What problem does it solve?
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.
Core Features & Use Cases
- Public Substack fetching: Downloads Substack article HTML via plain HTTP (no Chrome, no login) and extracts the main article body.
- Readability + Turndown cleaning: Produces Readability-cleaned Markdown and normalizes structures like figures and captions.
- Local image localization: Downloads remote images into RAW_DIR/<slug>/assets and rewrites image links to relative paths.
- Metadata in YAML frontmatter: Writes title, author, url, fetched date, optional published date, optional tags, and optional excerpt into the Markdown header.
Quick Start
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.
Dependency Matrix
Required Modules
@mozilla/readabilityjsdomturndownyaml
Components
scripts
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: substack-fetch Download link: https://github.com/beatai-org/beatai/archive/main.zip#substack-fetch Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.