Extract HackerNews posts and threaded comments into a Markdown file.
npx skills add https://github.com/guoqiao/skills --skill hn-extract
Please help me install this Agent Skill. Skill: hn-extract Source: https://github.com/guoqiao/skills/tree/main/hn-extract/hn-extract Command: npx skills add https://github.com/guoqiao/skills --skill hn-extract
This Skill automates the process of extracting the main article content and all comments from a HackerNews post, consolidating them into a single, clean Markdown file for easier reading or input into LLMs.
Use the hn-extract skill to extract the HackerNews post with ID 46861313 into a Markdown file.
High-intent search queries and answers about installing and using this skill.
To extract HackerNews posts and comments into Markdown, provide a post URL or item ID to the scraper. It downloads the article text and fetches threaded comments, consolidating everything into one clean file for offline reading or LLM input.
Saving HackerNews threaded comments for LLM consumption is best handled by a scraper that preserves the hierarchical comment structure. This approach fetches all replies and main article text, outputting a structured Markdown file that language models can easily parse.
Yes, you need the uv Python package manager to run the HackerNews scraper. It handles script execution and manages dependencies like requests, trafilatura, and urllib3, ensuring the Python environment is correctly set up for extracting HTML content.
Yes, you can use a HackerNews item ID instead of a URL to extract post content. The scraper accepts either input format, fetching the main article and associated threaded comments based on the unique item identifier provided.
Yes, the HackerNews extractor includes post metadata like points and author. Alongside the cleaned article HTML and threaded comments, the generated Markdown file contains key metadata such as the post title, author, URL, and points.
A limitation when extracting HTML content from linked HackerNews articles is that the tool relies on the trafilatura library to clean HTML and extract main text. If the linked website blocks scraping or has complex JavaScript rendering, the extraction may fail or return incomplete content.
AutumnsGroveAutomates Python project setup, dependency management and virtual environments using UV commands.
i0switchExtract clean article text from URLs and save it as a plain-text file.
JongsixGenerate technical documentation from source code and API definitions.
danielschollFetch web pages and convert HTML to clean Markdown.
