Search, download, and clean public-domain ebooks from Project Gutenberg via the Gutendex API.
npx skills add https://github.com/magnus919/agent-skills --skill gutenberg
Please help me install this Agent Skill. Skill: gutenberg Source: https://github.com/magnus919/agent-skills/tree/main/gutenberg Command: npx skills add https://github.com/magnus919/agent-skills --skill gutenberg
This skill eliminates the friction of finding, downloading, and cleaning classic literature by providing a unified, automated pipeline for accessing the entire Project Gutenberg library.
Use the gutenberg skill to search for Moby Dick and download the clean text version to your local directory.
High-intent search queries and answers about installing and using this skill.
Automatically strip licensing boilerplate and extract clean text from complex EPUB files during download. The pipeline handles format conversion and boilerplate removal to produce ready-to-use plain text for analysis.
Run the skill with Python 3.8+ using only standard library modules for network requests and file parsing. It requires no external dependencies, making it straightforward to execute in a standard Python environment.
Build a text-mining corpus by searching the Gutenberg catalog by title or author, downloading books in plain text, and removing boilerplate automatically. This creates a clean dataset of public-domain literature for analysis.
No external Python libraries are required. The text extraction pipeline relies exclusively on Python 3.8+ standard library modules to perform network requests and parse files without additional dependencies.
RheasilviaProvides OpenStreetMap-based geocoding, POI discovery, and routing services via OSRM APIs.
cas-bigdatalabExtract text from DOCX files to plain text using Python's zipfile and xml libraries.
jameswong2011Ingest URLs and local files into structured research notes with deduplication.
taracodlabsSearch arXiv's REST API and download paper PDFs.
