feat: add gutenberg skill — search, download, extract public-domain books #64

Merged

magnus merged 1 commit from feat/gutenberg-skill into main

2026-06-13 14:26:39 -04:00

jasper commented

2026-06-13 14:24:29 -04:00

Contributor

Summary

New skill: gutenberg — Search, download, and extract public-domain books from Project Gutenberg.

What it does

Ships a portable Python CLI () with zero external dependencies (stdlib only):

Command	Description
	Keyword search via gutendex API (returns ID, title, author, downloads)
	Full book metadata by Gutenberg ID (all formats, subjects, shelves)
	Plain text, EPUB with images, or HTML. Auto-detects format URLs
	Strip PG license boilerplate from txt, or extract clean text from EPUB
	Fiction vs non-fiction via subject/shelf keyword matching
	End-to-end: search → metadata → download → extract → classify

Key features

EPUB extraction fallback for illustrated/mathematical books (plain text truncation detection)
Zero deps — uses only Python stdlib (, , )
Fiction/non-fiction classification with ambiguity detection
**, , ** flags on all commands
Progressive disclosure: brief SKILL.md with reference file for EPUB details

Files

File	Purpose
	Agent instructions — commands, usage, gotchas
	Portable Python CLI (684 lines, stdlib only)
	EPUB extraction details for illustrated books

Compatibility

Python 3.8+ with no external dependencies
No API key required (gutendex is fully public)
Portable across all AgentSkills-compatible harnesses

## Summary New skill: **gutenberg** — Search, download, and extract public-domain books from Project Gutenberg. ## What it does Ships a portable Python CLI () with **zero external dependencies** (stdlib only): | Command | Description | |---------|-------------| | | Keyword search via gutendex API (returns ID, title, author, downloads) | | | Full book metadata by Gutenberg ID (all formats, subjects, shelves) | | | Plain text, EPUB with images, or HTML. Auto-detects format URLs | | | Strip PG license boilerplate from txt, or extract clean text from EPUB | | | Fiction vs non-fiction via subject/shelf keyword matching | | | End-to-end: search → metadata → download → extract → classify | ## Key features - **EPUB extraction** fallback for illustrated/mathematical books (plain text truncation detection) - **Zero deps** — uses only Python stdlib (, , ) - **Fiction/non-fiction classification** with ambiguity detection - **, , ** flags on all commands - **Progressive disclosure**: brief SKILL.md with reference file for EPUB details ## Files | File | Purpose | |------|---------| | | Agent instructions — commands, usage, gotchas | | | Portable Python CLI (684 lines, stdlib only) | | | EPUB extraction details for illustrated books | ## Compatibility - Python 3.8+ with no external dependencies - No API key required (gutendex is fully public) - Portable across all AgentSkills-compatible harnesses

jasper added 1 commit

2026-06-13 14:24:29 -04:00

feat: add gutenberg skill — search, download, and extract public-domain books from Project Gutenberg b2cb7d9672

Ships a portable Python CLI (stdlib only, zero external dependencies) with:
- search: keyword search via gutendex API
- metadata: full book metadata by Gutenberg ID
- download: plain text, EPUB, or HTML format
- extract: strip PG boilerplate or extract text from EPUB
- classify: fiction vs non-fiction classification
- pipeline: full search → download → extract → classify workflow

AgentSkills.io compliant with SKILL.md, scripts/gutenberg, and
references/epub-extraction.md for progressive disclosure.

magnus merged commit 4176886e99 into main

2026-06-13 14:26:39 -04:00

magnus referenced this pull request from a commit

2026-06-13 14:26:40 -04:00

Merge pull request 'feat: add gutenberg skill — search, download, extract public-domain books' (#64) from feat/gutenberg-skill into main