# virgiliojr94/book-to-skill

Turn any technical book PDF into a Claude Code skill — ready to study, reference, and use while you work.

Repository: https://github.com/virgiliojr94/book-to-skill
Canonical: https://ross.abutalabs.com/products/book-to-skill
Language: Python
License: MIT
License Family: permissive
Topics: agent-skills, ai-agents, context-engineering, document-processing, edtech, knowledge-base, knowledge-management, llm, pdf-to-markdown, rag, self-study, study-tools, book-to-skill
Last push: 2026-08-26T00:08:14+00:00

## Health v2 (maintenance only)
Score: 80/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 97, longevity 8
- inputs: {"age_days": 125, "days_push": 8, "days_rel": 23, "gap_med": 8.0, "n_releases_24m": 5}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 25880, forks 2679 (observed 2026-08-28T04:11:38.682278+00:00)

## What it is
A Python CLI tool that converts technical books and document collections (PDF, EPUB, DOCX, MD, HTML, etc.) into agent skills for AI coding assistants like Claude Code, GitHub Copilot CLI, and Amp. It builds a structured, token-efficient knowledge base so agents can answer questions from the source material using far fewer tokens than dumping the full text into context.

## Use cases
- turn a technical book pdf into a claude code skill
- make an epub book queryable by my ai coding agent
- convert a folder of docs into a knowledge base for copilot cli
- answer questions from a book without dumping it into context
- build a study reference from pdfs for self-study
- create agent skills from documentation collections

## When to choose
- you want a book or doc corpus usable inside Claude Code, Copilot CLI, or Amp as an agent skill
- you need token-efficient retrieval from long technical documents
- you want to study or reference books while coding with AI assistance

## When to avoid
- you need a general-purpose RAG pipeline with your own vector database and API
- you don't use agent-skill-compatible coding assistants
- you need to process non-document media like audio or video

## Facets
- artifact type: cli-tool
- maturity: active
- function: pdf, rag, llm-inference, agent-framework, developer-tools, cli
- domain: artificial-intelligence, developer-tools, education, pdf, self-hosted
- platform: python, cli, cross-platform
- tags: agent-skills, claude-code, pdf-to-markdown, knowledge-base, context-engineering, study-tools, document-processing, ai-agents, retrieval-augmented-generation

## Member repositories
- virgiliojr94/book-to-skill (main) score 80

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:38.682278+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:55:58.064724+00:00, confidence not recorded.
  - readme: https://github.com/virgiliojr94/book-to-skill (fetched 2026-08-28T04:11:38.682278+00:00, sha dd4dde368db6)
- Data as of 2026-08-30T08:39:29.467469+00:00.