# virgiliojr94/book-to-skill

Source: [GitHub](https://github.com/virgiliojr94/book-to-skill)  
Feed7 permalink: https://feed7.dev/p/book-to-skill-1av16sr  
Published: Unknown  
Trust: Needs Review (needs_review)

## Why Included

book-to-skill compiles books and document sets into on-demand agent skills, reducing repeated context loading while preserving chapter-level references and reusable decision rules.

## Source Summary

book-to-skill converts PDFs, ebooks, document folders, or globs into a shared SKILL.md, a core index, and on-demand chapter files. Its tests report **24–51× fewer tokens** than repeatedly placing a full book in context.

## Practical Implication

Use this pattern for references you revisit: internal docs, standards, research clusters, or technical books. The generated structure front-loads mental models and loads only the relevant chapter, while the same skill format works in Claude Code, Amp, and GitHub Copilot CLI.

## Agent-Ready Context

book-to-skill converts PDFs, ebooks, document folders, or globs into a shared SKILL.md, a core index, and on-demand chapter files. Its tests report **24–51× fewer tokens** than repeatedly placing a full book in context.

Use this pattern for references you revisit: internal docs, standards, research clusters, or technical books. The generated structure front-loads mental models and loads only the relevant chapter, while the same skill format works in Claude Code, Amp, and GitHub Copilot CLI.

The repository says conversion costs roughly **$1 per book**, and repeated use is where amortization helps. Chapter detection expects explicit numbered headings; one-off reading, broad library search, and poorly segmented sources may be better served by other approaches.

## Connected Context

Feed7 judgment across 262 accumulated Signals:

This makes the shared-context pattern concrete for stable, repeatedly consulted documents: preprocess them into a portable skill with a compact index and selectively loaded chapters. Unlike repository graphs, recursive inspection, or evidence replay, it pays an upfront conversion cost and depends on explicit document structure; its reported token savings therefore support repeated reference use, not general library search or one-off reading.

- [WTF Is the Context Layer? The Missing Infrastructure for Production Agents — Prukalpa Sankar](https://feed7.dev/p/wtf-is-the-context-layer-the-missing-infrastructure-for-production-agent-0t47xqf) — It implements the talk’s portable, shared-context idea as a skill that multiple agent harnesses can reuse.
- [RLM: Recursive Language Models for Large Codebases - Shashi, Superagentic AI](https://feed7.dev/p/rlm-recursive-language-models-for-large-codebases-shashi-superagentic-ai-1w21nex) — Both keep large source material outside the main context, but book-to-skill preprocesses structured chapters while RLMs inspect external data recursively at runtime.
- [Graphify-Labs/graphify](https://feed7.dev/p/graphify-1e0bs1f) — Both reduce repeated retrieval work, but target different source shapes: chapter-indexed documents versus provenance-tagged relationships in codebases.
- [ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning](https://feed7.dev/p/2607-02509v1-11vodps) — Both surface only relevant evidence, but ReContext performs query-time replay from long inputs whereas book-to-skill creates a reusable indexed artifact in advance.

## Context Map

- Layer: context
- Domains: coding, research
- Topics: skills, context-engineering, retrieval

## Uncertainty

- The repository says conversion costs roughly **$1 per book**, and repeated use is where amortization helps. Chapter detection expects explicit numbered headings; one-off reading, broad library search, and poorly segmented sources may be better served by other approaches.

## Agent Instruction

Use this item as source-backed context. Do not invent claims beyond the linked source. If this item conflicts with another source, call out the conflict.