virgiliojr94 /book-to-skill
Turn any technical book PDF into a Claude Code skill — ready to study, reference, and use while you work.
★ 37,970⑂ 4,037👁 152⑃ 258● 79▤ 5
+106
Daily
+542
Weekly
+3,545
Monthly
37,970
stars
4,037
forks
152
watchers
258
prs
79
issues
5
releases
README
book-to-skill English · Русский · 简体中文 Turn any technical book, document folder, or collection of sources into a unified agent skill — ready to study, reference, and use while you work in GitHub Copilot CLI, Amp, Claude Code, Codex, Hermes Agent, OpenCode, or OpenClaw. Why · What it generates · Beyond books · How it works · Usage · Install · FAQ · Performance · Architecture · Changelog 24×–51× fewer tokens than dumping the book into context to answer one question, measured on real books (how it's measured). How it works, in 3 steps: 1. Point it at a file, folder, or glob — /book-to-skill ./my-book.pdf 2. It distills the book into a skill — frameworks, decision rules, anti-patterns, and per-chapter files. Structure, not a summary. 3. Your agent loads it on demand — ask /my-book replication and it reads the right chapter and answers from the real content, no hallucination. --- 🤔 Why You buy a great technical book. You read it once. Three months later you can't remember chapter 7 existed. The usual workarounds don't help: - 📄 "Let me just search the PDF" → you get a list of pages, not answers - 🧠 "I'll ask the agent about this book" → it either hallucinates or says it doesn't have the content - 📝 "I'll take notes as I read" → you end up with a 200-line doc you never open again book-to-skill solves this by turning the book into a structured skill your agent loads on demand. Once installed, you just type /your-book-slug replication and the agent reads the right chapter and answers from the actual content. No hallucination. No digging through PDFs. The book becomes part of your workflow. Works with any host that supports the open Agent Skills standard — GitHub Copilot CLI, Amp, Claude Code, Codex, Hermes Agent, OpenCode, and OpenClaw all read the same SKILL.md format. --- 📦 What it generates Running /book-to-skill your-book.pdf (or a folder, glob, or list of files) creates a full skill in the user-level cross-agent skills directory ~/.agents/skills// — one copy that Copilot CLI, Amp, Codex, OpenCode, and OpenClaw discover natively (OpenCode also reads its own managed root ~/.config/opencode/skills//; OpenClaw also discovers it when using its default state directory, with a non-default OPENCLAW_STATE_DIR use the active state's skills/ root instead). When run under Claude Code, the converter also attempts a verified symlink at ~/.claude/skills// — Claude Code sees the skill when the link read-back confirms it; otherwise the run report says so. Hermes Agent partitions its personal skills by category and does not scan the cross-agent root, so a Hermes install lands in /skills/// instead. OpenClaw-managed, OpenCode-managed, and project-local destinations remain available when explicitly requested: | File | Purpose | Size | |------|---------|------| | SKILL.md | Core mental models + chapter index | ~4,000 tokens | | chapters/ch01-.md … | One file per chapter, loaded on-de
Top issues
#309Proposal: slim down the installed skill payload (split runtime files from dev/site files)4 comments · 2026-10-27#128PDF: `pdftotext -layout` interleaves columns on multi-column documents, and the word-based token estimate hides the 26x size blowup2 comments · 2026-08-10#169The generator's own SKILL.md is 7k tokens with zero references — 52% of it loads before the run knows it can proceed2 comments · 2026-08-15#263[bug] BeautifulSoup HTML/EPUB extraction inserts newlines inside inline headings and code tokens1 comments · 2026-10-01#259[bug] Interrupted-run reuse accepts missing or corrupted extracted text1 comments · 2026-09-30#334[bug] DOCX fallback concatenates paragraphs inside table cells0 comments · 2026-11-11#330[bug] PDF page-count mismatch does not mark individual pages for review0 comments · 2026-11-09#326[bug] Reused workdir can retain stale PDF page evidence0 comments · 2026-11-06
Latest release
v1.4.0 v1.4.0 2026-08-10Extraction reliability release: six fixes for silent content loss or silent wrong answers, plus the first changelog generated from commit messages. Highlights - Scanned PDFs fail fast. An image-only PDF used to run the whole extraction chain — Docling across every page in technical mode — before failing with a message about Unicode sanitization. It now stops on the first pages in ~0.01s and tells you to run ocrmypdf (130), and the docs finally state the limit (132). - Real words stopped being deleted. Page-edge cleanup treated any short word built from ivxlcdm as a page number, so "MIX", "CI
相关报道 (11)
blog.csdnGitHub爆火项目book-to-skill:把书变成实战技能的免费训练系统2026-09-15blog.csdn从读书到掌握技能:book-to-skill如何引爆GitHub,打造高效学习闭环2026-09-12blog.csdnbook-to-skill 使用教程:把任意文档蒸馏成 AI Skill 个人知识库 Agent 技能详解2026-09-03bilibiliGithub八月开源 Top 10:500+ GPT 生图神级灵感库、DeepSeek Harness、AI 入门课 ...2026-08-28note読んだ本をAIスキル化する「book-to-skill」——技術書が、いつでも参照できる辞書になる2026-08-17CSDN从GitHub周榜看Skill崛起:AI能力包如何重塑开发范式2026-11-09CSDNGitHub周榜权力交接:Skill退烧,大厂接棒定标准2026-11-09CSDNGitHub周榜揭示AI Agent技能生态交接:Skill退烧后大厂接棒2026-11-09CSDNGitHub周榜观察:Skill类项目热度暴涨,如何理解并手写技能包2026-11-06CSDNGitHub周报Skill霸榜:从SKILL.md到AI技能包,轻量方案逆袭Agent2026-11-06