Layout rules and templates that let AI agents export documents as PDF, PNG and editable PowerPoint.
dmoshehun-prog/learn-from-materials
An agent skill that turns PDFs, books, slides and papers into traceable knowledge bases and interactive learning web pages.
- Stars
- 1,061
- Forks
- 98
- Open issues
- 0
- Last commit
- 13 days ago
What is it?
learn-from-materials is a skill for AI coding agents that read local files and run Python, such as Claude Code, Codex and WorkBuddy. You point it at a book, PDF, EPUB, DOCX, PPTX, HTML or a set of files, and it produces a `.learnkb/` knowledge base, a self-contained offline HTML learning page, and a Markdown version built from the same content data.
The generated pages organize material into core frameworks, guided content with source locations, a glossary, action rules, self-check quizzes and local notes. Fine-grained source mapping covers PDF pages, PPT slides and EPUB chapters. Reusable methods are saved to a `methods.json` library with stable IDs, and an "Apply This Methodology" panel builds a prompt for asking your agent questions about the material.
The skill offers two depths: a quick overview of core arguments, and a systematic study that reads the full source and runs coverage and reverse checks. Material-backed facts are kept separate from model-added content, and pages store notes and quiz records only in the browser's local storage.
Key features
- 01Converts PDF, EPUB, DOCX, PPTX, Markdown and other formats into a traceable knowledge base
- 02Generates a self-contained offline HTML learning page with framework maps and self-check quizzes
- 03Maps facts to PDF pages, PPT slides and EPUB chapters for source checking
- 04Saves reusable methods to a versioned methods.json library
- 05Offers quick overview and systematic study depths with coverage checks
- 06Keeps reader notes and quiz records only in the local browser
Use cases
- Systematically studying a technical book or research paper with a checkable outline
- Getting a quick overview of a slide deck or industry report with page-level citations
- Building a self-study quiz and notes page from course materials
- Turning a set of related documents into one browsable offline learning site
Quick start
- 1
Extract the 1.0 release ZIP and place the learn-from-materials folder in your agent's skill directory
- 2
Or clone the repository into your agent's skill directory (example for Claude Code)
git clone https://github.com/dmoshehun-prog/learn-from-materials.git ~/.claude/skills/learn-from-materials
Things to know
- It needs an agent that can read files, run local commands and recognize SKILL.md, plus Python 3.10 or later.
- Pure chat environments without file access or Python can only use parts of the prompting workflow.
Topics
FAQ
- What is learn-from-materials?
- An agent skill that turns PDFs, books, slides and papers into traceable knowledge bases and interactive learning web pages. learn-from-materials is a skill for AI coding agents that read local files and run Python, such as Claude Code, Codex and WorkBuddy. You point it at a book, PDF, EPUB, DOCX, PPTX, HTML or a set of files, and it produces a `.learnkb/` knowledge base, a self-contained offline HTML learning page, and a Markdown version built from the same content data.
- Is learn-from-materials free to use? What license does it have?
- learn-from-materials is open source under the MIT license. Check the license terms before using it in commercial products.
- Is learn-from-materials still maintained?
- Actively maintained. The last commit to learn-from-materials was on Oct 7, 2026.
- What can I use learn-from-materials for?
- Systematically studying a technical book or research paper with a checkable outline Getting a quick overview of a slide deck or industry report with page-level citations Building a self-study quiz and notes page from course materials Turning a set of related documents into one browsable offline learning site
- How do I install learn-from-materials?
- Extract the 1.0 release ZIP and place the learn-from-materials folder in your agent's skill directory Or clone the repository into your agent's skill directory (example for Claude Code): git clone https://github.com/dmoshehun-prog/learn-from-materials.git ~/.claude/skills/learn-from-materials
- Where can I get learn-from-materials?
- The source code and installation instructions are on GitHub: https://github.com/dmoshehun-prog/learn-from-materials
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Claude Code, Codex and OpenCode plugin that builds LLM-compiled, Obsidian-compatible knowledge bases through parallel research, source ingestion and querying.
A browser built for AI agents and you to share: agents run tasks in isolated Spaces while your own tabs and logins stay untouched.
A curated directory of 1000+ Claude Skills and plugins for Claude Code, Claude.ai and coding agents like Codex, Cursor and Gemini CLI.
A collection of AI agent skills by Baoyu for content creation, image generation, and publishing to WeChat, X, and Weibo, for Claude Code, Codex, and similar agents.
An Obsidian plugin that embeds AI coding agents such as Claude Code and Codex into your vault as a working collaborator.