satori

Name: satori
Author: yuxino

by yuxino

Verified

Read PDF textbooks and ask AI about any paragraph, figure, or code block.

136stars

16forks

TypeScript

Added 8/28/2026

Installation

# Add to your Claude Code skills
git clone https://github.com/yuxino/satori

Getting Started

Guides for using ai agents skills like satori.

Caveman: Cut Claude Token Use by 65%
How agent-side prompt compression works, when to use it, and when not to.
What is an AI Skills Marketplace?
Definitions, how marketplaces work, and how to choose between them in 2026.
Getting Started with AI Skills

Security ReportVerified

Last scanned: 8/28/2026

{
  "issues": [],
  "status": "PASSED",
  "scannedAt": "2026-08-28T15:56:02.669Z",
  "npmAuditRan": true,
  "pipAuditRan": true,
  "promptInjectionRan": true
}

README.md

Frequently Asked Questions

What is satori?

satori is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by yuxino. Read PDF textbooks and ask AI about any paragraph, figure, or code block. It has 136 GitHub stars.

Is satori safe to use?

Yes. satori passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.

How do I install satori?

Clone the repository with "git clone https://github.com/yuxino/satori" and add it to your Claude Code skills directory (see the Installation section above).

What programming language is satori written in?

satori is primarily written in TypeScript. It is open-source under yuxino on GitHub, so you can review or fork the full source.

Are there alternatives to satori?

Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh satori against similar tools.

Agentic AI for Beginners

Build your first AI agent from scratch - tool use, ReAct pattern, memory, deployment

41 minBeginner

Comments (0)

to leave a comment.

No comments yet. Be the first to share your thoughts!

Related Skills

ECC

by affaan-m

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

256,066

sail-skill source-reading-methodology

⚠️ Third-Party Software Notice

This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.

Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.

Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.

Read the Terms of Service

Satori means “enlightenment” in Japanese.

A local-first PDF learning app for macOS and Windows 11. Ask AI about the current page or a selected region, then compare the explanation with the source. Your reading progress and Q&A are saved locally for each book.

Demo

Features

Ask about the current page or drag over a paragraph, figure, or code block for a visual explanation. Text, scanned, and mixed PDFs are supported.
Read in single- or two-page view with outline navigation and zoom; each book reopens where you left it.
Keep reading activity and Q&A organized per book, with links back to the source page.
Choose among Alibaba Cloud Model Studio, OpenAI, and custom OpenAI-compatible visual models.
Check for a signed update in Settings, review its notes, then explicitly download, verify, and install it.
Read and manage the library without configuring AI.

Download

Satori supports Windows 11 on x64 and ARM64, and macOS 14+ on Apple silicon. Download Satori 3.4.6 from GitHub Releases.

Windows: choose the NSIS installer matching your architecture. It installs for the current user. The installers are not Authenticode-signed, so Windows shows an unknown publisher warning. Interactive validation is architecture-specific; x64-on-x64 manual acceptance is not yet claimed.
macOS: unzip the download and move Satori to Applications. The build has a local signature but is not notarized; on first launch, Control-click Satori and choose Open.

Version 3.4.4 introduced the updater: anyone using 3.4.3 or earlier must manually install the current release once from GitHub Releases. From 3.4.4 onward, Settings can download and verify later signed releases before an explicit install. Satori never downloads or installs an update in the background. On macOS, the learner clicks Restart and finish after installation; on Windows, starting installation closes Satori and hands control to the visible system installer.

The interface is currently available in Simplified Chinese only. Reading works without AI; questions and scanned-outline recognition require an image-capable OpenAI-compatible model. Satori is free and open source; your chosen AI service may charge separately.

Development

Install Node.js 22.13+, stable Rust, and the platform-specific Tauri prerequisites. macOS development also requires a stable code-signing identity.

npm install
# macOS
npm run app
# Windows
npm run tauri -- dev

Privacy

PDFs remain at their original paths. Library data and Q&A stay in Application Support on macOS or application LocalAppData on Windows; API keys stay in macOS Keychain or Windows Credential Manager. Page images are sent to the selected AI service only after an explicit question, explanation request, or confirmed outline scan. Opening a book does not contact an AI service. The launch-time update check fetches only the static updater manifest from GitHub Releases; it never sends book content, history, AI profiles, or keys.