Turn an APK into readable Java or decompiled source artifacts so an agent can inspect behavior before deeper reverse-engineering or triage.
Scanned 6/8/2026
Install via CLI
openskills install agentskillexchange/skills---
name: "Decompile Android APKs into readable source with jadx for review and analysis"
slug: "decompile-android-apks-into-readable-source-with-jadx-for-review-and-analysis"
description: "Turn an APK into readable Java or decompiled source artifacts so an agent can inspect behavior before deeper reverse-engineering or triage."
github_stars: 46142
verification: "security_reviewed"
source: "https://github.com/skylot/jadx"
author: "skylot"
publisher_type: "individual"
category: "Security & Verification"
framework: "Multi-Framework"
tool_ecosystem:
github_repo: "skylot/jadx"
github_stars: 46142
---
# Decompile Android APKs into readable source with jadx for review and analysis
Turn an APK into readable Java or decompiled source artifacts so an agent can inspect behavior before deeper reverse-engineering or triage.
## Prerequisites
jadx CLI or GUI, target APK or DEX files, Java runtime, local workspace for extracted artifacts
## Installation
Use the upstream install or setup path that matches your environment:
- brew install jadx
- git clone https://github.com/skylot/jadx.git
Requirements and caveats from upstream:
- JDK 17 or higher must be installed:
Basic usage or getting-started notes:
- find usage
- smali debugger, check [wiki page](https://github.com/skylot/jadx/wiki/Smali-debugger) for setup and usage
- After download unpack zip file go to bin directory and run:
- Source: https://github.com/skylot/jadx
- Extracted from upstream docs: https://raw.githubusercontent.com/skylot/jadx/HEAD/README.md
## Documentation
- https://github.com/skylot/jadx
## Source
- [Agent Skill Exchange](https://agentskillexchange.com/skills/decompile-android-apks-into-readable-source-with-jadx-for-review-and-analysis/)
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.