zhaoxuya520 / reverse-skill

zhaoxuya520 / reverse-skill

reverse-skill Cybersecurity Skills Router · 逆向技能路由包 Navigate the dark waters, sail against the stream. 在暗流中航行,逆流而上。


About

关于

If you are an AI Agent, jump to README_AI.md and follow the instructions strictly. When an AI agent (Claude Code, Codex CLI, Cursor, etc.) encounters an APK, a binary, frontend JS encryption, a CTF challenge, or a pentesting target, this package routes it to the right methodology, checks available tools, and executes a repeatable workflow instead of guessing commands. 如果你是 AI Agent,请跳转至 README_AI.md 并严格遵循说明。当 AI Agent(如 Claude Code、Codex CLI、Cursor 等)遇到 APK、二进制文件、前端 JS 加密、CTF 挑战或渗透测试目标时,该包会将任务路由至正确的方案,检查可用工具,并执行可重复的工作流,而不是盲目猜测命令。

User task → RULES.md → MASTER-ROUTING / master-route.ps1 (PRIMARY) → case-init / scope.md (auth + network_profile; no target ACT until ready) → Scenario skill → tools / MCP / scripts → timeline + Evidence→Finding→Path → report + field-journal 用户任务 → RULES.md → MASTER-ROUTING / master-route.ps1 (主路由) → case-init / scope.md (授权 + 网络配置;准备就绪前不执行目标操作) → 场景技能 → 工具 / MCP / 脚本 → 时间线 + 证据→发现→路径 → 报告 + 现场日志

Why this exists: 存在意义:

  • AI agents don’t know whether to use jadx, apktool, Frida, IDA, or BurpSuite for a given task.
  • AI Agent 不知道针对特定任务该使用 jadx、apktool、Frida、IDA 还是 BurpSuite。
  • APK, ELF, JS, PCAP, and CTF tasks each need different playbooks.
  • APK、ELF、JS、PCAP 和 CTF 任务各自需要不同的行动指南。
  • Tools, MCP servers, and scripts are scattered across machines.
  • 工具、MCP 服务器和脚本分散在各台机器上。
  • The same mistakes get repeated because experience isn’t reused.
  • 由于经验无法复用,同样的错误会反复出现。

PRIMARY ladder: skills/MASTER-ROUTING.md · Full matrix: skills/routing.md · Ops: skills/ops/ 主阶梯: skills/MASTER-ROUTING.md · 完整矩阵: skills/routing.md · 运维: skills/ops/


Getting Started

入门指南

Prerequisites 先决条件

  • Java / JDK — for jadx and apktool
  • Java / JDK — 用于 jadx 和 apktool
  • Node.js 22.12+ — for JS toolchain and MCP servers
  • Node.js 22.12+ — 用于 JS 工具链和 MCP 服务器
  • Python 3.x — for Frida and helper scripts
  • Python 3.x — 用于 Frida 和辅助脚本
  • A code AI client — Claude Code, Codex CLI, Cursor, etc.
  • 代码 AI 客户端 — Claude Code、Codex CLI、Cursor 等。

Installation 安装 git clone https://github.com/zhaoxuya520/reverse-skill.git Then refresh the tool index per platform: 然后根据平台刷新工具索引:

PlatformCommand
Windowspowershell -File skills/scripts/refresh-tool-index.ps1
Linux / macOSbash skills/scripts/refresh-tool-index.sh
Kali Linuxbash kali/scripts/refresh-tool-index.sh

Check skills/tool-index.md to see detected tools. 查看 skills/tool-index.md 以查看已检测到的工具。


Usage

使用方法

Supported scenarios 支持的场景

ScenarioEntry
APK / Android analysisskills/apk-reverse/
iOS / mobileskills/mobile-reverse/
Binary reverse (exe/dll/so/elf)skills/ida-reverse/ / skills/radare2/
.NET / C#skills/dotnet-reverse/
Frontend JS / encrypted paramsskills/js-reverse/
DSL VM / custom JS opcode VMskills/reverse-engineering/dsl-vm-reverse/
HTTP capture / request replayanything-analyzer + js-reverse/
Malware / YARAskills/malware-analysis/
Penetration testing / scanningskills/pentest-tools/
Attack chain / red-team orchestrationskills/attack-chain/
CTF competitionCTF-Sandbox-Orchestrator/ (40+ sub-skills)
Firmware / IoTskills/firmware-pentest/
Patch diff / N-dayskills/patch-diff-exploit/
Pwn / exploit developmentskills/pwn-chain/
EDR bypassskills/edr-bypass-re/
API / GraphQLskills/api-security/
Supply chain / SBOMskills/supply-chain-security/
LLM / AI securityskills/llm-security/
OLLVM deobfuscationskills/reverse-engineering/references/ollvm-deobfuscation.md
Diagrams / reportsskills/diagram-generator/ / skills/docs-generator/

Contributing

贡献

Contributions are welcome! Fork the repo, create a feature branch, and open a PR. 欢迎贡献!请 Fork 本仓库,创建功能分支,并提交 PR。


License

许可

This project (reverse-skill) is primarily licensed under the MIT License (see LICENSE). 本项目 (reverse-skill) 主要采用 MIT 许可证(详见 LICENSE)。


Acknowledgments

致谢

Thanks to all open-source tool authors. This project integrates tools across reverse engineering, penetration testing, CTF, and security analysis — every tool is the fruit of community effort. 感谢所有开源工具作者。本项目整合了逆向工程、渗透测试、CTF 和安全分析领域的工具——每一个工具都是社区努力的结晶。