ai-reverse-toolkit
CLAUDE.md462 starsChanged 8 months agoMITView on GitHub
AI-assisted skills, rules, and prompts for reverse engineering (Web/JS, Android/iOS App). This is a prompt/knowledge repository, not a runnable application — there are no build steps, tests, or dependencies to install. This toolkit is designed to work with the js-reverse MCP server for browser debugging. The MCP provides Chrome DevTools Protocol access: network inspection, breakpoints, script source retrieval, function hooking, and JS evaluation. Skills are defined as SKILL.md files with YAML frontmatter (name, description, argument-hint). Follow the pattern in skills/find-crypto-entry/SKILL.md:…
In this repository4 other files it gives its agents.
- ast-deobfuscateSkill
- env-patchSkill
- find-crypto-entrySkill
- skill-creatorSkill
The file
We split this CLAUDE.md into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 27
Use uv to run Python and manage Python projects
≈ “Common” is an estimate: at least 1 in 5 of the 27,641 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
AI-assisted skills, rules, and prompts for reverse engineering (Web/JS, Android/iOS App). This is a prompt/knowledge repository, not a runnable application — there are no build steps, tests, or dependencies to install.
Repository Structure
skills/— Task-oriented Claude Code skills (SKILL.md files with frontmatter). Each skill is a self-contained workflow for a specific reverse engineering task.rules/— Background knowledge documents providing reference guides, tool usage patterns, and domain expertise for reverse engineering.prompts/— Common prompt templates (planned, not yet populated).
Key MCP Dependency
This toolkit is designed to work with the js-reverse MCP server for browser debugging. The MCP provides Chrome DevTools Protocol access: network inspection, breakpoints, script source retrieval, function hooking, and JS evaluation.
Conventions
- Skills use
$ARGUMENTSas placeholder for user-provided parameters - Analysis progress is tracked in
PROGRESS.md(created per-project, not in this repo) - Deobfuscation scripts go in
scripts/deobfuscate_{target}.js - Deobfuscated output goes in
source/deobfuscated/{filename}_deobf.js - Python algorithm implementations go in
output/sign.py - Content is written in Chinese (Simplified)
- Use
uvto run Python and manage Python projects
Writing New Skills
Skills are defined as SKILL.md files with YAML frontmatter (name, description, argument-hint). Follow the pattern in skills/find-crypto-entry/SKILL.md: define clear step-by-step workflows with decision points and fallback paths between steps.
Writing New Rules
Rules are standalone markdown files in rules/. They should provide structured reference material (identification tables, tool command references, common patterns) rather than step-by-step workflows.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

