Maintainer of this skill?
by reacher-z
Awesome Reverse Engineering Anything: tools, projects, case studies and research papers for websites, games, apps, binaries, firmware and communication protocols.
# Add to your Claude Code skills
git clone https://github.com/reacher-z/Awesome-REASee how Awesome-REA compares with popular alternatives.
Awesome-REA is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by reacher-z. Awesome Reverse Engineering Anything: tools, projects, case studies and research papers for websites, games, apps, binaries, firmware and communication protocols. It has 62 GitHub stars.
Awesome-REA's catalog security scan is still queued. You can run an instant dependency and prompt-injection check now with the "Scan for vulnerabilities" button above.
Clone the repository with "git clone https://github.com/reacher-z/Awesome-REA" and add it to your Claude Code skills directory (see the Installation section above).
Awesome-REA is primarily written in Python. It is open-source under reacher-z on GitHub, so you can review or fork the full source.
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 Awesome-REA against similar tools.
No comments yet. Be the first to share your thoughts!
Available after the catalog security scan passes.
⚠️ 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.
The deep catalog scan for this skill is still queued. Run an instant dependency check now instead.
An independent collection of tools, case studies and research for websites, games, apps, native binaries, firmware and communication protocols.
English · 简体中文
Search & filter · Browse cases · Research papers · HTML survey
Source review does not imply runtime verification. Review method
Tools and cases by target
Research and workflows
More ways to browse
| Task | Relevant sections |
|---|---|
| Inspect a website or app interface | Websites · Apps |
| Rebuild a game or check matching code | Games · Game cases |
| Analyze compiled code or recover symbols | Native binaries · Agents and MCP |
| Investigate firmware or device protocols | Firmware · Protocols |
| Compare methods and evaluation evidence | Papers · Survey comparisons |
Names link to original sources. Each description is followed by its type, relationship and a “Requirements & evidence” link for prerequisites, limitations and review sources.
Each resource appears once under its main purpose. Cases reuse these entries; papers are listed separately. Browse the resource directory.
REA labels refer to the separate upstream CLI and MCP project. Listing does not imply REA integration. About this independent collection.
Dinosaur runner: recovering one acceleration rule
REA’s documented teaching case inspects the HTTP t-rex-runner edition and reconstructs its speed-update rule. A separate controlled original-game check and a new demonstration compare update counts, including the floating-point step that crosses the nominal speed threshold.
Case study · REA · Requirements & evidence
rauchg.com: rebuilding an RSC blog from captured Flight output
Documents a website-rebuild-skill case that decodes browser-delivered React Server Component Flight streams, reconstructs a buildable Next project and compares its output with a captured site. The reported rauchg.com campaign uses route-tree comparison and module-reference mapping; the new server source is inferred from observable output.
Case study · Independent reconstruction · Requirements & evidence
BaoCut Slides: adapting an interactive web editor
Documents BaoCut’s interactive slide editor, whose author says the implementation draws on Claude Slides. It adds a local deck store, HTML/CSS compiler and annotation-to-agent bridge for browser and desktop hosts; the design reports a Web-flow check, without establishing original backend recovery or full behavioral parity.
Case study · Independent reconstruction · Requirements & evidence
REA in Claude Code: an isolated static-analysis A/B trial
A Japanese field report connects REA 6.4.0 to Claude Code in a separate project directory, denies 43 of its 170 tools and common shell launch forms, and compares REA-enabled and REA-disabled runs on two real tasks: an Electron terminal’s packaged files and a saved HAR capture. Both arms answered correctly, while the REA arm took up to 2.00× the time and 1.67× the API-equivalent cost. It is an analysis-evaluation and safety-configuration case, not a reconstruction.
Case study · Mixed workflow · Requirements & evidence
Dinosaur runner: an REA-inspected speed rule rebuilt with Codex
The author uses REA’s MCP browser tools to passively capture the JavaScript loaded by wayou’s open-source T-Rex Runner page, then has Codex rebuild its acceleration rule in one self-contained HTML5 Canvas game. The report identifies the captured script by SHA-256 and separates verified source facts from reconstruction choices; only the speed rule is claimed, not full gameplay equivalence.
Case study · Mixed workflow · Requirements & evidence
BaoCut Design: porting reconstructed canvas and design-system editors
Documents BaoCut’s design-canvas and design-system editors, which the project says it ported 1:1 from TypeScript reconstructions of Claude Design’s editors and hosts in agent sessions with annotation and export. Its runtime notes record identifier fixes checked against the original scripts and a structural comparison matching 19,111 of 20,463 canvas main-page functions. Unreviewed differences, the unpublished reconstruction record and reuse rights remain open; no hosted-backend recovery is claimed.
Case study · Independent reconstruction · Requirements & evidence
Improves JavaScript readability by reversing supported obfuscation patterns and unpacking webpack/Browserify bundles.
Tool · Requirements & evidence
Rename identifiers in minified JavaScript with LLM-suggested names, applied through scope-aware AST rewriting so the program structure stays unchanged. The new names are model suggestions, not recovered original identifiers.
Tool · Requirements & evidence
WebAssembly tools for binary-to-text conversion, section inspection, validation, interpretation and C translation.
Tool · WebAssembly · Requirements & evidence
Bytecode Alliance CLI and Rust libraries for inspecting WebAssembly modules, metadata, components and WIT interfaces.
Tool · WebAssembly · Requirements & evidence
Connect an agent to Chrome for live page inspection, network debugging, and performance traces.
Integration · Independent MCP · Requirements & evidence
Inspect and record HTTP traffic with an interactive proxy, web interface, or scriptable command-line tools.
Tool · Requirements & evidence
Drive browser interactions through structured accessibility snapshots to investigate reproducible web behavior.
Integration · Independent MCP · Requirements & evidence
PortSwigger's Burp Suite ext
