rea
Lets your agent reverse engineer an app from the outside, down to native binaries, and then build its own version.
Install
npx skills add morluto/rea -a claude-code
npx skills add morluto/rea -a claude-code -g
Or copy the skill folder into .claude/skills/ (project) or ~/.claude/skills/ (all projects).
npx skills add morluto/rea -a codex
npx skills add morluto/rea -a codex -g
Or copy the skill folder into .agents/skills/ (project) or ~/.agents/skills/ (all projects).
npx skills add morluto/rea -a cursor
npx skills add morluto/rea -a cursor -g
Or copy the skill folder into .agents/skills/ (project) or ~/.cursor/skills/ (all projects).
npx skills add morluto/rea -a gemini-cli
npx skills add morluto/rea -a gemini-cli -g
Or copy the skill folder into .agents/skills/ (project) or ~/.gemini/skills/ (all projects).
Ask your agent to set up REA, which registers it as an MCP server, or use the terminal tools. Analysis runs locally.
When to use
Use it for interoperability work, security research or studying software you're permitted to analyze. Check the license and local law before you analyze or copy a commercial product.
REA, short for Reverse Engineer Anything, is an MCP server that lets an agent inspect apps from the outside. It connects the agent to tools for native binaries, JavaScript and Electron apps, .NET assemblies and websites. Point it at a feature in someone else's product and it works out how the feature behaves without the source code. Each conclusion comes with the evidence behind it and a note on what the agent couldn't confirm.
The pitch is to understand how a feature works, down to the binary, and then build your own version. Reverse engineering has legal limits that depend on your license terms and jurisdiction. The README is translated into more than twenty languages.
Related skills
-
superpowers
A set of development habits for your agent: test first, debug systematically, and plan before you code.
-
skills
The skills Matt Pocock uses in his own day-to-day engineering work.
-
ECC
A ready-made setup for coding agents that adds skills, persistent memory and security checks.
-
Anthropic Skills
Anthropic's own repository of Agent Skills: folders of instructions, scripts and resources that Claude loads when a task needs them.