/reverse-engineering
Use the bundled r2mcp MCP server for binary analysis, disassembly, and reverse-engineering tasks.
$ npx -y skills add radareorg/radare2-mcp --skill reverse-engineering --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/reverse-engineering
Context preview
The summary Claude sees to decide when to auto-load this skill.
Use the bundled r2mcp MCP server for binary analysis, disassembly, and reverse-engineering tasks.
SKILL.md
reverse-engineering.SKILL.mdname: reverse-engineering description: Use the bundled r2mcp MCP server for binary analysis, disassembly, and reverse-engineering tasks.
Use the bundled `r2mcp` MCP tools when the user asks about binaries, executables, libraries, firmware, shellcode, functions, symbols, strings, control flow, or patching with radare2.
Preferred workflow:
1. Open the target file or session first. 2. Run the minimum analysis needed for the task. 3. Prefer structured r2mcp tools over raw command execution when both are available. 4. Summarize findings in reverse-engineering terms the user can act on. 5. Close files or sessions when the task is finished.
Be explicit about uncertainty when analysis is partial or when the binary has not been fully analyzed yet.
An MCP server to use radare2 with AI agents such as OpenCode, Mai, VSCode, Claude, CLION, ...