Ida Reverse Engineering
Drive IDA Pro through the IDA Pro MCP like a senior reverse engineer: don't just narrate decompiler output, transform the database. Use this whenever the user is reverse engineering, analyzing malware, working a crackme or CTF, or doing binary/firmware analysis with IDA Pro over an MCP connection (mrexodia/ida-pro-mcp or idalib-mcp) — and especially when the agent keeps guessing at raw pseudocode instead of renaming functions and variables, defining structs, fixing types, and adding comments. Covers the iterative cleanup loop, anti-hallucination rules (always use int_convert; read real bytes/s
Install
npx skills add Newmcpe/ida-reverse-engineering-skill --skill ida-reverse-engineeringgit clone --depth 1 https://github.com/Newmcpe/ida-reverse-engineering-skill.git /tmp/ida-reverse-engineering-skill
mkdir -p ~/.claude/skills
cp -r /tmp/ida-reverse-engineering-skill/. ~/.claude/skills/ida-reverse-engineeringPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Senior Reverse Engineering with IDA Pro (MCP) This skill turns a model connected to IDA Pro via MCP into something that behaves like an experienced reverse engineer instead of a narrator. The single biggest failure mode of an MCP-driven RE agent is treating decompiler output as an *answer to explain* rather than *raw material to transform*. A junior reads `sub_401000`, says "this looks like it validates a license," and moves on. A senior renames the function to `validate_license`, names every variable, defines the struct behind `*(a1 + 0x10)`, fixes the argument types, comments the algorithm, re-decompiles to confirm the output got cleaner, and only then moves on — leaving the database permanently better than they found it. Your job is to do the second thing, on every function, using the MCP write tools. You are a capable model. Use that: reason from evidence, form hypotheses and test them against the binary, and decide *where to spend effort*. The structure below is a reliable default, not a cage — adapt it when the binary calls for it, but never skip the parts that exist because models specifically fail at them (base conversion, struct recovery, writing findings back). > **Scope and ethics.** This skill supports legitimate reverse engineering: malware *analysis* > and triage, vulnerability research, interoperability, firmware/protocol analysis, CTFs, and > crackmes. It is about *understanding* and *documenting* binaries. Do not use it to author
Details
- Skill name
ida-reverse-engineering- Repository
- Newmcpe/ida-reverse-engineering-skill
- License
- WTFPL
- Repo updated
- 11 June 2026
FAQ
What does the Ida Reverse Engineering skill do?
Drive IDA Pro through the IDA Pro MCP like a senior reverse engineer: don't just narrate decompiler output, transform the database. Use this whenever the user is reverse engineering, analyzing malware, working a crackme or CTF, or doing binary/firmware analysis with IDA Pro over an MCP connection (mrexodia/ida-pro-mcp or idalib-mcp) — and especially when the agent keeps guessing at raw pseudocode instead of renaming functions and variables, defining structs, fixing types, and adding comments. Covers the iterative cleanup loop, anti-hallucination rules (always use int_convert; read real bytes/s
How do I install the Ida Reverse Engineering skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add Newmcpe/ida-reverse-engineering-skill --skill ida-reverse-engineering. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Ida Reverse Engineering popular?
It lives in Newmcpe/ida-reverse-engineering-skill, which has 8 GitHub stars and 1 forks.
Related skills
Information Literacy
9Liii8888/information-literacy
专为大学生“AI+信息素养”大赛备赛、模拟练习和规则允许的辅助答题设计。为单选、多选、判断题拆解条件，核验学术检索、科研AI工具、文件版本、产品菜单与引用证据；不提供题库或默认正式考试授权。
Hebbs
9hebbs-ai/hebbs-skill
Cognitive engine for AI agents: index files and memories, retrieve across 4 weighted dimensions (similarity, temporal, importance, frequency), automatic insight consolidation, automatic contradiction detection, with full parameter control on every function.
Interview Designer
8zhangchau/interview-designer-skill
Generate interview questions with assessment dimensions and A-level reference answers from a resume, JD, PRD, or portfolio. Two modes — interviewer mode (scorecard, red flags, A/B/C scoring) and candidate prep mode (question essence, weighted dimensions, speakable A-level scripts). Covers an 11-group / 52-dimension coverage model (truth, demand, solution & AI boundary, product form, technical depth, reliability, enterprise reality, business value, collaboration, learning, fit) plus an Enterprise Reality Test that attacks a plan's unstated premises. Staged output with a hard context budget so l
Genpark Sourcing
9alphaparkinc/openclaw-genpark-sourcing
Product sourcing agent to identify suppliers and compare prices.
Manju Creator
9rfdiosuao/Yuhang-ManJu
漫剧创作大师 - 全流程 AI 视频创作体系。整合提示词工程、图像生成、视频生成、后期剪辑四大能力。Invoke when user wants to create AI video, manga, short drama, or needs prompt engineering for video generation.
Genpark Nano Banana Stylizer
9alphaparkinc/genpark-nano-banana-stylizer
Creative Style Transformer. Applies complex AI stylizations (LEGO, Funko Pop, Toy styles) while maintaining character consistency.
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.