Ghidra Iterative Re
Use when reverse-engineering a game (or any binary) in Ghidra via MCP or PyGhidra - establishes the apply-cascade-verify loop, the SourceType trust model that stops an agent corroborating its own guesses, invariant bracketing against Ghidra's silent collateral damage, and the game-specific evidence sources worth sweeping before any analysis.
Install
npx skills add GeReV/ghidra-iterative-re --skill ghidra-iterative-regit clone --depth 1 https://github.com/GeReV/ghidra-iterative-re.git /tmp/ghidra-iterative-re
mkdir -p ~/.claude/skills
cp -r /tmp/ghidra-iterative-re/. ~/.claude/skills/ghidra-iterative-rePersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Iterative reverse engineering in Ghidra Ghidra is not a disassembly viewer you read from. It is an inference engine with a persistent, versioned database. Knowledge you apply changes what the decompiler shows you next, which is where the next round of knowledge comes from. Refusing to write to it throws away the tool's main mechanism and is the more expensive choice. But the loop has a failure mode batch analysis does not: **you can corroborate your own guesses.** Apply an inference, re-read, and the confirming read looks independent when it is not. This file is the loop and the rules that bind every round; the catalogues behind it are in `references/`, keyed by the kind of work you are about to do. **Confidence convention.** Claims marked *(doc)* come from Ghidra's own documentation but have not been executed. Unmarked claims were either measured live or are project history. Quoted numbers from one binary are examples for calibration, not properties of yours. ## Start here **The loop below begins at `apply`, and on a binary you have just opened there is nothing to apply yet.** Two different things bring you to this file, and they have different first moves. Find yours before reading further. **A — A binary nobody has worked yet.** Do not enter the loop. Round zero is measurement, not inference: 1. **Confirm what you are looking at.** Architecture, endianness and the compiler toolchain, from the file itself — getting endianness wrong at import garbles the whole
Details
- Skill name
ghidra-iterative-re- Repository
- GeReV/ghidra-iterative-re
- License
- MIT
- Repo updated
- 23 October 2026
FAQ
What does the Ghidra Iterative Re skill do?
Use when reverse-engineering a game (or any binary) in Ghidra via MCP or PyGhidra - establishes the apply-cascade-verify loop, the SourceType trust model that stops an agent corroborating its own guesses, invariant bracketing against Ghidra's silent collateral damage, and the game-specific evidence sources worth sweeping before any analysis.
How do I install the Ghidra Iterative Re skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add GeReV/ghidra-iterative-re --skill ghidra-iterative-re. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Ghidra Iterative Re popular?
It lives in GeReV/ghidra-iterative-re, which has 5 GitHub stars and 1 forks.
Related skills
Gpt Pro Audit
5hubeiqiao/gpt-pro-audit
Use when the user asks to audit a plan, document, diff, website finding, or implementation proposal with ChatGPT using Pro reasoning effort through Chrome - starts automatically after invocation, packages codebase/project context ChatGPT cannot see, runs up to 5 review rounds until accepted, verifies Effort Pro and the response, and applies only accepted findings.
Filemaker AI Vocabulary
5andykear/FileMaker-AI-vocabulary
Use this skill whenever Claude needs to name, call, or validate a FileMaker function or script step — writing a calculation, writing a script, checking whether a function or script step exists, checking parameter order or count, or checking whether a script step is supported on a given platform (Pro, Go, WebDirect, Server, Cloud, Data API, Custom Web Publishing). Trigger any time FileMaker calculation syntax or script step syntax is being written or reviewed. Do not name or call a FileMaker function or script step from memory alone — check the reference files first.
Handover
5Hype-yolo/handover-skill
换账号、额度用完或会话中断后，接手本机其他 Claude 会话的工作。本机所有 Claude Code / 桌面端 Code 会话（不分账号）的记录都在 ~/.claude/projects，从中读出每个会话的标题、用户原话和附图、最后的回复、是否因额度用完中断、哪条用户指令还没做完、改过哪些文件，再对照磁盘真实状态接着做。用于 /handover、「接手」「交接」「另一个 Claude / 另一个账号做到哪了」「额度用完了换个账号继续」「你看得到另一个会话吗」。项目有自己的接手流程时，先用本 skill 找出各会话的状态和用户原话，再按项目流程续做。
Eforest Agent Skills
5eforest-finance/eforest-agent-skills
eForest symbol and forest NFT operations for agent workflows.
Horse Race
5qiao/horse-race
Competitive multi-agent problem solving: spawns multiple Claude Code sub-agents in parallel git worktrees to independently solve the same programming task, then cross-pollinates their solutions through improvement rounds where each agent sees and learns from all others' diffs, and finally selects the best solution through Borda count consensus voting with independent judges. Use this skill whenever the user says 'horse race', 'race', 'compete', 'multi-agent', wants to compare multiple approaches to a problem, or wants higher-quality solutions through competitive iteration. Also triggers when u
Claudeshrink
5g-akshay/ClaudeShrink
Automatically compress large natural text or log files before processing. Trigger when the user pastes massive text blobs, or asks to analyze a large file (logs, docs, transcripts), or provides a prompt that is too large for the context window. DO NOT trigger on source code files or structural data (JSON, XML).
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.