State Diff logo

State Diff

Community
dariushoule
state-diff

Compare two state snapshots to identify register and memory changes between two points in time

Overview

Publisherdariushoule
Repositoryx64dbg-skills
Skill namestate-diff
Stars
210
Forks
18
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by dariushoule on GitHub. Read the source before you install it.

Installation

Install the State Diff AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/dariushoule/x64dbg-skills/tree/main/skills/state-diff
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/dariushoule/x64dbg-skills.git /tmp/x64dbg-skills
mkdir -p .claude/skills
cp -r /tmp/x64dbg-skills/skills/state-diff .claude/skills/state-diff
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable State Diff in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads State Diff on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so State Diff is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

state-diff

Compare two debuggee state snapshots and produce a detailed change analysis — which registers changed, which memory regions were modified, and what the changes mean.

Instructions

Follow these steps exactly:

1. Identify snapshots

List the available snapshots:

dir "${CLAUDE_PLUGIN_ROOT}\snapshots"

If there are fewer than two snapshots, tell the user they need at least two snapshots (captured via /state-snapshot) and stop.

If the user specified two snapshot paths, use those directly. Otherwise, present the available snapshots and ask the user to pick the before (earlier) and after (later) snapshots.

2. Run the diff script

Execute the diff engine:

python "${CLAUDE_PLUGIN_ROOT}\skills\state-diff\state_diff.py" --before <before_snapshot_dir> --after <after_snapshot_dir>

The script writes diff_report.json into the after-snapshot directory by default. If the user specified a custom output path, pass --output <path>.

3. Read the report

Use Read to load the generated diff_report.json.

4. Analyze and reason

Interpret the diff report for the user:

  • Register changes: Explain what each changed register suggests. For example:

    • RIP/EIP advanced → instructions were executed
    • RSP/ESP changed → stack grew or shrank (function calls, local variables)
    • RAX/EAX changed → likely a return value or computation result
    • Flag changes → comparison or arithmetic results
  • Memory changes: Explain what modified regions likely represent:

    • Stack region modifications → local variables written, function arguments pushed
    • Heap regions → dynamic allocations or object mutations
    • Image/module regions → self-modifying code or relocations
    • Look at the actual byte patterns for clues (string data, pointers, counters)
  • Synthesize a narrative: Combine register and memory observations into a coherent explanation of what the program did between the two snapshots. For example: "The program called function X, which allocated Y bytes on the stack and wrote a string to a heap buffer."

Present the analysis in a clear, structured format with the raw evidence (hex values, addresses) supporting each conclusion.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the State Diff AI skill do?

Compare two state snapshots to identify register and memory changes between two points in time

Why use State Diff on TypingMind?

Because you install it once and use it with any model. State Diff is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install State Diff in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/dariushoule/x64dbg-skills/tree/main/skills/state-diff. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use State Diff?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with State Diff?

As many as you like. As long as a model supports skills, you can use State Diff with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the State Diff AI skill free?

Yes. It is published on GitHub by dariushoule under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇