Rev Symbol logo

Rev Symbol

CommunityPopular
P4nda0s
rev-symbol

Restore function symbols by analyzing code patterns, strings, constants, and cross-references

Overview

PublisherP4nda0s
Repositoryreverse-skills
Skill namerev-symbol
Stars
2.1K
Forks
268
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by P4nda0s on GitHub. Read the source before you install it.

Installation

Install the Rev Symbol 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.
  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/P4nda0s/reverse-skills.git /tmp/reverse-skills
mkdir -p .claude/skills
cp -r /tmp/reverse-skills/skills/rev-symbol .claude/skills/rev-symbol
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Rev Symbol 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 Rev Symbol 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 Rev Symbol 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.

rev-symbol - Symbol Recovery

Analyze function code characteristics to recover/identify function symbols and names.

Pre-check

Determine which IDA access method is available:

Option A — IDA Pro MCP (preferred if connected): Check if the IDA Pro MCP server is connected (look for an active ida-pro or equivalent MCP connection). If connected, you can query IDA directly via MCP tools — no exported files needed. Proceed with the analysis using MCP.

Option B — IDA-NO-MCP exported data: If MCP is not connected, check if IDA-NO-MCP exported data exists in the current directory:

  1. Check if decompile/ directory exists
  2. Check if there are .c files inside

If neither MCP nor exported data is available, prompt the user:

No IDA access method detected. Choose one of the following:

Option A — IDA Pro MCP (recommended):
  Connect the IDA Pro MCP server so Claude can query IDA directly.

Option B — IDA-NO-MCP export:
  1. Download plugin: https://github.com/P4nda0s/IDA-NO-MCP
  2. Copy INP.py to IDA plugins directory
  3. Press Ctrl-Shift-E in IDA to export
  4. Open the exported directory with Claude Code

Export Directory Structure

./
├── decompile/              # Decompiled C code directory
│   ├── 0x401000.c          # One file per function, named by hex address
│   ├── 0x401234.c
│   └── ...
├── decompile_failed.txt    # Failed decompilation list
├── decompile_skipped.txt   # Skipped functions list
├── strings.txt             # String table (address, length, type, content)
├── imports.txt             # Import table (address:function_name)
├── exports.txt             # Export table (address:function_name)
└── memory/                 # Memory hexdump (1MB chunks)

Function File Format (decompile/*.c)

Each .c file contains function metadata comments and decompiled code:

c
/*
 * func-name: sub_401000
 * func-address: 0x401000
 * callers: 0x402000, 0x403000    // List of functions that call this function
 * callees: 0x404000, 0x405000    // List of functions called by this function
 */

int __fastcall sub_401000(int a1, int a2)
{
    // Decompiled code...
}

Symbol Recovery Steps

Step 1: Analyze Internal Characteristics

Carefully examine the target function for:

  • String constants: Strings used in the function may reveal its purpose
  • Numeric constants / Magic Numbers:
    • MD5: 0x67452301, 0xEFCDAB89, 0x98BADCFE, 0x10325476
    • CRC32: 0xEDB88320
    • Base64 charset: ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/
    • AES S-Box: 0x63, 0x7C, 0x77, 0x7B...
    • Zlib: 0x78, 0x9C (compression header)
    • other constants/magic numbers...
  • Code structure: Loop patterns, bitwise operations, specific algorithm flows

If you can identify a known algorithm through constants/structure, tell the user directly.

Step 2: Analyze Cross-References

Analyze Callees (called functions):

  • Read functions in the callees list

  • For each callee, check if its address exists in imports.txt

  • Recognize call patterns even when symbols are missing:

    Paired function patterns (identify by matching call pairs):

    c
    // malloc/free, new/delete, alloc/dealloc
    xx = sub_A(0x100);        // alloc: takes size, returns pointer
    ...
    sub_B(xx);                // free: takes the same pointer
    
    // mutex_lock/mutex_unlock, pthread_mutex_lock/unlock
    sub_A(lock_ptr);          // lock
    ...                       // critical section
    sub_B(lock_ptr);          // unlock (same lock object)
    
    // open/close, fopen/fclose, CreateFile/CloseHandle
    fd = sub_A("/path", 0);   // open: path + flags, returns handle
    ...
    sub_B(fd);                // close: takes the handle
    
    // pthread_create/pthread_join
    sub_A(&tid, 0, func, arg); // create: out param, attr, func, arg
    ...
    sub_B(tid, &ret);          // join: tid, out param
    
    
    **Argument pattern recognition:**
    ```c
    // socket(AF_INET, SOCK_STREAM, 0) - fixed constants
    sub_XXX(2, 1, 0);         // socket: domain=2, type=1, protocol=0
    
    // connect/bind(sockfd, addr, addrlen)
    sub_XXX(fd, &var, 16);   // addr struct, len=16 for IPv4
    
    // memcpy/memmove(dst, src, size)
    sub_XXX(dst, src, n);     // 3 params: dst, src, count
    
    // memset(ptr, value, size)
    sub_XXX(ptr, 0, 0x100);   // 3 params: ptr, byte value, count
    
    // read/write(fd, buf, count)
    ret = sub_XXX(fd, buf, n); // returns bytes read/written
    
    // strcmp/strncmp(s1, s2) or (s1, s2, n)
    if (sub_XXX(s1, s2) == 0)  // returns 0 on equal

    Return value patterns:

    c
    // file/socket operations: -1 on error
    if ((fd = sub_XXX(...)) == -1) goto error;
    
    // allocation: NULL on failure
    if (!(ptr = sub_XXX(size))) goto error;
    
    // success/error: 0 = success
    if (sub_XXX(...) != 0) goto error;
    
    // strlen: returns size_t
    len = sub_XXX(str);
    sub_YYY(dst, src, len);   // len used in memcpy

Analyze Callers (calling functions):

  • Read functions in the callers list
  • If a caller has a symbol (check exports.txt), infer the callee's purpose from context
  • Recursive check: trace up the call chain until you find a function with a symbol
  • Analyze how the return value is used by callers

Step 3: Information Gathering and Search

Collect the following information:

  • Strings in the function (check strings.txt for addresses used in the function)
  • Magic Numbers / constants
  • Known imports called (cross-reference callees with imports.txt)
  • Caller/callee symbols from exports.txt
  • Paired function patterns identified

Based on collected information:

  1. First attempt local reasoning based on:

    • Function signature (number and types of parameters)
    • Paired call patterns (alloc/free, lock/unlock)
    • Known imports in the call chain
    • Code structure similarity to known algorithms
  2. If uncertain, use Web Search to search:

    • Search Magic Numbers: 0x67452301 0xEFCDAB89 algorithm
    • Search code patterns: rotate left xor constant algorithm
    • Search unique strings found in the function
    • Search parameter patterns: function(int, int, 0) socket

Output Format

## Symbol Recovery Analysis: <function_address>

### Function Characteristics
- Strings: <list discovered strings>
- Constants: <list key constants>
- Called imports: <list>

### Cross-Reference Analysis
- Callers: <callers and their symbols>
- Callees: <callees and their symbols>

### Inference Result
- **Suggested symbol name**: <suggested_name>
- **Confidence**: High / Medium / Low
- **Reasoning**: <explain why this name is suggested>

### Similar Open Source Implementation
- <if similar open source code is found, provide link>

Frequently asked questions

What does the Rev Symbol AI skill do?

Restore function symbols by analyzing code patterns, strings, constants, and cross-references

Why use Rev Symbol on TypingMind?

Because you install it once and use it with any model. Rev Symbol 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 Rev Symbol in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/P4nda0s/reverse-skills/tree/main/skills/rev-symbol. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Rev Symbol?

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 Rev Symbol?

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

Is the Rev Symbol AI skill free?

It is published on GitHub by P4nda0s. Check the repository for licensing terms. 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 👇