# Code Assist

> Use this tool when you need to automate code modification and generation tasks, such as refactoring, maintenance, or integrating AI-driven code generation into existing projects. It provides a standardized XML-based interface for instructing code changes, accepting inputs like modification instructions and code files, and producing outputs like modified code files and version control updates. Ideal for use cases where AI assistants require complex code editing capabilities without needing to handle file system operations or version control complexities.

Canonical page: https://skillsregistry.net/skills/abhishekbhakat-code-assist  
JSON: https://api.skillsregistry.net/v1/skills/abhishekbhakat-code-assist

## Description

This MCP server implementation, developed for code modification and generation tasks, provides a set of tools for AI assistants to create, modify, delete, and rewrite code files. Built with Python and leveraging libraries like aiofiles, gitpython, and xmlschema, it offers a standardized XML-based interface for instructing code changes. The implementation focuses on file operations, search-and-replace modifications, and version control integration, making it accessible for AI models to perform complex code editing tasks. It's particularly useful for automated code refactoring, codebase maintenance, or integrating AI-driven code generation into existing projects, allowing assistants to manipulate code without requiring deep knowledge of file system operations or version control complexities.

## Trust

- **Trust score (0–1):** 0.96
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** version-control
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/abhishekbhakat-code-assist)
- **Repository:** <https://github.com/abhishekbhakat/mcp_server_code_assist>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "abhishekbhakat-code-assist"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/abhishekbhakat-code-assist` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/abhishekbhakat-code-assist/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt