Code2Config banner
the-very-pulse-of-that-machine the-very-pulse-of-that-machine

Code2Config

Development community

Description

A Claude Code skill for turning a codebase to an interactive parameter tuning interface for non-technical vibe coders.

Installation

This entry records only its repository, not the path inside it, so there is no exact command to give. Open the source below and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

README

Code2Config

**Automated parameter extraction and real-time visualization suite.**

**Code2Config** is a refactoring tool designed for developers who build with AI. It identifies scattered hard-coded constants, refactors them into a unified dynamic configuration interface, and deploys a local web dashboard for real-time parameter tuning.


👁️ What the OUTPUT looks like

**Your code, visualized.** The tool analyzes your codebase and transforms abstract variables into an **interactive dashboard**.

  • Auto-Discovery: It finds your "magic numbers" and builds the UI for them.
  • Semantic Sync: Each UI component is labeled based on the variable's actual function in your project.
  • Live Link: Any adjustment on the dashboard propagates directly back into your program files.

![html](/asset/html.png)


🚀 Quick Start

1. Triggering the Tool

In your AI-integrated terminal (e.g., Claude Code, Cursor), use the keyword:

**UseCode2Config**

Or provide a prompt:

*"I need to visually tune the parameters of this project."*

2. Execution Steps

  1. Backup: Always back up your project folder before starting the refactoring.
  2. Automated Workflow: The AI will execute Phase 1 (Analysis), Phase 2 (Injection), and Phase 3 (Deployment) sequentially.
  3. Launch Dashboard:
    python ui_bridge.py
    Frontend of dashboard will be launched at 127.0.0.1:8000 if default

🧠 Design Philosophy:

We believe that **tuning a system should be as intuitive as playing an instrument.** Most codebases are black boxes where logic and parameters are tangled together. Code2Config acts as a dictionary of all members of a project, where you get concise explanation as well as fast manipulation

The Three-Stage Process (Our Pipeline):

  1. Extraction (De-coding): Instead of just searching for numbers, we perform a Semantic Scan performed by agent. We identify which constants actually drive your system's behavior and t