ClaudeForge

🥈Silver

ClaudeForge automates the creation and maintenance of CLAUDE.md files for Claude Code projects. It ensures alignment with Anthropic’s best practices, benefiting developers and operations teams. The tool connects to Python workflows and integrates with Claude agents.

342260Updated Today

Intermediate30min to implementautomation

Saves ~45 min per use

Quick InstallView Source

git clone https://github.com/alirezarezvani/ClaudeForge.git

Works with:

Claude

Overview

About This Skill

How to Use

1. **Install ClaudeForge**: Run `pip install claudeforge` in your project directory or use the Claude Code extension. 2. **Initialize Project**: Execute `claudeforge init --project-name "[PROJECT_NAME]"` in your terminal to generate a starter CLAUDE.md file. 3. **Customize Content**: Replace placeholders in the generated file with your actual project details (dependencies, commands, etc.). 4. **Validate Compliance**: Run `claudeforge validate` to check if your CLAUDE.md meets Anthropic's best practices for structure and content. 5. **Automate Updates**: Set up a GitHub Action using the `claudeforge update` command to automatically regenerate CLAUDE.md when dependencies change (e.g., in `requirements.txt` or `pyproject.toml`). Tip: Use `claudeforge diff` to compare your current CLAUDE.md against the latest Anthropic template before committing changes.

Setup & Installation

Quick Install

No install command available. Check the GitHub repository for manual installation instructions.

Alternative Install (Git Clone)

git clone https://github.com/alirezarezvani/ClaudeForge

Requirements

Claude Code or compatible AI agent
Works with: Claude

Quick Start Guide

Install the Skill

Copy the install command above and run it in your terminal.

Open Your AI Agent

Launch Claude Code, Cursor, or your preferred AI coding agent.

Try It Out

Use the prompt template or examples below to test the skill.

Customize

Adapt the skill to your specific use case and workflow.

Usage Examples

Prompt Template

Generate a CLAUDE.md file for the [PROJECT_NAME] repository following Anthropic's best practices. Include sections for: 1) Project Overview, 2) Key Dependencies, 3) Development Setup, 4) Common Commands, 5) Testing Guidelines, and 6) Deployment Notes. Use [PROJECT_DESCRIPTION] as the starting point. Ensure the file is compatible with Claude Code's context window and includes clear instructions for new contributors.

Example Output

```markdown
# CLAUDE.md - Project: `data-pipeline`

## Project Overview
A Python-based ETL pipeline that processes customer transaction data from S3, transforms it using PySpark, and loads it into Snowflake. Built with modular design for scalability and includes unit tests for data quality validation.

## Key Dependencies
- Python 3.10+
- PySpark 3.4.0
- Snowflake Connector 2.9.0
- Pandas 2.0.3
- pytest 7.4.2

## Development Setup
1. Clone repository: `git clone git@github.com:company/data-pipeline.git`
2. Create virtual environment: `python -m venv .venv`
3. Activate environment: `source .venv/bin/activate` (Linux/Mac) or `.venv\Scripts\activate` (Windows)
4. Install dependencies: `pip install -r requirements.txt`
5. Set environment variables in `.env` file:
   - `SNOWFLAKE_ACCOUNT=xy12345.us-east-2.aws`
   - `SNOWFLAKE_USER=etl_user`
   - `SNOWFLAKE_PASSWORD=secure_password_here`

## Common Commands
- Run pipeline: `python src/main.py --env prod --date 2024-01-15`
- Run tests: `pytest tests/ -v`
- Format code: `black src/ tests/`
- Lint code: `pylint src/`
- Generate docs: `sphinx-apidoc -o docs/ src/`

## Testing Guidelines
- All new features must include unit tests in `tests/unit/`
- Data quality tests must cover null values, duplicates, and schema validation
- Integration tests require Snowflake access and run nightly via GitHub Actions
- Test coverage must remain above 85% (verified via `pytest --cov=src`)

## Deployment Notes
- Production deployments occur every Wednesday at 2 AM UTC
- Rollback procedure: Revert to previous tag and notify #data-team Slack channel
- Monitor pipeline health via Grafana dashboard: `https://grafana.company.com/d/data-pipeline`
- Hotfixes require approval from Data Engineering Lead (Alice Chen)
```