AI automation skill that provides production-ready templates and domain-specific skills for bootstrapping AI-assisted development projects with Claude Code integration. Benefits developers by accelerating project initialization and setup.
git clone https://github.com/martinholovsky/claude-skills-generator.gitClaude Skills Generator provides an interactive template repository system for rapidly initializing new development projects optimized for Claude Code integration. It includes 67+ domain-specific skills across frontend, backend, DevOps, security, and platform categories, plus production-ready templates for README, CI/CD workflows, and Claude Code configuration. The generator automates project setup through interactive scripts that handle project type selection, language choice, skill copying, template variable substitution, and Git initialization. Developers use it to accelerate project bootstrapping while establishing security-first development practices and AI-assisted workflows from inception.
1. **Install Claude Code**: Ensure you have the latest version of Claude Code installed in your development environment. 2. **Create Project Structure**: Run `claude new --skill project_name` to scaffold a new skill directory with proper structure. 3. **Paste the Generated Skill**: Copy the complete Python module from the AI output into your skill's main file (e.g., `claude_skills/skill_name.py`). 4. **Customize Placeholders**: Replace all [PLACEHOLDERS] with your actual project requirements (function names, error cases, data formats). 5. **Test in Claude**: Use the skill in Claude by running `skill project_name --help` or integrating it into your workflow with `claude run skill_name`. Tip: For complex skills, generate unit tests by asking the AI to create a corresponding test file using the same prompt template with `[TEST_FRAMEWORK]` placeholder.
Initialize full-stack web applications with pre-configured Claude Code workflows and CI/CD templates
Scaffold backend APIs with FastAPI, GraphQL, or REST patterns and relevant security skills
Create desktop applications using Tauri with cross-platform build and auto-update configurations
Set up CLI tools or libraries with language-specific templates and contribution guidelines
No install command available. Check the GitHub repository for manual installation instructions.
git clone https://github.com/martinholovsky/claude-skills-generatorCopy the install command above and run it in your terminal.
Launch Claude Code, Cursor, or your preferred AI coding agent.
Use the prompt template or examples below to test the skill.
Adapt the skill to your specific use case and workflow.
Generate a production-ready Claude Code skill for [PROJECT_NAME] that handles [SPECIFIC_TASK]. Include: 1) A Python function with type hints, 2) Error handling for [COMMON_ERROR_CASES], 3) Logging setup with [LOG_LEVEL], and 4) A CLI interface using [CLICK/ARGUNAUT]. Structure the output as a complete Python module with a README snippet showing usage examples. Use [MOCK_DATA] for demonstration purposes.
```python
# File: claude_skills/claude_skill_project_name.py
import logging
from typing import Optional
import click
from pathlib import Path
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)
def process_data(input_path: Path, output_path: Path, batch_size: int = 100) -> dict:
"""
Process data from input_path and write results to output_path.
Args:
input_path: Path to input CSV file
output_path: Path to save processed JSON results
batch_size: Number of rows to process at once
Returns:
Dictionary with processing statistics
Raises:
FileNotFoundError: If input file doesn't exist
ValueError: If batch_size is invalid
"""
if not input_path.exists():
raise FileNotFoundError(f"Input file not found: {input_path}")
if batch_size <= 0:
raise ValueError("batch_size must be positive")
results = {"processed": 0, "errors": 0, "skipped": []}
try:
with input_path.open('r') as f:
# Mock processing - replace with actual logic
for i, line in enumerate(f):
if i % batch_size == 0:
logger.info(f"Processing batch {i//batch_size + 1}")
# Simulate processing
if "error" in line.lower():
results["errors"] += 1
results["skipped"].append(i)
else:
results["processed"] += 1
# Save mock results
output_path.write_text(str(results))
logger.info(f"Processing complete. Results saved to {output_path}")
except Exception as e:
logger.error(f"Processing failed: {str(e)}")
raise
return results
@click.command()
@click.argument('input_path', type=click.Path(exists=True))
@click.argument('output_path', type=click.Path())
@click.option('--batch-size', default=100, help='Number of rows to process at once')
def main(input_path: str, output_path: str, batch_size: int):
"""CLI interface for data processing skill."""
try:
stats = process_data(
input_path=Path(input_path),
output_path=Path(output_path),
batch_size=batch_size
)
click.echo(f"Processing complete. Stats: {stats}")
except Exception as e:
click.echo(f"Error: {str(e)}", err=True)
raise SystemExit(1)
if __name__ == '__main__':
main()
```
```markdown
# README Snippet
## Usage
```bash
# Basic usage
claude_skill_project_name.py data/input.csv results/output.json
# With custom batch size
claude_skill_project_name.py data/input.csv results/output.json --batch-size 200
```
## Mock Data Example
Input file contains:
```csv
id,name,status
1,Alice,active
2,Bob,error
3,Charlie,active
4,David,error
```
Expected output:
```json
{"processed": 2, "errors": 2, "skipped": [1, 3]}
```Your one-stop shop for church and ministry supplies.
AI assistant built for thoughtful, nuanced conversation
Automate your browser workflows effortlessly
IronCalc is a spreadsheet engine and ecosystem
Enterprise workflow automation and service management platform
Automate your spreadsheet tasks with AI power
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan