README Generator

Write a README from a project description, with installation, usage, API and contributing sections.

Pay by wallet (x402) AI-generated readme-generate

Example

Example answer
{
  "markdown": "# Automated Capability Testing Project\n\n## Overview\n\nThis project is designed to test and validate automated capabilities through comprehensive testing frameworks and protocols. It serves as a foundation for capability assessment and quality assurance in automated systems.\n\n## Features\n\n- Automated test execution and validation\n- Comprehensive capability assessment\n- Detailed reporting and metrics\n- Modular and extensible architecture\n- CI/CD integration support\n\n## Installation\n\n### Prerequisites\n\n- Python 3.8 or higher\n- pip package manager\n- Git\n\n### Setup Instructions\n\n1. Clone the repository:\n```bash\ngit clone https://github.com/yourusername/automated-capability-testing.git\ncd automated-capability-testing\n```\n\n2. Create a virtual environment:\n```bash\npython -m venv venv\nsource venv/bin/activate  # On Windows: venv\\Scripts\\activate\n```\n\n3. Install dependencies:\n```bash\npip install -r requirements.txt\n```\n\n## Usage\n\n### Basic Usage\n\n```bash\npython main.py --test all\n```\n\n### Running Specific Tests\n\n```bash\npython main.py --test unit\npython main.py --test integration\npython main.py --test capability\n```\n\n### Configuration\n\nEdit `config.yaml` to customize test parameters:\n\n```yaml\ntest_mode: automated\ntimeout: 300\nverbose: true\nreport_format: json\n```\n\n### Examples\n\n```bash\n# Run all tests with verbose output\npython main.py --test all --verbose\n\n# Generate HTML report\npython main.py --test all --report html\n\n# Run with custom configuration\npython main.py --config custom_config.yaml\n```\n\n## API Documentation\n\n### Core Functions\n\n#### `run_capability_test(test_name, timeout=300)`\n\nExecutes a capability test with specified parameters.\n\n**Parameters:**\n- `test_name` (str): Name of the test to execute\n- `timeout` (int): Maximum execution time in seconds\n\n**Returns:**\n- `TestResult`: Object containing test results and metrics\n\n**Example:**\n```python\nfrom capability_tester import run_capability_test\n\nresult = run_capability_test('authentication', timeout=60)\nprint(result.status)\nprint(result.metrics)\n```\n\n#### `TestRunner` Class\n\n```python\nfrom capability_tester import TestRunner\n\nrunner = TestRunner(config_path='config.yaml')\nresults = runner.run_all_tests()\nrunner.generate_report(format='json')\n```\n\n### Response Format\n\n```json\n{\n  \"test_name\": \"string\",\n  \"status\": \"PASSED|FAILED|SKIPPED\",\n  \"duration\": \"number (seconds)\",\n  \"metrics\": {\n    \"execution_time\": \"number\",\n    \"memory_usage\": \"number\",\n    \"success_rate\": \"number\"\n  },\n  \"details\": \"string\"\n}\n```\n\n## Contributing\n\nWe welcome contributions to this project! Please follow the guidelines below.\n\n### Getting Started\n\n1. Fork the repository\n2. Create a feature branch:\n```bash\ngit checkout -b feature/your-feature-name\n```\n\n3. Make your changes and commit:\n```bash\ngit commit -m 'Add your feature description'\n```\n\n4. Push to the branch:\n```bash\ngit push origin feature/your-feature-name\n```\n\n5. Open a Pull Request\n\n### Code Standards\n\n- Follow PEP 8 style guidelines\n- Write unit tests for new features\n- Maintain minimum 80% code coverage\n- Update documentation accordingly\n\n### Testing Requirements\n\n```bash\n# Run tests\npytest tests/ -v\n\n# Check code coverage\npytest tests/ --cov=src\n\n# Lint code\npylint src/\n```\n\n### Pull Request Process\n\n1. Update README.md with relevant changes\n2. Ensure all tests pass\n3. Add/update documentation\n4. Request review from maintainers\n\n## License\n\nThis project is licensed under the MIT License - see the LICENSE file for details.\n\n## Support\n\nFor issues and questions, please open an issue on the GitHub repository.\n\n## Authors\n\n- Project Team\n\n## Changelog\n\n### Version 1.0.0\n- Initial release\n- Core testing framework\n- Basic capability assessment\n- Report generation\n",
  "sections": [
    "Overview",
    "Features",
    "Installation",
    "Usage",
    "API Documentation",
    "Contributing",
    "License",
    "Support",
    "Authors",
    "Changelog"
  ],
  "has_usage": true,
  "has_api_docs": true,
  "badges_suggested": [
    "[![Python 3.8+](https://img.shields.io/badge/python-3.8+-blue.svg)](https://www.python.org/downloads/)",
    "[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)",
    "[![Build Status](https://img.shields.io/badge/build-passing-brightgreen.svg)](https://github.com)",
    "[![Code Coverage](https://img.shields.io/badge/coverage-80%25-brightgreen.svg)](https://codecov.io)",
    "[![Contributions Welcome](https://img.shields.io/badge/contributions-welcome-brightgreen.svg)](CONTRIBUTING.md)"
  ],
  "has_contributing": true,
  "has_installation": true
}

Inputs

FieldTypeRequiredWhat it is
tech_stackstringNo—
project_namestringNo—
project_descriptionstringYes—

Output fields

How reliably each field appears in a successful answer.

FieldTypeAppears
markdownstringAlways (present in every successful answer)
sectionsarrayAlways (present in every successful answer)
has_usagebooleanAlways (present in every successful answer)
has_installationbooleanAlways (present in every successful answer)

How to call it

The same tool through each route. MCP clients reach it through Strale’s server at https://api.strale.io/mcp; the call below is what the agent sends.

# Needs an API key. max_price_cents caps what this call may cost.
curl -X POST https://api.strale.io/v1/do \
  -H "Authorization: Bearer $STRALE_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "capability_slug": "readme-generate",
    "inputs": {
      "project_description": "This is a test input for automated capability testing."
    },
    "max_price_cents": 5
  }'

Limitations

  • Generated setup instructions can be inaccurate

    AI-generated README from project context — installation steps and configuration details may not reflect your actual setup process

    What to do instead: Verify all command examples and installation steps in a clean environment before publishing

  • Output size cap per call

    Structured output is limited to about 8000 output tokens per call; requests exceeding this limit are refused rather than returned truncated. Requests with large results can exceed this limit, and repeating the same request does not help.

    What to do instead: Retry with a smaller or more focused request — a shorter project_description