Skip to main content

Installer for GSI-Protocol workflow commands (Claude Code & Codex)

Project description

GSI-Protocol

Specification-Driven Development (SDD) Workflow for AI-powered Development

License: MIT Python Version Version

Language: English | 繁體中文

GSI-Protocol is an automated Specification-Driven Development (SDD) workflow system that transforms user requirements into production-ready code through a structured 4-phase process: Specification → Architecture → Implementation → Verification.

Features

  • Multi-Platform Support: Works with Claude Code, Codex (OpenAI), and GitHub Copilot
  • Language Agnostic: Architecture design independent of programming language
  • Automated Workflow: Execute complete development cycle with a single command
  • BDD Integration: Built-in support for Gherkin specifications and integration tests
  • Project-Aware: Automatically detects and adapts to your project's tech stack
  • Role-Based Phases: PM → Architect → Engineer → QA workflow

📚 Learn More

New to GSI-Protocol? Start here:

Quick Start

Installation

Install using uvx (recommended):

uvx --from gsi-protocol-installer gsi-install

Or using pipx:

pipx run gsi-protocol-installer

The installer will guide you through:

  1. Selecting AI platform(s) (Claude Code, Codex, GitHub Copilot)
  2. Choosing installation type (global or project-specific)
  3. Installing workflow commands

Basic Usage

Automatic Mode (Recommended)

Execute the complete 4-phase workflow automatically:

# For Claude Code / Codex
/sdd-auto <your requirement>

# For GitHub Copilot
@workspace /sdd-auto <your requirement>

Example:

/sdd-auto Add user authentication with email and password

Manual Mode

For more control over each phase:

  1. Generate Specification (PM Phase)

    /sdd-spec <requirement>
    
  2. Design Architecture (Architect Phase)

    /sdd-arch <feature_file_path>
    
  3. Implement Code (Engineer Phase)

    /sdd-impl <feature_file_path>
    
  4. Verify Implementation (QA Phase)

    /sdd-verify <feature_file_path>
    
  5. Generate Unit Test Scaffolds (Optional)

    /sdd-unit-test <feature_file_path>
    
  6. Generate Integration Tests (Optional)

    /sdd-integration-test <feature_file_path>
    

Workflow Overview

The GSI-Protocol follows a structured 4-phase process:

User Requirement
      ↓
[Phase 1: Specification (PM)]
   → features/{feature}.feature (Gherkin)
      ↓
[Phase 2: Architecture (Architect)]
   → docs/features/{feature}/architecture.md
      ↓
[Phase 3: Implementation (Engineer)]
   → Source code files
      ↓
[Phase 4: Verification (QA)]
   → docs/features/{feature}/conclusion.md

Learn the methodology: Read our GSI Theory & Methodology guide to understand how Gherkin (specification), Structure (architecture), and Implement (code) work together.

Available Commands

Command Description Phase
/sdd-auto Execute complete workflow automatically All
/sdd-spec Generate Gherkin specification from requirements 1
/sdd-arch Design architecture from specification 2
/sdd-impl Implement code based on architecture 3
/sdd-verify Verify implementation against spec 4
/sdd-unit-test Generate unit test scaffolds with test strategy analysis Optional
/sdd-integration-test Generate BDD integration tests Optional

Output Structure

After running the workflow, your project will have:

project_root/
├── features/
│   └── {feature_name}.feature          # Gherkin specifications
├── docs/
│   └── features/
│       └── {feature_name}/
│           ├── architecture.md         # Architecture design
│           └── conclusion.md           # Verification report
└── {your_project_structure}/
    ├── {model_files}                   # Generated models
    └── {service_files}                 # Generated services

Platform-Specific Usage

Claude Code

Commands are available directly in Claude Code CLI:

/sdd-auto <requirement>
/sdd-spec <requirement>

Codex (OpenAI)

Use prompts with argument placeholders:

/sdd-auto <requirement>

GitHub Copilot

Prefix commands with @workspace:

@workspace /sdd-auto <requirement>
@workspace /sdd-spec <requirement>

Requirements

  • Python 3.10 or higher
  • Git
  • One of the supported AI platforms:
    • Claude Code CLI
    • Codex (OpenAI)
    • GitHub Copilot

Documentation

For detailed documentation, see the docs directory:

Contributing

Contributions are welcome! Please feel free to submit issues and pull requests.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Author

James Hsueh - asdfg55887@gmail.com

Links

Changelog

See version history and updates in the project repository.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

gsi_protocol_installer-1.2.0.tar.gz (8.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

gsi_protocol_installer-1.2.0-py3-none-any.whl (8.6 kB view details)

Uploaded Python 3

File details

Details for the file gsi_protocol_installer-1.2.0.tar.gz.

File metadata

  • Download URL: gsi_protocol_installer-1.2.0.tar.gz
  • Upload date:
  • Size: 8.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for gsi_protocol_installer-1.2.0.tar.gz
Algorithm Hash digest
SHA256 8600d186f1f63042d04dc7100ff0fdb4be1339e41ad3e9a15e70eeefc45c3ac5
MD5 a123b96e4bd02b2a04d3f28abaf88459
BLAKE2b-256 51f4aeac1f452dc1be506468f74deef962df2840a00134023f7fae81eafb9101

See more details on using hashes here.

Provenance

The following attestation bundles were made for gsi_protocol_installer-1.2.0.tar.gz:

Publisher: publish-to-pypi.yml on CodeMachine0121/GSI-Protocol

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file gsi_protocol_installer-1.2.0-py3-none-any.whl.

File metadata

File hashes

Hashes for gsi_protocol_installer-1.2.0-py3-none-any.whl
Algorithm Hash digest
SHA256 ae1025169156b98c6900a2d0fa1e6017c99a7631ab3c65a25f37e3c32b31cfba
MD5 f9c34ac3cb29d248bc1dcd4981764c7c
BLAKE2b-256 24d3d2824b91d42f552fdaae8849f8f326114f9e428dd070cd861a46176eb385

See more details on using hashes here.

Provenance

The following attestation bundles were made for gsi_protocol_installer-1.2.0-py3-none-any.whl:

Publisher: publish-to-pypi.yml on CodeMachine0121/GSI-Protocol

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page