OpenShift AI Test Generation System
You can install this plugin from any of these themed marketplaces. Choose one, add it as a marketplace, then install the plugin.
Choose your preferred installation method below
A marketplace is a collection of plugins. Every plugin gets an auto-generated marketplace JSON for individual installation, plus inclusion in category and themed collections. Add a marketplace once (step 1), then install any plugin from it (step 2).
One-time setup for access to all plugins
When to use: If you plan to install multiple plugins now or later
Step 1: Add the marketplace (one-time)
/plugin marketplace add https://claudepluginhub.com/marketplaces/all.jsonRun this once to access all plugins
Step 2: Install this plugin
/plugin install test-gen@allUse this plugin's auto-generated marketplace JSON for individual installation
When to use: If you only want to try this specific plugin
Step 1: Add this plugin's marketplace
/plugin marketplace add https://claudepluginhub.com/marketplaces/plugins/test-gen.jsonStep 2: Install the plugin
/plugin install test-gen@test-genAI-assisted test generation and execution system that automates the complete testing workflow:
This system uses multiple specialized agents to handle each phase of the testing process, ensuring consistent and thorough test coverage for OpenShift components.
Before you can use this test generation system, you need to set up the following integrations:
ONE-COMMAND INSTALLATION - The simplest way to share with your team:
claude plugin marketplace add YOUR_USERNAME/test-generation-assistant
That's it! The plugin is now available in Claude Code with all agents and workflows.
What's included:
Complete Guide: PLUGIN_INSTALLATION.md
Apply for jira-mcp-snowflake token: Refer to Jira-MCP-Snowflake-Token-Guide
Config jira-mcp-snowflake mcp server:
claude mcp add jira-mcp-snowflake https://jira-mcp-snowflake.mcp-playground-poc.devshift.net/sse --transport sse -H "X-Snowflake-Token: your_token_here"
claude mcp add -s user -t http deepwiki https://mcp.deepwiki.com/mcp
config/rules/# macOS
brew install gh
# Linux/Windows
# Follow: https://cli.github.com/manual/installation
Purpose: Configure environment variables for GitHub, JIRA, and OpenShift access
Quick Setup:
# Copy example environment file
cp .env.example .env
# Edit with your credentials
nano .env
Required Variables:
GITHUB_FORK_OWNER - Your GitHub username (for E2E test generation)JIRA_SERVER - JIRA server URL (default: https://issues.redhat.com)JIRA_TOKEN - Your JIRA authentication tokenFor E2E Testing:
KUBECONFIG - Path to your OpenShift cluster kubeconfigTEST_PLATFORM - Target platform (AWS, Azure, GCP, etc.)See: ENV_SETUP.md for detailed environment setup guide
CRITICAL: All agents must be executed by reading agent YAML configurations directly.
Execution Pattern:
CLAUDE.md (for Claude Code), GEMINI.md (for Gemini), or Cursor documentation (see Cursor Configuration in Prerequisites) for agent instructionsconfig/agents/test_case_generation.yaml)MANDATORY: The workflow orchestrator is the PRIMARY entry point for ALL test generation requests.
CRITICAL: Before executing ANY user request, AI MUST:
config/agents/workflow_orchestrator.yaml FIRSTA top-level agent that automatically:
Location: config/agents/workflow_orchestrator.yaml
Guide: config/agents/WORKFLOW_ORCHESTRATOR_GUIDE.md
When AI reads any configuration or guideline files:
The orchestrator automatically identifies your intent from natural language:
# Complete flow (3 agents executed automatically)
"Generate test cases and run them for HIVE-2883"
# Single agent via orchestrator
"Create test case for HIVE-2883"
# Regenerate mode (skips prerequisite checks)
"re-create e2e test for HIVE-2883"
See config/agents/WORKFLOW_ORCHESTRATOR_GUIDE.md for detailed usage instructions.
Purpose: Generate manual test cases from JIRA tickets
Agent Config: config/agents/test_case_generation.yaml
Input: JIRA issue key (e.g., "HIVE-2883")
Output:
test_requirements_output.yaml - Detailed requirements analysistest_strategy.yaml - Test strategy based on requirements{JIRA_KEY}_test_case.md - Executable test cases in markdown formatExample Usage:
"Create test case for HIVE-2883"
"Generate test case for JIRA issue HIVE-2883"
"Generate test cases and run them for HIVE-2883" # Full flow
Features:
Purpose: Generate E2E test code based on existing test cases
Agent Config: config/agents/e2e_test_generation_openshift_private.yaml
Output: E2E test code integrated into openshift-tests-private repository
Purpose: Execute generated E2E tests and capture results
Agent Config: config/agents/test-executor.yaml
Output: Test execution results and reports
Purpose: Create PR for generated E2E tests
Tools: Git, GitHub CLI (gh)
Output: Created pull request with E2E test code
Setup Prerequisites (see above sections):
Open Claude Code:
claude
Navigate to project directory:
cd /path/to/.ai_testgen
Execute agents directly:
# Generate test cases
"Create test case for HIVE-2883"
# Generate E2E code
"Generate E2E case for HIVE-2883"
# Execute E2E tests
"Run E2E tests for HIVE-2883"
# Complete end-to-end flow (executes all 3 agents in sequence)
"Generate test cases and run them for HIVE-2883"
# This automatically executes: test_case_generation → e2e_test_generation_openshift_private → test-executor
# Create PR
"Create PR for HIVE-2883 E2E tests"
# Add QE comment
"Add QE comment to HIVE-2883"
Setup Prerequisites (see above sections):
Open Cursor IDE:
cursor /path/to/ai_testgen
Use Cursor's AI Chat:
Execute agents directly:
# Generate test cases
"Create test case for HIVE-2883"
# Generate E2E code
"Generate E2E case for HIVE-2883"
# Execute E2E tests
"Run E2E tests for HIVE-2883"
# Complete end-to-end flow (executes all 3 agents in sequence)
"Generate test cases and run them for HIVE-2883"
# This automatically executes: test_case_generation → e2e_test_generation_openshift_private → test-executor
# Create PR
"Create PR for HIVE-2883 E2E tests"
# Add QE comment
"Add QE comment to HIVE-2883"
jira-mcp-snowflakeDeepWiki MCP1.0.0