DMtools Development Assistant

Comprehensive knowledge base for DMtools - an AI-powered development toolkit that integrates with multiple platforms and provides 96+ MCP tools for automation.

🔧 FIRST-TIME SETUP (DO THIS PROACTIVELY)

When a user mentions DMtools or asks to use it, IMMEDIATELY perform these checks:

🚀 Quick Automated Setup (Recommended)

Run the automated setup helper that checks and configures everything:

bash
1# Download and run setup helper
2curl -fsSL https://raw.githubusercontent.com/IstiN/dmtools/main/dmtools-ai-docs/setup-dmtools.sh | bash

This script will:

1. ✓ Check if DMtools is installed (and install if missing)
2. ✓ Create dmtools.env template if missing
3. ✓ Add dmtools files to .gitignore
4. ✓ Verify Java installation
5. ✓ Test DMtools functionality

OR follow manual steps below:

Step 1: Check if DMtools is installed

bash
1# Check if dmtools command is available
2which dmtools || echo "DMtools not installed"

If NOT installed:

bash
1# Offer to install DMtools automatically
2curl -fsSL https://raw.githubusercontent.com/IstiN/dmtools/main/install.sh | bash

Step 2: Check for dmtools.env configuration

bash
1# Check if dmtools.env exists in current directory or home
2ls dmtools.env ~/.dmtools.env 2>/dev/null || echo "No dmtools.env found"

If NOT found, help user create it:

1. Ask user which integrations they need (Jira, ADO, Figma, etc.)
2. Ask user which AI provider they want (Gemini free tier recommended)
3. Create dmtools.env with appropriate template (see Configuration Template below)
4. Add dmtools.env to .gitignore (contains secrets!)

Step 3: Verify .gitignore

bash
1# Check if dmtools files are in .gitignore
2grep -q "dmtools.env\|dmtools-local.env" .gitignore 2>/dev/null || echo "Not in .gitignore"

If NOT in .gitignore, add these lines:

gitignore
1# DMtools configuration (contains secrets)
2dmtools.env
3dmtools-local.env
4.dmtools/

Configuration Template

When creating dmtools.env, use this template and fill with user's credentials:

bash
1# dmtools.env - NEVER commit this file
2# Generated by DMtools skill assistant
3
4# ================================
5# INTEGRATIONS (choose what you need)
6# ================================
7
8# Jira (if user needs Jira)
9JIRA_BASE_PATH=https://your-company.atlassian.net
10JIRA_EMAIL=your-email@company.com
11JIRA_API_TOKEN=your-jira-api-token
12JIRA_AUTH_TYPE=Basic
13
14# Azure DevOps (if user needs ADO)
15# ADO_BASE_PATH=https://dev.azure.com/your-org
16# ADO_PAT_TOKEN=your-ado-pat-token
17
18# ================================
19# AI PROVIDER (required - choose one)
20# ================================
21
22# Gemini (RECOMMENDED - free tier available)
23GEMINI_API_KEY=your-gemini-api-key
24# Get free key: https://aistudio.google.com/app/apikey
25
26# OR OpenAI
27# OPENAI_API_KEY=your-openai-api-key
28
29# OR AWS Bedrock
30# BEDROCK_ACCESS_KEY_ID=your-aws-key
31# BEDROCK_SECRET_ACCESS_KEY=your-aws-secret
32
33# ================================
34# DEFAULTS
35# ================================
36DEFAULT_LLM=gemini
37DEFAULT_TRACKER=jira

Quick Links for API Tokens:

• Jira: https://id.atlassian.com/manage-profile/security/api-tokens
• Gemini: https://aistudio.google.com/app/apikey (FREE - 15 req/min)
• OpenAI: https://platform.openai.com/api-keys
• ADO: https://dev.azure.com → User Settings → Personal Access Tokens

Step 4: Test Installation

bash
1# Verify installation works
2dmtools list | head -5

When to Use

Use this skill when:

• Installing or configuring DMtools (do setup steps above first!)
• Setting up integrations (Jira, Azure DevOps, Figma, Confluence, Teams)
• Configuring AI providers (Gemini, OpenAI, Claude, DIAL, Ollama)
• Developing JavaScript agents with MCP tools
• Generating test cases (Jira, Xray, Cucumber)
• Generating analytics reports (ReportGenerator, dmc_report)
• Troubleshooting DMtools issues
• Working with dmtools.env configuration
• Creating AI teammate configurations
• Setting up CI/CD run tracing (ciRunUrl) for ticket traceability

Quick Reference

⚠️ IMPORTANT: If this is first time using DMtools, see FIRST-TIME SETUP section above.

Manual Installation Steps

If automated setup didn't work, follow these manual steps:

1. Install DMtools CLI

bash
1curl -fsSL https://raw.githubusercontent.com/IstiN/dmtools/main/install.sh | bash

2. Create dmtools.env

Create dmtools.env in project root (see template in FIRST-TIME SETUP section)

3. Add to .gitignore

bash
1echo -e "\n# DMtools configuration\ndmtools.env\ndmtools-local.env\n.dmtools/" >> .gitignore

4. Get API Tokens

• Jira: https://id.atlassian.com/manage-profile/security/api-tokens
• Gemini (FREE): https://aistudio.google.com/app/apikey
• OpenAI: https://platform.openai.com/api-keys

See Installation Guide for detailed setup.

Common Commands

bash
1dmtools list                          # List all 96+ MCP tools
2dmtools jira_get_ticket PROJ-123      # Get Jira ticket
3dmtools run agents/config.json        # Run configuration
4dmtools run agents/config.json --ciRunUrl "https://ci.example.com/runs/42"  # With CI tracing
5dmtools run agents/config.json "${ENCODED_CONFIG}" --inputJql "key=PROJ-1"  # With overrides

Core Capabilities

152+ MCP Tools Available

Complete Reference: references/mcp-tools/README.md - Auto-generated from actual DMtools build

Current breakdown (16 integrations):

• Jira (52 tools): Ticket management, search, comments, Xray test management
• Teams (30 tools): Messages, chats, files, transcripts, meetings
• Confluence (17 tools): Page management, search, content access, attachments
• ADO (14 tools): Azure DevOps work items, queries, comments, attachments
• Figma (12 tools): Design extraction, icons, layers, styles, components
• AI Providers (12 tools):
  • Gemini (2): Chat, multimodal
  • OpenAI (2): Chat, vision models with files
  • Anthropic (2): Claude chat
  • Bedrock (2): AWS Claude
  • DIAL (2): Enterprise AI
  • Ollama (2): Local models
• Knowledge Base (5 tools): Document search, indexing, RAG
• File (4 tools): File operations, read/write
• Mermaid (3 tools): Diagram generation
• SharePoint (2 tools): Document management
• CLI (1 tool): Command execution

Example tools:

• jira_get_ticket, jira_search_by_jql, jira_xray_create_test
• ado_get_work_item, ado_move_to_state, ado_add_comment
• figma_get_layers, figma_get_icons, figma_download_node_image
• teams_send_message, teams_messages_since, teams_download_file
• gemini_ai_chat, openai_ai_chat, openai_ai_chat_with_files, bedrock_ai_chat

JavaScript Agent Pattern

All MCP tools are directly accessible as JavaScript functions in agents:

javascript
1function action(params) {
2    try {
3        // Direct MCP tool access
4        const ticket = jira_get_ticket(params.ticketKey);
5        const analysis = gemini_ai_chat(`Analyze: ${ticket.fields.description}`);
6
7        // Process and return
8        return { success: true, result: analysis };
9    } catch (error) {
10        return { success: false, error: error.toString() };
11    }
12}

📚 Detailed Documentation

⚠️ CRITICAL: JSON Configuration "name" Field

Before using any job configuration, understand this:

The "name" field in JSON configs is NOT a user-defined name. It is a Java class name (technical identifier).

json
1{
2  "name": "TestCasesGenerator"  // ← Exact Java class name (immutable)
3}

• ✅ DO: Use exact name from docs: TestCasesGenerator, Teammate, Expert
• ❌ DON'T: Change it to "My Test Generator" or "test-generator"

Why? DMtools maps this name directly to Java code: "TestCasesGenerator" → new TestCasesGenerator()

See JSON Configuration Rules for details.

Common Tasks

Configure Jira Integration

bash
1# 1. Generate API token at https://id.atlassian.com/manage-profile/security/api-tokens
2# 2. Encode credentials
3echo -n "email@company.com:token" | base64
4# 3. Add to dmtools.env
5JIRA_BASE_PATH=https://company.atlassian.net
6JIRA_LOGIN_PASS_TOKEN=base64_output_here

Generate Test Cases

IMPORTANT: "name" must exactly match Job class name. See JSON Configuration Rules.

json
1{
2  "name": "TestCasesGenerator",
3  "params": {
4    "inputJql": "project = PROJ AND type = Story",
5    "testCasesPriorities": "High, Medium, Low",
6    "outputType": "creation",
7    "testCaseIssueType": "Test",
8    "existingTestCasesJql": "project = PROJ AND type = Test",
9    "isFindRelated": true,
10    "isGenerateNew": true
11  }
12}

Create JavaScript Agent

javascript
1// agents/js/processTickets.js
2function action(params) {
3    const tickets = jira_search_by_jql(params.jql);
4
5    for (const ticket of tickets) {
6        // Process with AI
7        const result = gemini_ai_chat(`Analyze: ${ticket.fields.summary}`);
8
9        // Update ticket
10        jira_post_comment(ticket.key, result);
11    }
12
13    return { processed: tickets.length };
14}

CI Run Tracing (GitHub Actions / Azure DevOps)

When running Expert, Teammate, or TestCasesGenerator from CI/CD, pass --ciRunUrl to link every ticket comment to the pipeline run.

The workflow ai-teammate.yml does this automatically — no extra config needed. For other pipelines:

bash
1# GitHub Actions
2CI_RUN_URL="${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}"
3dmtools run agents/teammate.json --ciRunUrl "${CI_RUN_URL}"
4
5# Azure DevOps
6CI_RUN_URL="$(System.TeamFoundationCollectionUri)$(System.TeamProject)/_build/results?buildId=$(Build.BuildId)"
7dmtools run agents/teammate.json --ciRunUrl "${CI_RUN_URL}"

What happens on the ticket:

1. Processing started. CI Run: https://... — posted immediately when the job picks up the ticket
2. Normal result comment posted when job finishes

CLI overrides — any --key value after the config file patches the params block:

bash
1# Override any param at runtime without editing the JSON
2dmtools run agents/config.json "${ENCODED_CONFIG}" --inputJql "key=PROJ-42" --ciRunUrl "${CI_RUN_URL}"

See CI Run Tracing and GitHub Actions for full details.

Integrate CLI Agents (Cursor, Claude, Copilot)

Use Case: Code generation with full workspace context

json
1{
2  "name": "Teammate",
3  "params": {
4    "agentParams": {
5      "aiRole": "Senior Software Engineer",
6      "instructions": ["Implement ticket from input/ folder"]
7    },
8    "cliCommands": [
9      "./cicd/scripts/run-cursor-agent.sh \"Read from input/, write to output/\""
10    ],
11    "skipAIProcessing": true,
12    "postJSAction": "agents/js/developTicketAndCreatePR.js",
13    "inputJql": "key = PROJ-123"
14  }
15}

Pattern: Teammate prepares context → CLI agent processes → Post-action creates PR

See CLI Integration Guide for complete examples.

Best Practices

1. Security: Never commit credentials - use environment variables
2. AI Provider: Start with Gemini (free tier, 15 req/min)
3. Testing: Mock external APIs with Mockito
4. Batch Processing: Add delays to avoid rate limits
5. Error Handling: Always use try-catch in agents

Troubleshooting Quick Reference

Architecture Notes

• Job System: 20+ specialized jobs for workflows
• Agent System: Java and JavaScript agents for AI tasks
• Configuration: Hierarchy - env vars > dmtools.env > dmtools-local.env
• Thread Safety: JobContext with thread-local storage
• DI Framework: Dagger 2 for dependency injection

Resources

• Repository: https://github.com/IstiN/dmtools
• MCP Tools Reference: https://github.com/IstiN/dmtools/blob/main/docs/README-MCP.md
• Issues: https://github.com/IstiN/dmtools/issues

🤖 AI Assistant Instructions

When to Trigger Setup Automatically

ALWAYS run setup checks when user:

• Mentions "dmtools" for the first time in conversation
• Asks to use any DMtools feature (Jira, test generation, etc.)
• Gets an error like "dmtools: command not found"
• Asks "how do I install dmtools"

Proactive Setup Pattern

markdown
1I see you want to use DMtools. Let me check if it's set up properly...
2
3[Run setup checks]
4
5Results:
6- ✓ DMtools installed
7- ✗ dmtools.env not found
8- ✗ Not in .gitignore
9
10I'll help you configure it. First, which integrations do you need?
111. Jira
122. Azure DevOps
133. Both
144. Other
15
16[Create appropriate dmtools.env template]
17[Add to .gitignore]
18[Guide user to get API tokens]

Example: Automated Setup Flow

bash
1# Step 1: Run automated setup
2curl -fsSL https://raw.githubusercontent.com/IstiN/dmtools/main/dmtools-ai-docs/setup-dmtools.sh | bash
3
4# Step 2: If dmtools.env needs credentials, guide user:
5# "I've created dmtools.env. You need to add your credentials:
6#  1. Jira API token: https://id.atlassian.com/manage-profile/security/api-tokens
7#  2. Gemini API key (FREE): https://aistudio.google.com/app/apikey
8#
9#  Would you like me to help you configure Jira or Gemini first?"
10
11# Step 3: Help user edit dmtools.env
12# Step 4: Test with: dmtools list

Configuration Templates

Keep these handy for quick setup:

Jira Only:

bash
1JIRA_BASE_PATH=https://company.atlassian.net
2JIRA_EMAIL=user@company.com
3JIRA_API_TOKEN=token_here
4JIRA_AUTH_TYPE=Basic
5GEMINI_API_KEY=key_here
6DEFAULT_LLM=gemini
7DEFAULT_TRACKER=jira

Azure DevOps Only:

bash
1ADO_BASE_PATH=https://dev.azure.com/org
2ADO_PAT_TOKEN=token_here
3GEMINI_API_KEY=key_here
4DEFAULT_LLM=gemini
5DEFAULT_TRACKER=ado

Both Jira + ADO:

bash
1JIRA_BASE_PATH=https://company.atlassian.net
2JIRA_EMAIL=user@company.com
3JIRA_API_TOKEN=jira_token
4JIRA_AUTH_TYPE=Basic
5ADO_BASE_PATH=https://dev.azure.com/org
6ADO_PAT_TOKEN=ado_token
7GEMINI_API_KEY=key_here
8DEFAULT_LLM=gemini
9DEFAULT_TRACKER=jira

Ask Questions

If you need clarification on requirements or implementation details, ask the user for more information before proceeding.