@vfarcic/dot-ai 0.99.0 → 0.101.0

package/README.md

@@ -8,6 +8,7 @@
 
 DevOps AI Toolkit is an AI-powered development productivity platform that enhances software development workflows through intelligent automation and AI-driven assistance.
 
+📚 [Quick Start](./docs/quick-start.md) | 🔧 [MCP Setup](./docs/mcp-setup.md) | 🛠️ [Features & Tools](./docs/mcp-tools-overview.md)
 
 ## Who is this for?
 
@@ -44,6 +45,8 @@ DevOps AI Toolkit is an AI-powered development productivity platform that enhanc
 🔧 **Operator-Aware**: Leverages custom operators and CRDs when available  
 🚀 **Complete Workflow**: From discovery to deployment with automated Kubernetes integration
 
+📖 [Learn more →](./docs/mcp-recommendation-guide.md)
+
 #### Capability-Enhanced Recommendations
 Transform how AI understands your cluster by discovering semantic capabilities of each resource:
 
@@ -65,7 +68,7 @@ AI: Gets pre-filtered relevant resources with rich context
 Result: Finds sqls.devopstoolkit.live as perfect match ✨
 ```
 
-**Get Started**: See the [Tools and Features Overview](./docs/mcp-tools-overview.md) for complete guide to all available tools including capability management, deployment recommendations, and workflow integration.
+📖 [Learn more →](./docs/mcp-capability-management-guide.md)
 
 ### Kubernetes Issue Remediation
 🔍 **AI-Powered Root Cause Analysis**: Multi-step investigation loop identifies the real cause behind Kubernetes failures  
@@ -74,18 +77,24 @@ Result: Finds sqls.devopstoolkit.live as perfect match ✨
 🔒 **Safety Mechanisms**: Automatic fallback to manual mode when validation discovers additional issues  
 🎯 **Cross-Resource Intelligence**: Understands how pod issues may require fixes in different resource types (storage, networking, etc.)
 
+📖 [Learn more →](./docs/mcp-remediate-guide.md)
+
 ### Documentation Testing & Validation
 📖 **Automated Testing**: Validates documentation by executing commands and testing examples  
 🔍 **Two-Phase Validation**: Tests both functionality (does it work?) and semantic accuracy (are descriptions truthful?)  
 🛠️ **Fix Application**: User-driven selection and application of recommended documentation improvements  
 💾 **Session Management**: Resumable testing workflows for large documentation sets
 
+📖 [Learn more →](./docs/mcp-documentation-testing-guide.md)
+
 ### Organizational Pattern Management
 🏛️ **Pattern Creation**: Define organizational deployment patterns that capture institutional knowledge  
 🧠 **AI Enhancement**: Patterns automatically enhance deployment recommendations with organizational context  
 🔍 **Semantic Search**: Uses Vector DB (Qdrant) for intelligent pattern matching based on user intent  
 📋 **Best Practices**: Share deployment standards across teams through reusable patterns
 
+📖 [Learn more →](./docs/pattern-management-guide.md)
+
 ### Policy Management & Governance
 🛡️ **Policy Creation**: Define governance policies that guide users toward compliant configurations  
 ⚠️ **Compliance Integration**: Policies create required questions with compliance indicators during deployment  
@@ -93,245 +102,37 @@ Result: Finds sqls.devopstoolkit.live as perfect match ✨
 🎯 **Proactive Governance**: Prevents configuration drift by embedding compliance into the recommendation workflow  
 🔍 **Vector Storage**: Uses Qdrant Vector DB for semantic policy matching and retrieval
 
+📖 [Learn more →](./docs/policy-management-guide.md)
+
 ### Shared Prompts Library
 🎯 **Native Slash Commands**: Prompts appear as `/dot-ai:prompt-name` in your coding agent  
 📚 **Curated Library**: Access proven prompts for code review, documentation, architecture, and project management  
 🔄 **Zero Setup**: Connect to MCP server and prompts are immediately available across all projects  
 🤝 **Team Consistency**: Standardized prompt usage with centralized management
 
+📖 [Learn more →](./docs/mcp-prompts-guide.md)
+
 ### AI Integration
 ⚡ **MCP Integration**: Works seamlessly with Claude Code, Cursor, or VS Code through Model Context Protocol  
 🤖 **Conversational Interface**: Natural language interaction for deployment, documentation testing, pattern management, and shared prompt workflows
 
 **Setup Required**: See the [MCP Setup Guide](./docs/mcp-setup.md) for complete configuration instructions.
 
+---
+🚀 **Ready to deploy?** Jump to the [Quick Start](./docs/quick-start.md) guide to begin using DevOps AI Toolkit.
+---
+
 ## See It In Action
 
 [![DevOps AI Toolkit: AI-Powered Application Deployment](https://img.youtube.com/vi/8Yzn-9qQpQI/maxresdefault.jpg)](https://youtu.be/8Yzn-9qQpQI)
 
 This video explains the platform engineering problem and demonstrates the Kubernetes deployment recommendation workflow from intent to running applications.
 
-## Quick Start
-
-### Prerequisites
-
-**For Kubernetes deployment and documentation testing:**
-- **Claude API key** (required for AI analysis)
-  - Get your API key from [Anthropic Console](https://console.anthropic.com/) (requires account login)
-  <!-- dotai-ignore: Console URL may return 403 - expected behavior for auth-protected endpoint -->
-  - Set it as environment variable: `export ANTHROPIC_API_KEY=your_api_key_here`
-
-**For shared prompts library:**
-- **No API key required** - Works with any MCP-enabled coding agent (other features like deployments do require ANTHROPIC_API_KEY)
-
-**For Kubernetes deployment recommendations:**
-- **kubectl** configured with cluster access
-  - Verify cluster access with: `kubectl get nodes`
-  - Should show your cluster nodes without authentication errors
-<!-- dotai-ignore: kubectl verification command output format - implementation-specific -->
-
-**For documentation testing:**
-- **Documentation files** to test (Markdown, HTML, etc.)
-- **File system access** to the documentation you want to validate
-
-**For organizational pattern management:**
-- **Vector DB service** (Qdrant) for pattern storage and semantic search
-- **OpenAI API key** (required) for semantic pattern matching and vector operations
-
-**For policy management and governance:**
-- **Vector DB service** (Qdrant) for policy storage and semantic search
-- **OpenAI API key** (required) for semantic policy matching and vector operations  
-- **Optional**: Kyverno installed in cluster for active policy enforcement
-
-### Installation
-
-DevOps AI Toolkit is designed to be used through AI development tools via MCP (Model Context Protocol). No direct installation needed - simply configure your AI tool to connect to the MCP server.
-
-### Usage
-
-**🎯 Recommended: Docker Setup (Complete Stack)**
-Perfect for getting all features working immediately with minimal setup:
-
-1. **Download Docker Compose configuration:**
-```bash
-curl -o docker-compose-dot-ai.yaml https://raw.githubusercontent.com/vfarcic/dot-ai/main/docker-compose-dot-ai.yaml
-```
-
-2. **Set environment variables and create MCP configuration:**
-```bash
-# Set your API keys
-export ANTHROPIC_API_KEY="sk-ant-api03-your-key-here"
-export OPENAI_API_KEY="sk-proj-your-openai-key-here"
-
-# Create MCP configuration for Claude Code
-cat > .mcp.json << 'EOF'
-{
-  "mcpServers": {
-    "dot-ai": {
-      "command": "docker",
-      "args": [
-        "compose", 
-        "-f",
-        "docker-compose-dot-ai.yaml",
-        "--env-file",
-        ".env",
-        "run", 
-        "--rm",
-        "--remove-orphans",
-        "dot-ai"
-      ]
-    }
-  }
-}
-EOF
-```
-
-**What you get:**
-- ✅ **Complete Stack**: MCP server + Qdrant vector database included
-- ✅ **All Features Working**: Capability management, pattern storage, policy governance, semantic search
-- ✅ **No External Dependencies**: Everything runs in containers
-- ✅ **Kubernetes Integration**: Direct kubectl access to your clusters
-
-**Alternative Methods**: See the [MCP Setup Guide](docs/mcp-setup.md) for NPX (Node.js) and Development setup options.
-
-3. **Start your MCP client:**
-```bash
-claude  # or your preferred MCP-enabled AI tool
-
-# Verify everything works by asking:
-"Show dot-ai status"
-```
-
-4. **Use conversational workflows:**
-
-**Example: Kubernetes Deployment**
-```
-User: I want to deploy a web application to my cluster
-
-Agent: I'll help you deploy a web application. Let me get recommendations. First, a few questions to provide better suggestions:
-
-What type of web application is this? Is it for development or production? 
-Does it need external access?
-[Uses recommend tool for clarification]
-
-User: It's a production Node.js API that needs external access
-
-Agent: Perfect! Based on your production requirements, I found 3 deployment options. 
-Let's use the Production Web Stack with external access.
-What's your application name and container image?
-[Uses recommend tool with refined intent]
-
-User: App name is "myapp" and image is "myapp:v1.0.0"
-
-Agent: Excellent! Generating production-ready manifests and deploying...
-[Uses chooseSolution, answerQuestion, generateManifests, deployManifests]
-
-Agent: ✅ Successfully deployed! Your production API is running with external access.
-```
-
-**Example: Capability Management**
-```
-User: I want to scan my cluster for resource capabilities to improve recommendations
-
-[Uses manageOrgData with capabilities scanning]
-
-Agent: Would you like to scan all cluster resources or specify a subset?
-Options: 1) All resources 2) Specific subset
-
-User: All resources in auto mode
-
-Agent: Starting comprehensive cluster capability scan...
-✅ Capability scan completed! Processed cluster resources successfully.
-
-User: Now I need a PostgreSQL database
-
-Agent: Let me get enhanced recommendations using your capability data.
-[Uses recommend tool with capability pre-filtering]
-
-Agent: Perfect! I found sqls.devopstoolkit.live as the top match - it's a managed database solution supporting PostgreSQL with multi-cloud capabilities and low complexity. Much better than the generic StatefulSet approach I would have suggested before!
-```
-
-**Example: Kubernetes Issue Remediation**
-```
-User: Something is wrong with my database in postgres-demo namespace
-
-Agent: I'll investigate the database issue using AI-powered analysis.
-[Uses remediate tool for systematic investigation]
-
-Agent: 🔍 Root Cause (95% confidence): PostgreSQL pod can't start because the required PersistentVolumeClaim 'postgres-pvc' is missing.
-
-🔧 Recommended Fix: Create missing PVC
-- Risk Level: Low  
-- Command: kubectl apply [PVC manifest]
-
-Choose execution: 1) Execute via MCP  2) Show commands
-
-User: 1
-
-Agent: ✅ Issue Resolved! Created postgres-pvc, pod transitioned to Running state. Database is operational!
-```
-
-**Example: Policy Management**
-```
-User: I want to create a policy requiring resource limits on all deployments
-
-Agent: I'll help you create a governance policy for resource limits. Let me start the creation workflow.
-[Uses manageOrgData with policy creation]
-
-Agent: Please describe your resource limits policy intent:
-
-User: All container deployments must have CPU and memory limits to prevent resource exhaustion. CPU limits should be between 100m-2000m, memory between 128Mi-4Gi.
-
-Agent: Excellent! I've created your Resource Limits Policy and generated a Kyverno ClusterPolicy for enforcement. 
-
-Would you like to:
-1. Store policy intent only (for AI guidance)  
-2. Apply Kyverno policy to cluster (active enforcement)
-
-User: Apply the Kyverno policy for active enforcement
-
-Agent: ✅ Policy deployed! Now when users deploy applications, they'll get required questions for CPU/memory limits with your specified ranges, and any non-compliant deployments will be blocked by Kyverno.
-```
-
-**Example: Documentation Testing**
-```
-User: I want to test my README.md file to make sure all the examples work
-
-Agent: I'll help you test your README.md for accuracy. Let me start a documentation testing session.
-[Uses testDocs tool]
-
-Agent: Found 6 testable sections in your README. Testing installation instructions...
-
-✅ npm install command works correctly
-❌ Configuration example has wrong port number (8080 vs 3000)
-⚠️  Claims "works out of the box" but requires additional setup
-
-Which issues would you like me to help you fix?
-
-User: Fix the port number directly in the doc, and I'll create a GitHub issue for the setup requirements.
-
-Agent: ✅ Documentation testing complete! Fixed 1 issue directly, 1 issue tracked externally.
-```
-
-*Note: Conversational examples are illustrative - actual AI responses will vary based on specific context and implementation.*
-
-**Example: Shared Prompts Library**
-```
-# Conversational approach
-User: I want to create a new PRD for a feature
-
-Agent: I'll help you create a documentation-first PRD. Let me start the process.
-[Uses prd-create prompt via /dot-ai:prd-create]
-
-Agent: Great! I've created GitHub issue #34 and the PRD file. What feature would you like to document?
-
-# Direct slash command approach  
-User: /dot-ai:prd-create
-
-Agent: I'm executing the PRD creation workflow. Please describe the feature you want to create a PRD for...
-```
+## Documentation
 
-📖 **[Complete MCP Setup Guide →](docs/mcp-setup.md)** - Detailed configuration, troubleshooting, and examples
+### 🚀 Getting Started
+- **[MCP Setup Guide](docs/mcp-setup.md)** - Complete configuration instructions for AI tools integration
+- **[Tools and Features Overview](docs/mcp-tools-overview.md)** - Comprehensive guide to all available tools and features
 
 ## Troubleshooting
 
@@ -347,12 +148,6 @@ Agent: I'm executing the PRD creation workflow. Please describe the feature you
 - Check KUBECONFIG path in environment variables
 - Test cluster access: `kubectl get nodes`
 
-## Documentation
-
-### 🚀 Getting Started
-- **[MCP Setup Guide](docs/mcp-setup.md)** - Complete configuration instructions for AI tools integration
-- **[Tools and Features Overview](docs/mcp-tools-overview.md)** - Comprehensive guide to all available tools and features
-
 ## Support
 
 - **Issues**: [GitHub Issues](https://github.com/vfarcic/dot-ai/issues)

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@vfarcic/dot-ai",
-  "version": "0.99.0",
+  "version": "0.101.0",
   "description": "AI-powered development productivity platform that enhances software development workflows through intelligent automation and AI-driven assistance",
   "mcpName": "io.github.vfarcic/dot-ai",
   "main": "dist/index.js",

package/shared-prompts/prd-done.md

@@ -60,6 +60,9 @@ Complete the PRD implementation workflow including branch management, pull reque
 - [ ] **Check PR details**: Use `gh pr view [pr-number]` to check for human review comments and PR metadata
 - [ ] **Review all automated feedback**: Check PR comments section for automated code review feedback (bots, linters, analyzers)
   - **Use multiple methods to capture all feedback**:
+    - **MCP servers** (preferred when available): Use any available MCP servers for comprehensive review data
+      - Code review MCPs (e.g., CodeRabbit, custom review servers) for detailed AI code reviews
+      - Check available MCP tools/functions related to code reviews, pull requests, or automated feedback
     - CLI commands: `gh pr view [pr-number]`, `gh pr checks [pr-number]`, `gh api repos/owner/repo/pulls/[pr-number]/comments`
     - **Web interface inspection**: Fetch the PR URL directly to capture all comments, including inline code suggestions that CLI tools may miss
     - Look for comments from automated tools (usernames ending in 'ai', 'bot', or known review tools)