@vfarcic/dot-ai 0.117.0 → 0.119.0

package/README.md

@@ -4,146 +4,81 @@
 
 ![DevOps AI Toolkit Logo](assets/images/logo.png)
 
+[![npm version](https://badge.fury.io/js/%40vfarcic%2Fdot-ai.svg)](https://www.npmjs.com/package/@vfarcic/dot-ai)
+[![npm downloads](https://img.shields.io/npm/dm/@vfarcic/dot-ai.svg)](https://www.npmjs.com/package/@vfarcic/dot-ai)
+[![GitHub release](https://img.shields.io/github/release/vfarcic/dot-ai.svg)](https://github.com/vfarcic/dot-ai/releases/latest)
+[![License](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
+![Project Status](https://img.shields.io/badge/status-beta-orange)
+[![OpenSSF Scorecard](https://api.scorecard.dev/projects/github.com/vfarcic/dot-ai/badge)](https://scorecard.dev/viewer/?uri=github.com/vfarcic/dot-ai)
+[![GitHub stars](https://img.shields.io/github/stars/vfarcic/dot-ai.svg?style=social&label=Star)](https://github.com/vfarcic/dot-ai)
+
 </div>
 
-DevOps AI Toolkit is an AI-powered development productivity platform that enhances software development workflows through intelligent automation and AI-driven assistance.
+**AI-powered platform engineering and DevOps automation through intelligent Kubernetes operations and conversational workflows.**
 
 📚 [Quick Start](./docs/quick-start.md) | 🔧 [MCP Setup](./docs/mcp-setup.md) | 🛠️ [Features & Tools](./docs/mcp-tools-overview.md)
 
-## Who is this for?
-
-### Kubernetes Deployment
-- **Developers**: Deploy applications without needing deep Kubernetes expertise
-- **Platform Engineers**: Create organizational deployment patterns that enhance AI recommendations with institutional knowledge and best practices, and scan cluster resources to enable semantic matching for dramatically improved recommendation accuracy
-- **Security Engineers**: Define governance policies that integrate into deployment workflows with optional Kyverno enforcement
-
-### Kubernetes Issue Remediation
-- **DevOps Engineers**: Quickly diagnose and fix Kubernetes issues without deep troubleshooting expertise
-- **SRE Teams**: Automate root cause analysis and generate executable remediation commands
-- **Support Teams**: Handle incident response with AI-guided investigation and repair workflows
-
-<!--
-### Platform Building
-DEVELOPER NOTE: This tool is under active development with incomplete functionality. Not recommended for production use.
-- **Platform Engineers**: Install and configure platform tools conversationally without memorizing script paths and commands
-- **New Team Members**: Build platform infrastructure through zero-knowledge guided workflows
-- **DevOps Teams**: Create and manage Kubernetes clusters through natural language interactions
--->
-
-### Shared Prompts Library
-- **Development Teams**: Share proven prompts across projects without file management
-- **Project Managers**: Standardize workflows with consistent prompt usage across teams
-- **Individual Developers**: Access curated prompt library via native slash commands
-
-### Project Setup & Governance
-- **Project Maintainers**: Bootstrap new repositories with governance, legal, and security files
-- **Development Teams**: Standardize repository setup and workflows across projects
-- **Security Teams**: Implement consistent security policies, vulnerability reporting, and compliance standards
-
-### AI Integration
-- **AI Agents**: Integrate all capabilities with Claude Code, Cursor, or VS Code for conversational workflows
-- **Multiple AI Providers**: Choose from multiple AI models and providers to optimize for quality, cost, and reliability - see [AI Model Configuration](./docs/mcp-setup.md#ai-model-configuration)
-- **REST API**: Access all tools via standard HTTP endpoints for CI/CD pipelines, automation scripts, and traditional applications
+---
 
-## Key Features
+## What is DevOps AI Toolkit?
 
-### Kubernetes Deployment Intelligence
-🔍 **Smart Discovery**: Automatically finds all available resources and operators in your cluster  
-🧠 **Semantic Capability Management**: Discovers what each resource actually does for intelligent matching  
-🤖 **AI Recommendations**: Smart intent clarification gathers missing context, then provides deployment suggestions tailored to your specific cluster setup with enhanced semantic understanding  
-🔧 **Operator-Aware**: Leverages custom operators and CRDs when available  
-🚀 **Complete Workflow**: From discovery to deployment with automated Kubernetes integration
+DevOps AI Toolkit brings AI-powered intelligence to platform engineering, Kubernetes operations, and development workflows. It provides intelligent Kubernetes deployment recommendations through capability discovery and semantic matching, AI-powered issue remediation, automated repository setup with governance and security files, and shared prompt libraries for consistent development workflows—all through natural language conversation.
 
-📖 [Learn more →](./docs/mcp-recommendation-guide.md)
+Built on the Model Context Protocol (MCP), it integrates seamlessly with Claude Code, Cursor, and VS Code to provide conversational interaction for complex DevOps and development tasks.
 
-#### Capability-Enhanced Recommendations
-Transform how AI understands your cluster by discovering semantic capabilities of each resource:
+## Mission
 
-**The Problem**: Traditional discovery sees `sqls.devopstoolkit.live` as a meaningless name among hundreds of resources.
+DevOps AI Toolkit democratizes platform engineering and cloud native operations by making complex workflows accessible through AI-powered automation. We eliminate the expertise barrier that prevents teams from adopting best practices in Kubernetes operations, repository governance, and standardized development workflows—making professional-grade DevOps accessible through natural language interaction.
 
-**The Solution**: Capability management teaches the system that `sqls.devopstoolkit.live` handles PostgreSQL databases with multi-cloud support.
+## Who Should Use This?
 
-**Before Capability Management:**
-```
-User: "I need a PostgreSQL database"
-AI: Gets 400+ generic resource names → picks complex multi-resource solution
-Result: Misses optimal single-resource solutions
-```
+**DevOps AI Toolkit is for teams who want to**:
+- Manage cloud resources (AWS, Azure, GCP) using Kubernetes as a control plane (developers, platform engineers)
+- Quickly diagnose and fix cluster and infrastructure issues (SREs, DevOps engineers)
+- Standardize resource provisioning with organizational patterns and policies (security engineers, platform teams)
+- Bootstrap repositories with governance and security files (project maintainers)
+- Access curated development prompts through native slash commands (development teams)
 
-**After Capability Management:**
-```
-User: "I need a PostgreSQL database"  
-AI: Gets pre-filtered relevant resources with rich context
-Result: Finds sqls.devopstoolkit.live as perfect match ✨
-```
+## Scope
 
-📖 [Learn more →](./docs/mcp-capability-management-guide.md)
+### In Scope
+- AI-powered resource provisioning recommendations using Kubernetes as control plane
+- Intelligent issue remediation and root cause analysis
+- Organizational pattern and policy management with semantic search
+- MCP-based integration with AI coding assistants
+- Multi-provider AI model support (Claude, GPT, Gemini)
+- Project setup with governance, legal, and security files
 
-### Kubernetes Issue Remediation
-🔍 **AI-Powered Root Cause Analysis**: Multi-step investigation loop identifies the real cause behind Kubernetes failures  
-🛠️ **Executable Remediation**: Generates specific kubectl commands with risk assessment and validation  
-⚡ **Dual Execution Modes**: Manual approval workflow or automatic execution based on confidence thresholds  
-🔒 **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.)
+### Out of Scope
+- Kubernetes cluster provisioning/management (delegates to existing tools)
+- CI/CD pipeline execution (provides recommendations only)
+- Application runtime monitoring (integrates with existing observability tools)
 
-📖 [Learn more →](./docs/mcp-remediate-guide.md)
+## Key Features
 
-<!--
-### Platform Building
-DEVELOPER NOTE: This tool is under active development with incomplete functionality. Not recommended for production use.
-🗣️ **Natural Language Operations**: Install tools and create clusters through conversation without memorizing commands
-🔍 **Dynamic Discovery**: Automatically discovers 21+ available platform operations from infrastructure scripts
-🤖 **AI-Powered Intent Mapping**: Understands variations like "Install Argo CD", "Set up ArgoCD", "Deploy Argo CD"
-💬 **Conversational Configuration**: Guides through parameter collection step-by-step with sensible defaults
-🎯 **Zero-Knowledge Onboarding**: New users successfully build platforms without documentation
-
-📖 [Learn more →](./docs/mcp-build-platform-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  
-🤖 **Kyverno Generation**: Automatically generates Kyverno ClusterPolicies for active enforcement  
-🎯 **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
+### 🔍 Resource Provisioning Intelligence
+Automatically discovers cluster resources using semantic capability management. AI understands what each resource actually does, providing intelligent recommendations for provisioning resources across clouds using Kubernetes as a control plane.
+📖 [Deployment Guide](./docs/mcp-recommendation-guide.md) | [Capability Management](./docs/mcp-capability-management-guide.md)
 
-📖 [Learn more →](./docs/mcp-prompts-guide.md)
+### 🛠️ Issue Remediation
+AI-powered root cause analysis with multi-step investigation, executable remediation commands, and safety mechanisms for manual or automatic execution.
+📖 [Learn more →](./docs/mcp-remediate-guide.md)
 
-### Project Setup & Governance
-📦 **Repository Audit**: Scans repositories to identify missing governance, legal, and automation files
-📋 **25+ Templates**: Generates LICENSE, CODE_OF_CONDUCT, CONTRIBUTING, SECURITY, GitHub workflows, and automation
-🔧 **GitHub Automation**: Sets up Renovate for dependency updates, PR labeling, and stale issue management
-🛡️ **Security Workflows**: Includes OpenSSF Scorecard for security posture analysis
-✅ **Standards-Based**: All templates based on authoritative sources (Contributor Covenant, OpenSSF, GitHub)
+### 🏛️ Pattern & Policy Management
+Capture organizational knowledge and governance policies that automatically enhance AI recommendations with best practices and compliance requirements. Uses vector search for intelligent semantic matching.
+📖 [Pattern Management](./docs/pattern-management-guide.md) | [Policy Management](./docs/policy-management-guide.md)
 
+### 📦 Project Setup & Governance
+Generate 25+ governance, legal, and automation files (LICENSE, CODE_OF_CONDUCT, CONTRIBUTING, SECURITY, GitHub workflows, Renovate, OpenSSF Scorecard) for repository standardization.
 📖 [Learn more →](./docs/mcp-project-setup-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, remediation, pattern management, and shared prompt workflows
-🎯 **Multiple AI Providers**: Choose from multiple AI models and providers to optimize for quality, cost, and reliability - see [AI Model Configuration](./docs/mcp-setup.md#ai-model-configuration)
+### 💬 Shared Prompts Library
+Access curated prompts as native slash commands (`/dot-ai:prompt-name`) in your coding agent for consistent workflows across projects.
+📖 [Learn more →](./docs/mcp-prompts-guide.md)
 
-**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.
----
+### ⚡ AI Integration
+Works with Claude Code, Cursor, VS Code via Model Context Protocol. Supports multiple AI providers (Claude, GPT, Gemini) for flexibility and cost optimization.
+📖 [AI Model Configuration](./docs/mcp-setup.md#ai-model-configuration)
 
 ## See It In Action
 
@@ -151,42 +86,58 @@ DEVELOPER NOTE: This tool is under active development with incomplete functional
 
 This video explains the platform engineering problem and demonstrates the Kubernetes deployment recommendation workflow from intent to running applications.
 
-## 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
+## Quick Start
 
-## Troubleshooting
+Get started in 3 steps:
+1. Configure MCP server (Docker or npm)
+2. Connect your AI coding assistant (Claude Code, Cursor, VS Code)
+3. Start using conversational workflows
 
-### MCP Issues
+## Documentation
 
-**MCP server won't start:**
-- Verify environment variables are correctly configured in `.mcp.json` env section
-- Check session directory exists and is writable
-- Ensure `ANTHROPIC_API_KEY` is valid
+### Getting Started
+- **[Quick Start Guide](docs/quick-start.md)** - Get started in minutes
+- **[MCP Setup Guide](docs/mcp-setup.md)** - Complete configuration instructions
+- **[Tools Overview](docs/mcp-tools-overview.md)** - All available tools and features
 
-**"No active cluster" errors:**
-- Verify kubectl connectivity: `kubectl cluster-info`
-- Check KUBECONFIG path in environment variables
-- Test cluster access: `kubectl get nodes`
+### Feature Guides
+- **[Resource Provisioning](docs/mcp-recommendation-guide.md)** - AI-powered deployment recommendations
+- **[Capability Management](docs/mcp-capability-management-guide.md)** - Semantic resource discovery
+- **[Issue Remediation](docs/mcp-remediate-guide.md)** - AI-powered troubleshooting
+- **[Pattern Management](docs/pattern-management-guide.md)** - Organizational deployment patterns
+- **[Policy Management](docs/policy-management-guide.md)** - Governance and compliance
+- **[Project Setup](docs/mcp-project-setup-guide.md)** - Repository governance automation
 
 ## Support
 
-- **Issues**: [GitHub Issues](https://github.com/vfarcic/dot-ai/issues)
+- **[Support Guide](SUPPORT.md)** - How to get help and where to ask questions
+- **GitHub Issues**: [Bug reports and feature requests](https://github.com/vfarcic/dot-ai/issues)
+- **GitHub Discussions**: [Community Q&A and discussions](https://github.com/vfarcic/dot-ai/discussions)
+- **Troubleshooting**: See [Troubleshooting Guide](./docs/mcp-setup.md#troubleshooting) for common problems
+
+## Contributing & Governance
 
-## Contributing
+We welcome contributions from the community! Please review:
 
-We welcome contributions! Please:
-- Fork the repository and create a feature branch
-- Run integration tests to ensure changes work correctly (see [Integration Testing Guide](docs/integration-testing-guide.md))
-- Follow existing code style and conventions
-- Submit a pull request with a clear description of changes
+- **[Contributing Guidelines](CONTRIBUTING.md)** - How to contribute code, docs, and ideas
+- **[Code of Conduct](CODE_OF_CONDUCT.md)** - Community standards and expectations
+- **[Security Policy](SECURITY.md)** - How to report security vulnerabilities
+- **[Governance](docs/GOVERNANCE.md)** - Project governance and decision-making
+- **[Maintainers](docs/MAINTAINERS.md)** - Current project maintainers
+- **[Roadmap](docs/ROADMAP.md)** - Project direction and priorities
 
 ## License
 
 MIT License - see [LICENSE](LICENSE) file for details.
 
+## Acknowledgments
+
+DevOps AI Toolkit is built on:
+- [Model Context Protocol](https://modelcontextprotocol.io/) for AI integration framework
+- [Vercel AI SDK](https://sdk.vercel.ai/) for unified AI provider interface
+- [Kubernetes](https://kubernetes.io/) for the cloud native foundation
+- [CNCF](https://www.cncf.io/) for the cloud native ecosystem
+
 ---
 
-**DevOps AI Toolkit** - AI-powered development productivity platform for enhanced software development workflows.
+**DevOps AI Toolkit** - Making cloud native operations accessible through AI-powered intelligence.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@vfarcic/dot-ai",
-  "version": "0.117.0",
+  "version": "0.119.0",
   "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-create.md

@@ -118,6 +118,17 @@ Work through the PRD template focusing on project management, milestone tracking
 
 **CRITICAL**: Steps 2-4 must happen in this exact order to avoid the chicken-and-egg problem of needing the issue ID for the filename.
 
+### Step 5: Update ROADMAP.md (If It Exists)
+
+After creating the PRD, check if `docs/ROADMAP.md` exists. If it does, add the new feature to the appropriate timeframe section based on PRD priority:
+- **High Priority** → Short-term section
+- **Medium Priority** → Medium-term section
+- **Low Priority** → Long-term section
+
+Format: `- [Brief feature description] (PRD #[issue-id])`
+
+The ROADMAP.md update will be included in the commit at the end of the workflow (Option 2).
+
 ## Next Steps After PRD Creation
 
 After completing the PRD, present the user with numbered options:
@@ -150,8 +161,10 @@ This will help identify the first task and set up the development workflow.
 If user chooses option 2:
 
 ```bash
-# Stage the PRD file
+# Stage the PRD file (and ROADMAP.md if it was updated)
 git add prds/[issue-id]-[feature-name].md
+# If docs/ROADMAP.md exists and was updated, include it:
+# git add docs/ROADMAP.md
 
 # Commit with skip CI flag to avoid unnecessary CI runs
 git commit -m "docs(prd-[issue-id]): create PRD #[issue-id] - [feature-name] [skip ci]
@@ -159,6 +172,7 @@ git commit -m "docs(prd-[issue-id]): create PRD #[issue-id] - [feature-name] [sk
 - Created PRD for [brief feature description]
 - Defined [X] major milestones
 - Documented problem, solution, and success criteria
+- Added to ROADMAP.md ([timeframe] section)
 - Ready for implementation"
 
 # Push to main

package/shared-prompts/prd-done.md

@@ -33,6 +33,7 @@ Complete the PRD implementation workflow including branch management, pull reque
 - [ ] **No outstanding blockers**: All dependencies resolved and technical debt addressed
 - [ ] **Update PRD status**: Mark PRD as "Complete" with completion date
 - [ ] **Archive PRD file**: Move completed PRD to `./prds/done/` directory to maintain project organization
+- [ ] **Update ROADMAP.md (if it exists)**: Remove the completed feature from `docs/ROADMAP.md` roadmap if the file exists
 
 **Note**: Tests will run automatically in the CI/CD pipeline when the PR is created. Do not run tests locally during the completion workflow.
 
@@ -52,10 +53,191 @@ Complete the PRD implementation workflow including branch management, pull reque
 - [ ] **Push to remote**: `git push -u origin feature/prd-[issue-id]-[feature-name]`
 
 ### 3. Pull Request Creation
-- [ ] **Create PR**: Use `gh pr create` with comprehensive description
-- [ ] **Link to PRD**: Reference the original issue and PRD file
-- [ ] **Review checklist**: Include testing, documentation, and quality confirmations
-- [ ] **Request reviews**: Assign appropriate team members for code review
+
+**IMPORTANT: Always check for and use PR template if available**
+
+#### 3.1. PR Template Detection and Parsing
+- [ ] **Check for PR template** in common locations:
+  - `.github/PULL_REQUEST_TEMPLATE.md`
+  - `.github/pull_request_template.md`
+  - `.github/PULL_REQUEST_TEMPLATE/` (directory with multiple templates)
+  - `docs/pull_request_template.md`
+
+- [ ] **Read and parse template comprehensively**: If found, analyze the template to extract:
+  - **Structural elements**: Required sections, checklists, format requirements
+  - **Content requirements**: What information needs to be provided in each section
+  - **Process instructions**: Any workflow enhancements or prerequisites specified in the template
+  - **Validation requirements**: Any checks, sign-offs, or verifications mentioned
+
+- [ ] **Extract actionable instructions from template**:
+  - **Commit requirements**: Look for DCO sign-off, commit message format, commit signing requirements
+  - **Pre-submission actions**: Build commands, test commands, linting, format checks
+  - **Documentation requirements**: Which docs must be updated, links that must be added
+  - **Review requirements**: Required reviewers, approval processes, special considerations
+
+  **Examples of template instructions to identify and execute:**
+  - "All commits must include a `Signed-off-by` line" → Validate commits have DCO sign-off, amend if missing
+  - "Run `npm test` before submitting" → Execute test command
+  - "PR title follows Conventional Commits format" → Validate title format
+  - "Update CHANGELOG.md" → Check if changelog was updated
+  - Any bash commands shown in code blocks → Consider if they should be executed
+
+#### 3.2. Analyze Changes for PR Content
+- [ ] **Review git diff**: Analyze `git diff main...HEAD` to understand scope of changes
+- [ ] **Review commit history**: Use `git log main..HEAD` to understand implementation progression
+- [ ] **Identify change types**: Determine if changes include:
+  - New features, bug fixes, refactoring, documentation, tests, configuration, dependencies
+  - Breaking changes or backward-compatible changes
+  - Performance improvements or security fixes
+- [ ] **Check modified files**: Identify which areas of codebase were affected
+  - Source code files
+  - Test files
+  - Documentation files
+  - Configuration files
+
+#### 3.3. Auto-Fill PR Information
+Automatically populate what can be deduced from analysis:
+
+- [ ] **PR Title**:
+  - Follow template title format if specified (e.g., Conventional Commits: `feat(scope): description`)
+  - Extract from PRD title/description and commit messages
+  - Include issue reference if required by template
+
+- [ ] **Description sections**:
+  - **What/Why**: Extract from PRD objectives and implementation details
+  - **Related issues**: Automatically link using `Closes #[issue-id]` or `Fixes #[issue-id]`
+  - **Type of change**: Check appropriate boxes based on file analysis
+
+- [ ] **Testing checklist**:
+  - Mark "Tests added/updated" if test files were modified
+  - Note: Tests run in CI/CD automatically
+
+- [ ] **Documentation checklist**:
+  - Mark items based on which docs were updated (README, API docs, code comments)
+  - Check if CONTRIBUTING.md guidelines followed
+
+- [ ] **Security checklist**:
+  - Scan commits for potential secrets or credentials
+  - Flag if authentication/authorization code changed
+  - Note any dependency updates
+
+#### 3.4. Prompt User for Information That Cannot Be Deduced
+**IMPORTANT: Don't just ask - analyze and propose answers, then let user confirm or correct**
+
+For each item, use available context to propose an answer, then present it to the user for confirmation:
+
+- [ ] **Manual testing results**:
+  - **Analyze PRD testing strategy section** to understand what testing was planned
+  - **Check git commits** for testing-related messages
+  - **Propose testing approach** based on change type (e.g., "Documentation reviewed for accuracy and clarity, cross-references validated")
+  - Present proposal and ask: "Is this accurate, or would you like to modify?"
+
+- [ ] **Breaking changes**:
+  - **Scan commits and PRD** for breaking change indicators
+  - If detected, **propose migration guidance** based on PRD content
+  - If not detected, **confirm**: "No breaking changes detected. Correct?"
+
+- [ ] **Performance implications**:
+  - **Analyze change type**: Documentation/config changes typically have no performance impact
+  - **Propose answer** based on analysis (e.g., "No performance impact - documentation only")
+  - Ask: "Correct, or are there performance considerations?"
+
+- [ ] **Security considerations**:
+  - **Check if security-sensitive files** were modified (auth, credentials, API keys)
+  - **Scan commits** for security-related keywords
+  - **Propose security status** (e.g., "No security implications - documentation changes only")
+  - Ask: "Accurate, or are there security considerations to document?"
+
+- [ ] **Reviewer focus areas**:
+  - **Analyze PRD objectives** and **git changes** to identify key areas
+  - **Propose specific focus areas** (e.g., "Verify documentation accuracy, check cross-reference links, confirm workflow examples match implementation")
+  - Present list and ask: "Are these the right focus areas, or should I adjust?"
+
+- [ ] **Follow-up work**:
+  - **Check PRD for "Future Enhancements" or "Out of Scope" sections**
+  - **Analyze other PRDs** in `prds/` directory for related work
+  - **Propose follow-up items** if any (e.g., "Future enhancements listed in PRD: template validation, AI-powered descriptions")
+  - Ask: "Should I list these, or is there other follow-up work?"
+
+- [ ] **Additional context**:
+  - **Review PRD for special considerations**
+  - **Check if this is a dogfooding/testing PR**
+  - **Propose any relevant context** (e.g., "This PR itself tests the enhanced workflow it documents")
+  - Ask: "Anything else reviewers should know?"
+
+**Presentation Format:**
+Present all proposed answers together in a summary format:
+```markdown
+📋 **Proposed PR Information** (based on analysis)
+
+**Manual Testing:** [proposed answer]
+**Breaking Changes:** [proposed answer]
+**Performance Impact:** [proposed answer]
+**Security Considerations:** [proposed answer]
+**Reviewer Focus:** [proposed list]
+**Follow-up Work:** [proposed items or "None"]
+**Additional Context:** [proposed context or "None"]
+
+Please review and respond:
+- Type "yes" or "confirm" to accept all
+- Specify corrections for any items that need changes
+```
+
+#### 3.5. Execute Template Requirements
+**IMPORTANT: Before creating the PR, identify and execute any actionable requirements from the template**
+
+- [ ] **Analyze template for actionable instructions**:
+  - Scan template content for imperative statements, requirements, or commands
+  - Look for patterns like "must", "should", "run", "execute", "ensure", "verify"
+  - Identify bash commands in code blocks that appear to be prerequisites
+  - Extract any validation requirements mentioned in checklists
+
+- [ ] **Categorize identified requirements**:
+  - **Commit-level actions**: Sign-offs, formatting, validation
+  - **Pre-submission commands**: Tests, builds, lints, format checks
+  - **Validation checks**: File existence, format compliance, content requirements
+  - **Documentation actions**: Required updates, links to add
+
+- [ ] **Propose and execute requirements**:
+  - Present identified requirements to user: "Template specifies these actions: [list]"
+  - For each requirement, determine if it can be automated
+  - Propose execution: "Should I execute these now?"
+  - Execute confirmed actions and report results
+  - Handle failures gracefully and ask user how to proceed
+
+- [ ] **Summary before PR creation**:
+  ```markdown
+  ✅ Template Requirements Status:
+  [List each requirement with status: executed/validated/skipped/failed]
+
+  Ready to create PR? (yes/no)
+  ```
+
+#### 3.6. Create Pull Request
+- [ ] **Construct PR body**: Combine auto-filled and user-provided information following template structure
+- [ ] **Create PR**: Use `gh pr create --title "[title]" --body "[constructed-body]"` or `gh pr create --title "[title]" --body-file [temp-file]`
+- [ ] **Verify PR created**: Confirm PR was created successfully and template was populated correctly
+- [ ] **Request reviews**: Assign appropriate team members for code review if specified
+
+#### 3.7. Fallback for Projects Without Templates
+If no PR template is found, create a sensible default structure:
+
+```markdown
+## Description
+[What this PR does and why]
+
+## Related Issues
+Closes #[issue-id]
+
+## Changes Made
+- [List key changes]
+
+## Testing
+- [Testing approach and results]
+
+## Documentation
+- [Documentation updates made]
+```
 
 ### 4. Review and Merge Process
 - [ ] **Check ongoing processes**: Use `gh pr checks [pr-number]` to check for any ongoing CI/CD, security analysis, or automated reviews (CodeRabbit, CodeQL, etc.)

package/shared-prompts/prd-next.md

@@ -198,8 +198,6 @@ Present findings in this focused format:
 
 **Dependencies**: [What's already complete that makes this ready to work on]
 
-**Effort estimate**: [Realistic time estimate]
-
 **Success criteria**: [How you'll know it's done]
 
 ---

package/shared-prompts/prd-start.md

@@ -10,6 +10,8 @@ category: project-management
 
 You are helping initiate active implementation work on a specific Product Requirements Document (PRD). This command bridges the gap between PRD planning and actual development work by setting up the implementation context and providing clear next steps.
 
+**IMPORTANT**: Do NOT include time estimates or effort estimates in your responses. Focus on task prioritization, dependencies, and clear next steps without speculating on duration.
+
 ## Process Overview
 
 1. **Select Target PRD** - Ask user which PRD they want to implement
@@ -190,8 +192,6 @@ Present the implementation plan:
 
 **Success criteria**: [How you'll know this task is complete]
 
-**Estimated effort**: [Time estimate]
-
 **Next steps after this**: [What becomes possible once this is done]
 
 ## Implementation Approach