I Built a Portable AI Skill That Safely Upgrades .NET Applications

I Built a Portable AI Skill That Safely Upgrades .NET Applications AI coding assistants have become incredibly good at writing code. But I kept running into the same problem... When I asked an AI to upgrade a .NET application, the response usually looked something like this: "Update the TargetFramework, update the NuGet packages, and build." Anyone who has upgraded a real production application knows that's only a tiny part of the job. A proper upgrade normally involves: - Choosing the correct supported .NET version - Updating Microsoft and third-party packages - Handling private NuGet feeds - Fixing vulnerable dependencies - Detecting deprecated packages - Removing unused packages safely - Updating Docker images - Updating CI/CD pipelines - Understanding breaking changes - Running builds and tests - Producing an upgrade report That's not a prompt. That's an engineering workflow. So I decided to build one. Introducing CoreLogic AI Skills CoreLogic AI Skills is an open-source library of reusable engineering workflows designed for AI coding agents. Instead of writing the same prompts repeatedly, each workflow is packaged as a reusable Skill. The goal is simple: Build once. Use with any AI coding agent. The library currently supports: - Claude Code - Cursor - OpenCode - Codex - ChatGPT (packaged skills) GitHub Repository: 👉 https://github.com/mrlokeshagarwal/corelogic-ai-skills The first public skill: dotnet-upgrade The first skill I created is called dotnet-upgrade. Instead of blindly modifying a repository, it behaves more like an experienced senior engineer. Phase 1 - Repository Assessment It first analyses the repository. It looks for things like: - Current .NET version - Solution structure - Project types - NuGet packages - Private package feeds - Vulnerable dependencies - Deprecated packages - Docker configuration - CI/CD pipelines It then creates an upgrade plan. Nothing is modified yet. Phase 2 - Approval One design decision was very important to me. The skill never starts changing code immediately. Instead it presents something like this: .NET Upgrade Assessment Current framework: .NET 6 Recommended target: .NET 10 LTS Projects: 6 Vulnerable packages: 4 Deprecated packages: 2 Docker changes required: Yes CI/CD changes required: Yes No files have been modified. Approve this plan? Only after explicit approval does the upgrade begin. Phase 3 - Upgrade After approval the skill can: - Upgrade the target framework - Update NuGet packages - Handle private NuGet feeds - Fix vulnerable dependencies - Review deprecated packages - Remove unused packages carefully - Update Docker files - Update CI/CD pipelines - Resolve common upgrade issues Phase 4 - Validation The work isn't finished after changing code. The skill validates the application by: - Restoring packages - Building the solution - Running tests - Publishing the application - Producing a comparison report Because a successful build doesn't always mean a successful upgrade. More than a prompt library One thing I wanted to avoid was creating another repository full of prompts. Instead, I built a small ecosystem. The repository includes: - Reusable Skills - Generic installer - Multi-skill support - Validation tooling - Packaging utilities - GitHub Actions - Platform adapters - Automated tests - Documentation Adding a new skill shouldn't require changing the installer or packaging logic. Another included skill The repository also includes start-story. It helps developers begin work from an Azure DevOps work item by: - Retrieving the work item - Determining the correct repository - Creating or reusing the appropriate branch - Validating the implementation - Creating a Pull Request Like dotnet-upgrade , it includes approval checkpoints before potentially destructive actions. Why portable skills? Every AI coding tool has its own way of working. Some support Skills. Some support Rules. Some support Instructions. Some support AGENTS.md. I wanted the workflow itself to remain portable while only the discovery mechanism changed. That's why the repository includes adapters for multiple platforms rather than maintaining completely different implementations. What's next? I'm planning to add more engineering-focused skills, including: - SQL Performance Review - .NET Code Review - Entity Framework Modernization - Architecture Review - CI/CD Pipeline Review - Security Audit - Dependency Modernization I'd love your feedback This is the first public beta. If you use Claude Code, Cursor, OpenCode, Codex, ChatGPT-or any other AI coding assistant-I would really appreciate your feedback. Which engineering workflow would you like to see turned into a reusable AI Skill? ⭐ GitHub Repository https://github.com/mrlokeshagarwal/corelogic-ai-skills Feedback, ideas and contributions are always welcome. Top comments (0)