OpenClawNet - Skills + Memory

In this session we will personalize the agent with skills — reusable knowledge bundles defined in Markdown with YAML frontmatter — and add conversation memory so it retains context across sessions. We will build a skill loader, implement automatic summarization to manage token budgets, and create a UI to toggle skills on and off in real time.

At the end we will have an agent that adapts its expertise based on loaded skills and remembers your preferences across conversations. Add a "Git Expert" skill or a "JavaScript Mentor" skill and watch the agent's behavior change. Your users can create custom skills without touching code.

Key Topics & Technologies:

• Skill architecture (Markdown + YAML)
• Markdown parsing and metadata extraction
• In-memory caching and skill composition
• Conversation memory and summarization strategies
• Token budgeting and context window management
• Skill UI with toggle controls
• Workspace customization patterns

Pre-requisites:

• Experience: Intermediate C# and ASP.NET Core knowledge (not a .NET 101)
• Environment: .NET 10 SDK, VS Code + GitHub Copilot (or Visual Studio), Docker (for Ollama)
• Optional: Azure subscription (for Sessions 3–4, but local development works fine throughout)
• Mindset: Curiosity about AI agents, willingness to follow along live and ask questions