I can't open Claude code in VS Code

What's up peeps. I've been trying to get a lot done these past few weeks. One of those projects was creating a portfolio showcasing some of my newer projects. It still needs work, but I don't like taking to long to get things live. If you have the time to check it out I would appreciate it. If it looks crappy I'd love to know. My design skills are not the best and looking back I probably should have just went with a fancy template, but I used the project to play around with claude code, claude design, etc. https://josephkemp.netlify.app/

RIGGS is a persistent AI assistant built on Claude Code, backed by a GitHub-synced knowledge base called RIGGS_BRAIN. It handles daily operations — email triage, calendar, research, task tracking — and maintains continuity between sessions via a structured session log. Repeatable workflows are defined as skill files and triggered by slash commands. Autonomous sub-agents handle research tasks independently and append findings to project files. Paired with RIGGS is Miggs — a locally-run LLM (Ollama3:8b on a spare laptop running a headless linux server) that processes overnight batch tasks like content generation and data extraction without API costs. Both systems are actively being expanded.

What It Does 1. Monitors job boards (Indeed, LinkedIn, Dice, ZipRecruiter, RemoteOK) for new listings 2. Filters out anything that doesn't match my criteria 3. Scores what's left: Strong, Moderate, or Weak match against my resume 4. Outputs a clean dashboard with one-click apply links --- How It's Built - Job boards send email alerts to a dedicated inbox when new listings go up - A Python script reads those emails and pulls out the key info (title, company, pay, link) - A second script hits the RemoteOK job board API directly for additional listings - Phase 2: an AI scorer (Claude) reads each listing and ranks it against my career profile --- Expected Results - 20–50 new listings per day pulled automatically - 3–8 strong matches surfaced per week - Daily review time: under 5 minutes instead of an hour Status: Pipeline is live. First alert emails incoming — once they land, I tune the scorer and wire up the dashboard.

I’ve been watching a lot of content on working with AI and wanted to share what I’ve learned from my own experience. My background includes jet engine maintenance in the military, IT and information security, and hands-on trades like carpentry and welding. I’ve used AI across both digital and physical projects, and after a couple of years of experimenting, I’ve settled into two main approaches: 1) I start with a clear idea and use AI to refine it and move faster than I could on my own. 2) I start with a rough concept and use AI to help develop it into something more complete. Both approaches work, but I’ve found I strongly prefer the first. I enjoy taking time to think through ideas on my own. I’ll bring a notebook into my workshop or outside, sit in the sun, and sketch or loosely wire frame concepts. That process—just thinking and creating internally—feels like play. Sometimes I go a step further and mentally simulate the idea as if it already exists. I “use” it in my head, test how it functions, and push on its weak points. Doing that has helped me catch design flaws and structural issues early. I treat those like small stress tests, iterate on them, and once the idea feels solid, I bring it to AI to accelerate the build-out. For anyone new to working with AI, a few things stand out: 1) Expect friction. You will make mistakes, lose work, break things, and backtrack. That’s part of learning any new tool. 2) This technology isn’t perfect. It will fail or give bad output at times. Step away when needed and rely on your own problem-solving skills. 3) Treat it as a creative process. There’s real enjoyment in building something, not just finishing it. 4) Focus on quality. Some ideas aren’t worth rushing. Focus on what’s meaningful or interesting, even if it takes longer. 5) Keep it light. Experiment, build things with friends, and don’t take it too seriously. It’s a tool meant to support you, not replace you. 6) Work in a collaborative manner. Some times asking for feedback, suggestions, or thoughts from a model can bring back useful information.