🧜‍♀️ The AI Collective Hampton Roads

Notice: This meeting will be recorded. By joining and remaining in this meeting, you consent to being recorded. If you do not consent, please do not join.

Build Your Own Claude Skills: Teach Claude How You Work
Every session, you explain the same things. Your coding standards. Your review process. Your preferred format. Your tone of voice. Your deployment steps.
Claude doesn't remember between sessions. CLAUDE.md helps — it tells Claude who you are and what you prefer. But a preference list isn't a playbook. You need something that says: "When you encounter THIS situation, follow THESE steps, use THESE templates, and produce THIS output."
That's a Skill. You teach Claude once. It follows the process forever. And it can auto-invoke — Claude detects when to use a skill without you even asking.
This session is a live, demo-driven workshop. We'll build 10 real skills from scratch, covering everything from daily standups and code reviews to meeting notes and project scaffolding. By the end, you'll have a personal skill library that makes Claude work the way you work.

What we'll cover:

🧠 Why Skills Matter CLAUDE.md tells Claude who you are. Skills tell Claude how you work. The difference between explaining something every session and teaching it once.

⚡ Built-In Skills You Might Not Know /review, /simplify, /plan, /loop, /batch, /anthropic — what ships with Claude Code and how to use each one.

🔧 Anatomy of a Skill SKILL.md frontmatter, the markdown body, supporting files (templates, scripts, examples), auto-invocation, and the $ARGUMENTS system.

🛠️ 10 Skills We'll Build Live:

1. Daily Standup Report — auto-generated from git history and calendar
2. Code Review Checklist — your team's standards, enforced every time
3. Meeting Notes Formatter — messy notes in, structured summary out
4. PR Description Generator — Claude writes the PR description from the diff
5. Bug Report Creator — plain language to structured report with GitHub issue
6. Email Drafter — with voice matching from a style guide file
7. Competitive Quick Look — one company name in, structured brief out
8. Project Scaffolder — /scaffold react-app and everything is set up
9. Weekly Reflection — end-of-week self-assessment that builds an archive
10. Documentation Updater — catches stale docs before your users do

📁 Organizing and Sharing Skills Global vs project skills, sharing via git, keeping SKILL.md lean, and building a team-wide skill library.

Who this is for: Developers and technical professionals who use Claude Code and want to stop repeating themselves. If you've attended any of our previous events, this is the session where you turn everything you've learned into reusable, persistent workflows. Non-technical Cowork users will benefit from skills 3, 6, 7, and 9 (meeting notes, email drafting, competitive research, weekly reflection).

Who this is NOT for: If you haven't used Claude Code or Cowork yet, start with our earlier events and free setup guides. This session assumes you're comfortable with Claude and want to go deeper.

What you'll leave with: ✅ At least 2-3 working skills installed and tested ✅ A free homework doc with all 10 skill templates ready to copy ✅ Understanding of SKILL.md anatomy, auto-invocation, and supporting files ✅ A framework for building and sharing skills across your team

Prerequisites: — Claude Desktop installed with Cowork, OR Claude Code CLI installed — Claude Pro ($20/month) or Max ($100+/month) subscription — Basic familiarity with Claude from a previous event or self-study — Developers: a terminal open and a project folder ready to work in

🎙️ Your Speaker Andrew Stafford Co-Lead of The AI Collective Hampton Roads. 25+ years across technology, cloud architecture, and AI — including work with Amazon, NASA, healthcare platforms, and enterprise systems. Author of AI for Business. Currently building at the intersection of AI tooling, agentic workflows, and practical business automation.

Notice: This meeting will be recorded. By joining and remaining in this meeting, you consent to being recorded. If you do not consent, please do not join.

This event is capped at 500 attendees. Register now to secure your spot.

Build Your Own AI Agent: The Claude Agent SDK -

You've been using Claude Code interactively. Type a prompt, watch it work, review the output. That's great for your workflow. But what happens when you need Claude running inside your application? Processing uploads at 3 AM? Reviewing PRs automatically? Analyzing logs as a service?

The Claude Agent SDK is Claude Code packaged as a Python and TypeScript library. One function call, one prompt, and you have a fully autonomous agent with 10+ built-in tools — file reading, code editing, shell commands, web search, MCP connections — all handled autonomously. No tool loop. No orchestration code. The SDK is free and open source. You pay for tokens only.

This is a live coding workshop. We'll build 10 real agents from scratch, starting with a 10-line bug finder and ending with a multi-agent coordinator that spawns subagents for parallel work.

What we'll cover:

🧠 Why the Agent SDK Changes Everything The difference between the Client SDK (you build the tool loop), Claude Code CLI (you interact manually), and the Agent SDK (Claude handles tools autonomously in your code).

⚡ 10 Agents We'll Build Live:

1. Bug Finder & Fixer — reads code, finds bugs, fixes them. 10 lines of Python.
2. Code Documentation Generator — docstrings for every function in a directory
3. Test Writer — writes tests, runs them, fixes failures, iterates until green
4. File Processor Pipeline — watch a folder, process every new file automatically
5. API Health Monitor — hits endpoints, reports status, opens issues on failure
6. Log Analyzer — reads logs, groups errors by pattern, produces a digest
7. Security Auditor — scans for hardcoded secrets, SQL injection, missing validation
8. Data Report Generator — reads a database or CSV, produces formatted reports
9. PR Review Bot — triggered by webhook, reviews against your checklist, posts comments
10. Multi-Agent Coordinator — spawns subagents for parallel research + writing + review

🏗️ Managed Agents Preview The hosted version: sandboxed containers, persistent state, credential vaulting. $0.08/session-hour + tokens. Public beta since April 8, 2026. When to use Agent SDK (your infra) vs Managed Agents (Anthropic's infra).

Who this is for: Python or TypeScript developers who want to build autonomous AI agents. If you've been using Claude Code and want to embed its capabilities into your own applications, services, or pipelines — this is the session. Prior experience with Claude Code is helpful but not required.

Who this is NOT for: Non-developers. This is a coding workshop. Every demo involves writing and running Python or TypeScript code. If you're looking for no-code AI workflows, see our earlier events in the series.

What you'll leave with: ✅ The Agent SDK installed and a working agent running on your machine ✅ A free homework doc with all 10 agent templates in Python and TypeScript ✅ Understanding of built-in tools, permission modes, MCP integration, and subagents ✅ The architecture for building production agent services

Prerequisites: — Python 3.10+ or Node.js 18+ — An Anthropic API key (sign up at console.anthropic.com) — A code editor and terminal — Basic Python or TypeScript proficiency

🎙️ Your Speaker Andrew Stafford Co-Lead of The AI Collective Hampton Roads. 25+ years across technology, cloud architecture, and AI — including work with Amazon, NASA, healthcare platforms, and enterprise systems. Author of AI for Business. Currently building at the intersection of AI tooling, agentic workflows, and practical business automation.

New AI tools are dropping every week. Bookmarks are piling up. “To-be-studied” lists are growing faster than we can keep up with.
Sound familiar?

Peninsula Builders Study Group is a local initiative for students and developers of the Peninsula area who want to stop meaning to learn and start actually doing it—together.
There’s no pressure to be an expert, and no bootcamp intensity. Just a consistent habit, a room full of curious people, and the accountability that comes from showing up.

How it works:
We meet every two weeks on Tuesdays from 6:00–7:30 PM at CNU. Sessions are a mix of focused study and group discussion.

Things to bring:

• Laptop
• Earphones/headphones

Meet people and pick up your weekly groceries.

🤝 A casual networking hangout in the grocery store cafe
Chats, connections, & grocery carts is a relaxed, social-first networking event for curious, friendly people across Hampton Roads who enjoy good conversation and knocking out life errands at the same time.

This is not a lecture.
This is not a pitch night.
And you definitely do not need to “prepare” anything.

It is simply a low-pressure space to meet new people, have real conversations, and casually connect while wandering the aisles and picking up your weekly groceries.

Whether you are deeply into AI and automation, adjacent to tech and creativity, or just someone who enjoys thoughtful conversations with interesting humans, you belong here.

✨ What to expect
- Casual, open networking with a mix of builders, creatives, technologists, founders, students, and professionals
- Easy, organic conversations while shopping at your own pace
- Light, optional conversation prompts to help break the ice if you want them
- No presentations, no panels, no pressure to “network correctly”
- A friendly, welcoming environment for all backgrounds and experience levels
- Come as you are. Grab a cart or a basket. Pick up dinner for the week. - - Meet a few new people along the way.

👥 Who should attend
Chats, Connections, & Grocery Carts is for:

People who enjoy meeting others without forced networking vibes
Builders, creatives, technologists, and curious minds
AI, automation, no-code, and tech-adjacent folks
Students and career switchers exploring what is next
Founders, consultants, operators, and professionals
Anyone who likes good conversation and low-stakes socializing

If you enjoy thoughtful chats and meeting people in unexpected places, you will fit right in.

🏪 Why a grocery store
You were probably going to the store anyway.

Hosting this event in a grocery store keeps things human, practical, and approachable. It removes the pressure of traditional networking and turns it into something simple, efficient, and a little fun.

Two errands. One cart.

💡 Why this event exists
Community grows best in relaxed, everyday spaces.

Chats, Connections, & Grocery Carts exists to create an easy, human-centered way for people to connect without titles, talks, or expectations. It is about building relationships, sharing ideas naturally, and strengthening the local community one conversation at a time.

Come say hi. Leave with groceries. Make a few new connections along the way.

ℹ️ Other bits of info & FAQs

• This is a free community event
• Drinks or food are available for purchase depending on the venue
• Photos or videos may be taken for community and marketing purposes
• Come solo or bring a friend
• ​​​Is there free parking in the area? Yes. They’ve got lots of spots available in their parking lot.
• ​​​Is this free? Yes, but space is limited. Make sure to RSVP.

🤝 Organizers & partners