Friday, August 7th @ 5pm - 6pm 501 Harris Ave, Bellingham, WA 98225 Laptops open, drinks poured. The Agentic Club Happy Hour is where you bring the half-built idea, the burning question, or the workflow that won't cooperate — and we work it out together. Come build. Who's gonna make it?

I am working on planning the upcoming meetups. What do you want to learn? Drop your requests in the comments below.

Some of you are running full Skill libraries. Some of you found out Skills exist at the meetup this month. Both are exactly where you should be, and I want to map where the group actually stands. Drop a reply hitting these three: 1. Where you’re at. Pick one: • 🌱 Haven’t built one yet, or still figuring out what they are • 🔨 Built a few, experimenting • ⚙️ Running a real library across my workflows 2. Your go-to. The one Skill you reach for constantly. What does it do, and what would break in your week without it? 3. Your stuck point. The one thing about Skills you can’t crack right now. Structure? Evals? Getting them to trigger reliably? Subagents? Name it. No wrong answers here. A “🌱 and honestly I don’t get the difference between a Skill and a prompt” is just as useful as a 12-Skill setup. This thread is the map we build the next few conversations from.

Skills — prompt chains, task prioritization, and cost optimization with Andy and Alex Thu, 09 Jul 26 What Skills Are and Why They Matter - A skill turns a good prompt into a reliable workflow - Best for tasks done repeatedly where quality matters every time - Not ideal for one-off tasks or processes that change constantly - Full skill system includes: skill.md, sub-agents, assets, references, and evals - Evals act as a scoring framework: they check output against the voice guide, the structure guide, etc. Prompt to Prompt Chain to Skill - Start with a single prompt; escalate only when it’s insufficient - Prompt chain: multiple prompts linked in sequence - Each step can go deeper - A human review loop can be inserted between steps - Once the chain is dialed in, convert to a skill (skill.md in markdown) - After building skills, bundle related ones into plugins to stay organized Task Prioritization Demo (Andy’s Hot Seat) - Framework recommended: Navy SEALs’ CEE model - Critical: urgent, must act now (flat tire) - Essential: needed soon (low gas) - Enhancing: nice to have (new paint job) - Workflow: dump task list into AI, apply CEE framework, output in preferred format - Demo ran live using a “C Task Prioritizer” skill in Claude’s Cowork mode - Cowork runs sub-agents and performs better than standard chat for multi-step skills - Output exported to Excel/TSV for potential import into task management tools - Trello is better suited for teams; personal task management works well in Notion or Obsidian Notion as an AI-Connected Knowledge Base - Notion connects natively to Claude Desktop via built-in connector - Claude can build and update Notion databases via plain-English commands - Demo: created a personal to-do database, added tasks by voice, and queried bills by name - Useful patterns: - Session recaps saved directly to Notion databases - Daily task queries: “show only tasks due today” - Status updates by voice: “Mark that task as done”

Great AI Skills training / live discussion today, thanks for hosting @Mitch Britt! There were several new (to me) concepts that sound very valuable... how is everyone using "evals" to keep their prompts "on the rails" so to speak? Are you baking this into your skill files along side the skill itself?