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?

Most people are using AI like a search engine. Ask a question. Get an answer. Move on. That’s not what we’re doing here. This community is for people who want to go deeper — building AI systems that actually work for their business. Context engineering. Memory. Agents. Workflows. Automation. The full stack. Some of you are just getting started. Some of you are already building. Both belong here. Here’s how this works — this isn’t a passive community where you watch speakers and disappear. Everyone brings something to the table. Share what’s working, what broke, what you built, what you learned. We’ll have live events, virtual hangouts, and local meetups for those nearby. But the real value is in the room — the people here figuring this out alongside you. One question to kick things off: Where are you right now with AI — just exploring, starting to build, or already running agents in your workflow? Drop it in the comments. Let’s see who’s in the room.

Here’s the deal: the stuff you’re stuck on is almost never as weird or unique as it feels at 11pm when nothing’s working. Someone in this room has hit the exact same wall — and climbed it. So let’s get you unstuck. Use the M.O.V.E framework prompt to help get unstuck 👉 https://www.skool.com/the-agentic-club-6051/classroom/aac37e25 Or drop it in the comments: • What you’re actually trying to do • Where it’s breaking • What you’ve already tried