NASA

General Dynamics Information Technology

CACI International Inc

VersAbility Resources

Andrew Keener

Founder, Keen Alliance | AI Transformation & Adoption Advisor

Design ChatGPT 5.6 Skills, Not Prompts

Founder, Keen Alliance | NASA AI Integration | Former $65M Operations Leader

Learn when to use Chat, Projects, Work, Skills, Sites, or Codex for different types of business work.

Navigate the new ChatGPT 5.6 Environment

Define the trusted sources, repeatable steps, boundaries, output, and human review that make a Skill dependable.

Design a Reusable ChatGPT Skill

Use the Reusable Skill Blueprint to define the job, trigger, sources, steps, boundaries, output, and review.

Map One Task Into a Reusable Skill

Make better decisions in the Age of AI. Turn ChatGPT into your strategic thinking partner.

Cohort 11

Decision Intelligence Pioneer

Google

Disney

HumanX

Intel

Salesforce

Cassie Kozyrkov

Founder of Decision Intelligence and Google’s first Chief Decision Scientist

Cohort 10

Most people use ChatGPT for emails and summaries. In this hybrid Maven course, Cassie will show you how to use it for what actually matters: career moves, negotiations, strategic planning, and high-stakes decisions where you need to think clearly under pressure. Forget busywork, let's focus on the things that really matter and make a real impact.We live in a world where advice is cheap, AI is abundant, and judgment is priceless. This course teaches you how to stay in charge of your thinking while using AI to enhance--not replace--your decision-making.✨ Cassie’s Note to You“AI will free you for the hard work of figuring out what actually matters. You don’t have to memorize everything anymore—but you still have to do the hard part: deciding what matters. That’s on you. Let’s make sure you’re really good at it.”My new course is about putting decision science on steroids with AI. It's an accelerated course in 5 modules with 30+ on demand videos as well as a 2 hour live Q&amp;A that you can attend with me where I answer all your burning questions. (If you can't make it live, you can access the recordings later.)

💡 Why This Course

Make better decisions with less wasted effort

Use ChatGPT as a decision-making partner, not a thinking substitute

Strengthen your judgment before rolling AI out across your organization

Spot and reduce cognitive bias in high-stakes decisions

Build a "decision scribe": reusable decision systems, prompts, and workflows

Document your reasoning so you can actually improve over time

Leaders ready to evolve with AI and motivate their teams. See what AI can do for you and become the AI champion your organization needs.

Professionals who want to think better—not just faster.﻿Turn ChatGPT into a strategic thinking assistant, not a glorified autocomplete.

Decision-makers looking for clarity. Supercharge your decisions and hone the human judgment skills that AI makes more valuable.

Build AI Agent Skills that Actually Work - 3 Hours Hands-on Workshop

Product Leader and Super IC at Google

Disney+ Hotstar

Zynga

Anshumani Ruddra

Product Super IC at Google with 22+ years crafting experiences and blockbuster products

Cohort 07

Cohort 08

Most product builders use AI agents the same way they used search - typing queries and hoping for the best. That's leaving most of the value on the table.The teams pulling ahead aren't using better prompts. They're teaching their agents. Agent Skills are reusable, testable instruction sets that tell AI agents exactly how to handle specific workflows: your deployment process, your code review standards, your team's edge cases. Write one skill well, and every agent on your team benefits from it, every time, automatically.The problem: nobody is teaching product builders how to create them. Most documentation is written for a narrow technical audience, and the tooling is fragmented across Claude Code, Codex, and Gemini.In this hands-on workshop, you'll go from zero to a working skill installed in your own agent: one that reflects your real workflows, not generic templates. You'll also learn how to evaluate and improve skills systematically, so they get better over time instead of drifting.If you build or are hoping to build products with AI agents: this is the highest-leverage skill you can develop right now.

🤖 Learn to build procedural Agent Skills, transforming your professional mindset from solo prompter to manager of elite AI agents

Shift to an AI Management Mindset

Build Custom, Reusable Agent Skills

Leverage the Open-Source Ecosystem

Evaluate and Iterate for 10x Output

Product Managers: who use Claude Code or Codex daily but rely on ad-hoc prompts - and want repeatable, team-shareable AI workflows.

Entrepreneurs &amp; Founders: building AI-native products who need their agents to encode business logic, not just generate code on demand.

Tech Executives &amp; Product Leaders: who want their teams to stop reinventing prompts and start shipping a shared skills library.

Build Claude skills that do your research the way you do

Founder @ User Research Strategist

Nikki Anderson

Founder of The User Research Strategist, trained 50+ research teams and 2K UXRs

Cohort 1

Cohort 2

Date and time: September 22, 2026 2:30pm GMTLevel: Beginner level; no prior experience with skills, just some comfort using the Claude chat. We will not cover Claude Code!Right now, somewhere in a research team, someone is re-typing the same context into Claude for the fourth time this week, getting something generic back, editing it into something usable, and wondering why AI was supposed to change everything.It does change things, just not through repetitive prompting.A Claude Skill tells Claude exactly how to approach a specific research task, your methodology, your quality bar, your output format, so you stop explaining yourself every session and Claude starts working the way you work.I have built over 52 of these skills for research and watched researchers go from "Claude is fine I guess" to running entire processes on autopilot. That change happens the moment you build something rather than just prompt something.In two hours you understand what a skill is and when it is worth building, watch me build a real one end to end, and draft the start of your own. You leave able to tell a strong skill from a weak one, with a real head start and the blueprint to build your full set.

Leave understanding what a skill is, able to spot the ones worth building, and brainstorm the start of your own, built to how you work

Place skills in your Claude work, and clear the tool confusion

Tell a strong skill from a weak one

Decide when a skill is worth building, and how big to make it

Watch a real skill built from scratch to working

Draft the start of your own skill and have the info to continue it forward

Researchers or people who do research that are new to Claude skills and not technical, who want a clear, hands-on start

Teams who want consistent, on-brand outputs across the group, not everyone prompting Claude their own way

User researchers or people who do research who keep getting generic output and want it working their way instead of fixing it every time

Skills as a Product for Agents. Ship to a New AI Distribution Channel in 4 hours

Founder, Level 250 | 3x VP, API Products

Verisk

Moodys

Oracle

SmartBear

Precisely

Emmanuel Paraskakis

3x VP Product (Apiary, Swagger, Oracle) | 1.3M APIs | Agent-ready APIs & MCP

Cohort 3

Skills are not just Markdown files that automate your day. They are a new way to package, distribute, and ship product experiences inside AI tools.This workshop takes you from "Skills as Automation" to "Skills as a Product".Turn your APIs, SDKs, CLIs, docs, and MCP servers into tutorials, onboarding flows, process libraries, product demos, and sales enablement. Publishing a Skill places your product inside Claude, Vercel, and the agent environments where users already work.In four hours, you'll build and ship a full Skill for your product.You'll see what's inside a real Skill, what good and risky look like, and how to spot malicious or unethical patterns. Then you'll create a Skill for your own product or idea, choosing from documentation, onboarding, process delivery, or marketing.You'll test it against real prompts, improve how it triggers, package it on GitHub, install it, and ship it where agents can find it.You leave with a working Skill, a clearer view of where Skills belong on your product roadmap, and a practical sense of what ethical Skills look like.Walk in: you've heard about Skills.Walk out: your product Skill is built, tested, installed, and shipping where agents live.

Know what makes a Skill valuable

The anatomy of an Agent Skill

How to build a usable Skill

Scan & secure Skills

Distribute via directories

Understanding context and how to prompt a model

Basic AI familiarity

A paid Claude subscription and access to Claude Code

Optionally, Node.js installed

Product Managers &amp; Ecosystem Leads who want agents to use their product.

Engineers &amp; Technical Leaders who want to make sure agents consistently and safely reach their Developer tools.

Founders &amp; Entrepreneurs who want maximum AI reach for their ideas and methodologies.

Agentic AI

Coding with AI

AI Workflows

Claude Code

OpenClaw

Vibe Coding

AI Evals

AI Transformation

RAG & Search

AI for PMs

AI for Engineers

AI for Designers

AI for Marketers

AI for Founders

Product Sense

Product Discovery

User Research

Prototyping

Growth

Analytics

Tech Foundations

Strategy

Influence

Leadership

Career Growth

Machine Learning

LLM Ops

Context Eng

Security

System Design

Figma

Design Systems

Visual Design

Design Strategy

Automation

Content Marketing

Demand Gen

Go-to-Market

Product Marketing

Positioning

Social Media

Brand

B2B Marketing

SEO & AEO

AI for Leaders

AI Governance

Communication

Management

People Operations

Exec Presence

Storytelling

Goal-setting

Personal Brand

Fundraising

Everyone

Operators

Data Scientists

Business Analysts

User Researchers

Customer Success

Project Managers

HR Professionals

Sales People

Lawyers

Finance

Investors

Real Estate

Educators

Creators

Introduction and Re-recording Explanation

Speaker Introduction: Andrew Keener

Identifying Repetitive Tasks and Rework

Choosing the Right ChatGPT Environment

Desktop App vs. Web Version Differences

Navigating the Desktop App: Chat vs. Work Modes

When to Use Chat vs. Work Environments

Using Codex for Technical Coding

Understanding Projects vs. Skills

Important UI Buttons: Atlas Browser and Terminal

Comparing Prompts, Projects, and Skills

Deciding Between a Prompt and a Skill

Locating and Creating Skills in ChatGPT

Blueprint for Designing a Dependable Skill

Case Study: Building a Policy Fact Checker Skill

The Prompt and Process for Building the Skill

Inspecting the Skill Blueprint Before Installation

Testing the Skill: PTO Carryover Inquiry

Testing the Skill: International Remote Work Inquiry

Testing the Skill: Implicit Invocation and Exceptions

Next Steps, Call to Action, and Conclusion

Operations professionals who optimize processes and manage day-to-day business functions.

Broad professional audience — content relevant across many roles and functions.

Applying AI tools and techniques to professional workflows — assign alongside more specific AI topics.

Automating professional workflows with AI tools — productivity, operations, and task automation.

Designing and optimizing the context window for LLM applications — prompt structure, memory, and information retrieval.

Design ChatGPT 5.6 Skills, Not Prompts

What you'll learn

Why this topic matters

You'll learn from

Andrew Keener