JJ’s Claude Code skill sets up new projects for him
JJ discusses his favorite meta workflow for setting up new projects using Claude, which automates the creation of repos, folders, Claude MD files, and project structure. This skill significantly reduces setup time by leveraging trained knowledge on repository building practices.
Summary
In this brief transcript, JJ shares his current favorite productivity tool: a meta workflow designed specifically for initializing new projects. The workflow automates multiple setup tasks including repository creation, folder structure organization, and the generation of Claude MD documentation files at various hierarchical levels. JJ explains that this skill is trained on established best practices for how repositories are built, allowing it to intelligently handle the layering of contacts and other project components during startup. He emphasizes that this automation saves him considerable time on routine project initialization tasks. The host affirms JJ's expertise, noting his professional approach to Claude and Claude Code utilization.
About this episode
Repos, folders, CLAUDE.md files, and project context—all handled by a reusable skill. JJ shares the Claude Code workflow that saves him time whenever he starts a new project. From How I Happy Hour with Claire Vo at Lenny’s Summit 2026. #HowIAI #ClaudeCode #AISkills
Key Insights
- JJ uses a meta workflow trained on established repository building practices to automatically set up new projects, which saves significant time on structural and documentation setup tasks
- The workflow handles multiple layers of project components including repos, folders, Claude MD files at different levels, and layering of contacts during project startup
- JJ considers this meta workflow one of his favorite skills currently because of its practical time-saving benefits in his development process
Topics
Transcript
[0:00] The Claude guy himself, the JJ. >> One of my favorites right now is a meta workflow for setting up a new project, the repo, the folders, the Claude MD, the sub Claude MDs, layering all the contacts when I'm starting up a new project. It's a skill that I use trained on how we build repos, and it just saves me so much time. >> Uh this guy's a pro. For more advanced Claude and Claude code tips, follow this guy on X. >> And this lady.
Full transcript available for MurmurCast members
Sign Up to AccessMore from How I AI
She uses Claude Code to find a house with the right vibe
Hillary shares an AI workflow she uses for house hunting that leverages Claude Code to find listings and filter them against her subjective "vibe-specific criteria," which she describes as evaluating whether a space would feel good to wake up in and spend time at.
She hasn’t sent a birthday text herself in 6 months
A speaker shares how they've delegated birthday acknowledgments to AI for the past 6 months, having their AI assistant research friends' children's ages and purchase appropriate gifts on Amazon. They frame this as automating 'emotional labor' through AI technology.
From Slack to Jira: customer feedback on autopilot
Victor shares his recent AI workflow that automates customer feedback ingestion from Slack into Jira Product Discovery. The system daily pulls app and customer service reviews, automatically classifies problems, and links customer demand.
A company brain to teach AI to 22,000 employees
A company successfully upskilled 22,000 global employees by creating a 'company brain' that leverages tools and processes to generate AI learning content at scale. This approach enabled customized, hands-on training across multiple disciplines including product management, engineering, and design.
The AI factory playbook for engineering teams
Zach Lloyd, CEO of Warp, explains how software factories—organized systems of AI agents integrated across development tools—enable teams to automate the full software development lifecycle while maintaining human oversight. The approach centralizes work in public spaces like Slack, measures efficiency through metrics like human interactions per PR, and uses continuous evaluation and self-improvement loops to optimize both cost and quality.