Building FrontendLeap: teaching how to build the professional Web with GenAI and learning science.
Helping companies and teams go AI First on the Claude platform.
✦ New tips daily
Claude Code: from zero to professional. Tips, tutorials and deep dive guides from an engineer who uses it 12 hours a day.
Claude Code first steps: the fundamentals that don't expire
The Claude Code fundamentals that don't expire: install, sessions, context, quota, models, permissions. What you actually need to grasp on day 1.
AI: the joy of missing out on what doesn't matter
You can't keep up with AI, and you shouldn't try. The answer isn't resistance or passive acceptance: go all in, but deep on one thing instead of scattered.
Claude Code Agent View: managing parallel agents without leaving the terminal
I spent months managing many Claude Code agents by hand. Agent View now does it: my terminal-native workflow with Warp and Neovim, and the gaps I patch.
Claude Code scheduled tasks: 3 common failures and how to fix them
A local Claude Code task only runs while the app is open and the machine is awake. Otherwise it gets skipped, shows up hours late, or waits on a permission nobody is there to approve.
Claude Code subagents: the limit Anthropic removed, and how to set it yourself
Claude Code added a cap of 200 subagents per session to stop runaway delegation loops. Twelve versions later it was gone. Here's how to get the brake back, with a tested hook and one frontmatter field.
/claude-api prompt-audit: your CLAUDE.md and skills, optimized for Opus 5.5
All-caps rules, "think step by step" and contradictory instructions were written for older models. `/claude-api prompt-audit` finds each one by file and line, and changes nothing until you say so.
Claude Code ultrathink: what it does now, and what it doesn't
Half the internet says it's dead, the other half thinks it maxes Claude out. I measured it across 45 runs: it's neither.
Get only what matters
If I have nothing worth saying, you won't hear from me. When I do, you'll be the first to know. 7,000+ people already trust this.
Unsubscribe at any time.