Posts tagged “claude-code”

The Work Starts When the Thought Does

An autonomous SDLC where a note fires a Claude session, and the pull request is waiting when I get home.

Self-healing software survives its bugs without changing a line. What I run against my projects changes the source. Logging the defect is what fires the work, and most days the completion email is the entirety of my involvement.

I Spent Years Automating My Obsidian Daily Note. Now It Files Itself.

I fed it by hand for years. Now an agent files my day's captures overnight, and I wake up to what's next.

For years I fed my Obsidian daily note by hand. Now an agent files my captures overnight, tells my thoughts from my tasks, and I wake up to a clear picture of what's next.

Sorties: Fire Real Actions Straight From Your AI Chat

Set up an action once. Fire it by name from anywhere, even your phone.

A Sortie turns a sentence in your AI chat into a real action. Fix a bug, message your team, fire an automation. Set it up once, fire it by name from anywhere, and your keys never touch the conversation.

Claude Code Is Not Your Project Manager. The Artifacts Are.

A markdown file got me started. Infrastructure is what it became.

A year ago I gave Claude a ROADMAP.md and called it my project manager. The post still ranks. The post is also out of date. Here is what Claude actually manages now.

Personal Second Brains Are Step One. Operational Second Brains Are The Actual Destination.

Every few months a new "second brain" build hits X. The pattern is real, the folder taxonomies are getting sharper. But every one of them stops in the same place: a markdown file. Here's the wall.

From It's a Small World to the Haunted Mansion: A Blog Post Written in Claude Chat via BlackOps MCP

How a single conversation, no app switching, no copy-paste, went from breaking news to published post before the ride ended.

Obsidian just shipped official Claude Code skills. Here's what it means when your vault already runs a custom skill ecosystem. And yes, I sent this from It's a Small World.

Everyone's Mad Anthropic Killed OpenClaw Access. I'm Not.

I spent a month debugging it every morning. The people crying loudest aren't the ones who were actually using it.

I bought the Mac mini. I posted that it was the future. A month later I was waking up every morning to fix something that broke overnight. Here's what I learned.

The Industry Just Validated What I've Been Building All Year

A 20-year product leader described the AI capability overhang. Every theme matched systems I'd already shipped. This is what it looks like from inside.

A great video just described the AI development revolution happening right now. I've been writing about it — and building it — for months. Here are the receipts.

Vibe Coding Isn’t the Problem - Vague Thinking Is

Why AI-assisted development exposes leadership, not recklessness

Discover why vibe coding is not the real problem in AI-assisted development and how clear thinking, intent, and constraints turn it into a powerful workflow

Command-Driven Development Logging with Visual Progress: A Better Way to Track Development with Claude Code

How I created and use a command-driven system in my everyday commerce development process with Claude Code to document progress with visual screenshots - giving me complete control over when and how enterprise development gets documented.

I Asked AI to Make My Site 'Pop' — It Built Asteroids Instead

From a simple UI request to shipping a complete Asteroids game—discover how Claude Code transformed casual conversation into production-ready code with authentic 1979 arcade gameplay.

Claude Code Is More Than a Dev Assistant—It’s My Project Manager

Discover how combining Claude Code with a simple ROADMAP.md file transformed my personal project management and delivered consistent progress on my blog.