One lab.
Infinite
experiments.

Skills let you stop re-explaining the same workflow to Claude Code. Here's how to write one that actually fires when you need it — and why the frontmatter description, not the body, makes or breaks it.

Most coding LLM rankings measure one slice — generic reasoning, repo-wide patching, or edit accuracy — and rank confidently. Picking by a single source steers you to the wrong model for your actual task. Here's how to read three together, and a live page that does it for you daily.

Forget the 'install 100 agents' hype. Here are the three subagent patterns I actually use — structured dispatch for decisions, mandatory review gates for autonomous work, and workload partition for big batches.

Last Wednesday, Claude navigated my multi-criteria scoring web app, evaluated a sample candidate, flagged a potential methodology bias, worked through a fix with me, ran 305 tests, and shipped the patch to production — all in one afternoon. Here is what made that possible (and what would have made it impossible).

If you've ever asked an AI to pull literature data and worried the cited PMIDs might be invented, here's a build-time check that refuses to ship the moment a quoted excerpt can't be found in its source URL. Six lines of logic, three layers of protection.

A non-developer's guide to setting up Obsidian as your personal knowledge base — from installation to graph view to connecting it with Claude AI via MCP. No coding required. Just folders, links, and a system that actually works.

meal.vibed-lab.com regenerates itself every month with zero clicks. Here is the exact, beginner-friendly recipe for setting up an OpenClaw cron job — the trigger, the skill, the test loop, and the patterns that make it actually trustworthy.

Built a monthly playground toy that measures your typing rhythm and maps it to one of 64 named auras with dual rarity scores. Here's how the feature vector + cosine distance pipeline works.

Andrej Karpathy posted a gist called 'LLM Wiki' — a pattern where the LLM maintains a compounding markdown wiki between you and your raw documents. I adapted it to my existing Obsidian vault without breaking what was already there. Here's what I changed, what surprised me, and the meta-lesson the wiki taught me about itself.

I merged the best parts of two GitHub repos — a forced review loop and a smart routing engine — into a custom Claude Code plugin called FRIDAY. It plans with Codex audit, routes implementation between Claude and Codex by size, enforces mandatory review, and does TDD. All in plain markdown files.