14 articles · newest first
A skill is a folder with one SKILL.md file that Claude opens only when your request matches. Here is what goes in it, how it loads, and when to reach for a skill instead of CLAUDE.md, a slash command, a hook or an MCP server.
Aliteq Team · 2h ago · 10 min
/compact squeezes your chat into a summary and keeps going. /clear wipes it and starts clean, for free. Here is what each one keeps, what auto-compact does on its own, and why your CLAUDE.md is the only rule book that survives both, from Anthropic's own docs.
Aliteq Team · 2h ago · 10 min
Manual, accept edits, plan, auto, don't ask, bypass: each one changes what Claude can do before it checks with you. Here is what Anthropic's docs say each does, how Shift+Tab moves between them, and where the safety lines sit.
Aliteq Team · 3d ago · 9 min
The weekly cap is a different clock from the 5-hour one, and switching models won't fix it. Here is what Anthropic's own pages say about both limits on Pro, Max and Team, how to see where you stand, and what each way of keeping going costs.
Aliteq Team · Oct 7 · 10 min
Your coding agent finds code by grepping and reading files, not by embeddings. Anthropic says that works. Cursor says semantic search added accuracy. Here is how to decide which your own app needs.
Aliteq Team · Oct 5 · 7 min
A hook is a small script Claude Code runs for you at fixed moments, such as before a tool call or when Claude finishes. Here is every piece in Anthropic's docs that matters: events, matchers, exit codes, JSON, where the file lives, and the security warning.
Aliteq Team · Oct 3 · 11 min
Lovable, Bolt, v0, Replit, Google AI Studio, Cursor, Claude Code and Antigravity all get lumped together. Their own documentation describes two different kinds of tool. A table of each one's own words, and two questions that narrow the choice.
Aliteq Team · Oct 3 · 7 min
Three tools get compared constantly, but they aren't three versions of the same thing. Here's what each one says it is in its own docs, the real decision hiding underneath, and when staying put is the right call.
Aliteq Team · Oct 3 · 7 min
You describe an app in plain English and an AI writes it — that's vibe coding, the term Collins named its 2025 Word of the Year. Here's where it came from, what it looks like in a tool like Lovable, and the one thing the definition quietly warns about.
Aliteq Team · Oct 2 · 7 min
In the US, people search "claude code" about ten times more than "vibe coding" — but if you've only used a visual builder, it's not obvious what it even is. Here's Claude Code explained for someone who started in Lovable.
Aliteq Team · Oct 2 · 7 min
"From vibe coding to agentic engineering" is one of the fastest-rising searches of 2026. The honest difference between the two terms is smaller — and more useful — than the jargon makes it sound.
Aliteq Team · Oct 2 · 7 min
In late September, DHH told a room of 1,200 developers that writing code by hand is now the exception. If you build apps by describing them to Lovable or Bolt, here's what actually changed for you — and what didn't.
Aliteq Team · Oct 2 · 7 min
All three coding agents can run on your own GPU through Ollama. The catch is 64k of context, which Ollama doesn't give you by default. Which agent to pick, and what your card can actually hold.
Aliteq Team · Sep 25 · 9 min
One command, or three environment variables. Plus the 64k context setting Ollama's defaults don't give you, the VRAM that costs, and what Ollama's Anthropic API doesn't support.
Aliteq Team · Sep 25 · 6 min