← The AI Hype Audit — all 244 verdicts
PARTLY "Claude can build this, but it's never gonna design this" — a fair point wearing an unfair word: 'never'
The claim“100 Claude Code Commands part two” — a slash-commands rundown for Anthropic’s Claude Code CLI, with a live demo of a pizza-ranking map app (‘Your restaurant 4.4’ among local competitors). 14.3K likes, 5.3K comments, 1.5K shares; the companion cheat sheet is comment-gated (‘Comment Claude’).
The biggest post of this batch is also one of the most defensible — mostly. Claude Code is real, the slash commands are documented by Anthropic, and the pizza-map demo is exactly the kind of small app the tool genuinely builds well. The stretch is the number: the official commands reference lists roughly 65+ built-ins (/help, /login, /doctor, /debug, /usage, /compact, /model, /mcp, /permissions and the rest). ‘100’ only gets there by padding with aliases (/cost = /usage, /quit = /exit) and custom commands — which are unlimited by design, because any file you drop in .claude/commands/ becomes one. That’s a real feature, but it means the ‘100’ says nothing about the product; you could as honestly claim 1,000. And the cheat sheet behind the comment gate is a repackaging of a free public docs page.
What holds up
- Claude Code and its slash commands are real and officially documented, including /status-class built-ins like /help, /login, /logout, /doctor, /debug, /feedback, /bug, /usage, /compact, /model, /mcp
- Custom slash commands are genuinely unlimited — any file in .claude/commands/ or a skill defines one
- The pizza-map demo is credible — a small map app is a bread-and-butter Claude Code build
What doesn't
- 'Never' is unsupportable — current Claude produces coherent, sometimes distinctive visual design today; the gap is context, not capability
- The slick site used to 'prove' human superiority is exactly what AI produces unassisted — and viewers can't verify it wasn't AI-assisted
- Soft self-interest: it's authority content from a designer whose livelihood the claim defends
- The build-vs-design binary is already stale — the real 2026 split is AI defaults vs human-directed AI output, and the winners use both
The catch
Nothing here is fake — it’s just inflated and gated. The real list is a free docs page; the funnel wants your comment more than it wants you fluent in the tool.
How to actually do it
- Type /help inside Claude Code — the real, current command list is built in
- Read the official commands reference on Anthropic’s docs instead of a DM’d cheat sheet
- If you want ‘100 commands,’ write your own: a markdown file in .claude/commands/ becomes a slash command — that’s the actual power feature the reel skips
Real tool, real demo, padded count — ~65+ documented built-ins, and the gated cheat sheet is a free docs page in disguise.
- Effort
- A brief takes an hour; it's the highest-leverage hour in the whole build
- Cost
- $20/mo DIY-with-taste; a few hundred to ~$2K for AI production + human direction; $3K–15K+ for full human design
- Stack
- A real brief + Claude for production + a human on intent
- Confidence
- Medium
- Posted by
- a working UX designer posting opinion commentary, no product
We test hype for free. We build the real thing for a living.
Thirty minutes, no pitch — and you'll leave with something useful either way.
Book a call with Todd or start with the free Business Checkup →The Verdict Weekly
Three verdicts every Friday. Free forever, unsubscribe anytime, no spam — that would be ironic.
© Schreier Group · schreiergroup.com · See a wild AI claim? Drop it here and we'll test it.