Brooke Wright
Brooke Wright · @wright_mode
FREE GUIDE

4 free plugins that fix generic AI output

One prompt installs all four: the one that strips AI writing tells and learns your voice, the one that catches design cliches, the component catalogue, and Anthropic's own setup check.

Copy-paste readyFree tools onlyEvery claim fact-checkedBuilt by Brooke
Something went wrong. Please try again.

No spam. Unsubscribe anytime.

One prompt installs all four: writing that sounds like you, design that does not scream AI, real components Jump to the prompt → Join the Membership
Wright Mode — Free Guide

4 Free Plugins That Fix Generic AI Output

Claude writes like a chatbot, designs like every other AI site, and invents components badly. These four free add-ons fix all three, plus the setup you never did. One prompt installs the lot.

4 free tools One installer prompt Mac, Windows or Linux About 10 minutes Undo prompt included

What's inside

Open Claude Code, paste this, and it installs three of the four for you and reminds you to type the fourth. It reports back in plain English after each one, so you always know what just happened on your computer.

Before you paste

You need Claude Code open — Mac, Windows or Linux all work. Any folder is fine, but use the project you actually work in. It takes about ten minutes. Claude asks permission before each install, so say yes. One of them (21st) needs a free account, and the prompt stops and tells you when it gets there instead of guessing.

Install these four free Claude Code add-ons for me, one at a time, and tell me in plain English what you did after each one. Work out which operating system I am on first and use the right commands for it. Check whether each one is already installed before installing it. If a step fails, tell me what went wrong in one sentence and move on to the next one. Do not stop the whole job. 1. Impeccable (catches the design cliches that make a site look AI-made). Needs Node.js. Run: npx impeccable install Then tell me to type /impeccable init inside Claude Code so it can write a PRODUCT.md describing what I am building. Do not run /impeccable init yourself. 2. Humanizer (strips the tells that make writing sound like a chatbot). Run: npx skills add blader/humanizer --global If that fails, use the plugin route instead and tell me to type these two lines inside Claude Code: /plugin marketplace add blader/humanizer /plugin install humanizer@humanizer 3. 21st MCP (search and install real React and Tailwind components instead of letting Claude invent them). Run: npx @21st-dev/cli@latest init --client claude This one needs a free API key from https://21st.dev/mcp. Do NOT invent a key. When you get to that step, stop and tell me to go and get one, tell me it goes in an environment variable called API_KEY_21ST, and then wait for me. Once I give you the key, set it up properly for my operating system. 4. Claude Code Setup (Anthropic's own plugin that reads a project and tells you what it needs) has to be installed by me, not by you. At the very end, remind me to type this inside Claude Code: /plugin install claude-code-setup@claude-plugins-official When you are done, give me a four-line summary: each tool, installed or not, and the one thing I do next to use it.
2

Then type this inside Claude Code

Anthropic's official plugin installs from the plugin menu, not from the terminal. One line, hit enter, done. The claude-plugins-official marketplace is built in, so there is nothing to add first.

/plugin install claude-code-setup@claude-plugins-official

Only want one or two?

Paste the big prompt anyway and delete the numbered steps you do not want before you hit enter. Claude only installs what is left. If you are only doing one, make it Humanizer — it is the fastest to install and the difference is immediate.


Generic AI output is not one problem, it is four. The writing sounds like a chatbot. The design looks like every other AI site. The components get invented instead of used. And the project was never set up properly in the first place. Find yours below.

✍

"It writes like a bot"

Humanizer. Marks every AI tell in your text and rewrites it, holding your facts fixed. Paste a few paragraphs of your own writing and it copies your rhythm instead of its own.

🎨

"Everything it designs looks the same"

Impeccable. Runs 61 rules over your interface that catch the tells — purple-to-blue gradients, bounce easing, dark glows — and gives you the words to ask for something better.

🧩

"It invents components badly"

21st MCP. A searchable catalogue of real React and Tailwind components. Claude picks one that exists and installs it with its dependencies instead of writing a wonky one from scratch.

🧭

"I never set this project up"

Claude Code Setup. Anthropic's own plugin reads your project and tells you which hooks, skills, MCP servers and sub-agents would actually help here. It only recommends, so nothing can break.

The prompt installs all four. If you would rather go one at a time: Humanizer first because you will feel it immediately, then Claude Code Setup so you know what your project is missing, then Impeccable, then 21st the next time you are actually building an interface.


What each one actually does, a prompt to prove it is working, and the catch. Strictly speaking two are skills, one is a plugin and one is an MCP server. I am calling them all plugins because that is what they feel like.

1

Humanizer · strips the tells that make writing sound like AI

It reads your text, marks every AI tell it finds worst-first, then rewrites without touching your facts. The patterns come from Wikipedia's own field guide to spotting AI writing, grouped into five habits: staging instead of stating, rhythm by rule, inflated and borrowed authority, formatting by rule, and leftovers from the chat window.

The part most people miss is the voice matching. Paste two or three paragraphs of your own writing with the request and it follows your rhythm, your word choice, your punctuation and your deliberate quirks — dashes included, if you use them.

Humanize this. Keep every fact exactly as it is and do not add anything I did not write. Here is a sample of how I actually write, so match my rhythm, word choice and punctuation rather than your own: [paste two or three paragraphs of your own writing here] Here is the text to fix: [paste the AI-sounding text here] Before you rewrite, list the tells you found in order of how badly they give it away.

The catch: the pattern count keeps moving. It was 33, then 35, and as of 6 September 2026 it was rebuilt down to 25 patterns ordered by strength. So do not quote a number at anyone. Several patterns are tagged "weak alone" — em dashes, passive voice — because careful humans use them on purpose, so it will not strip yours if your writing sample uses them. It also refuses to invent: if a sentence needs a fact that is not there, it stops and asks you instead of smoothing over the gap. See it on GitHub →

2

Impeccable · catches the design cliches

It installs 23 slash commands that give you and Claude the same design vocabulary — /impeccable polish, audit, critique, bolder, quieter — so "make it less AI-looking" becomes something Claude can actually act on. Behind those sits a set of 61 rules that run on your machine with no model and no API key, flagging the tells: the purple-to-blue gradient, the bounce easing, the dark glow, cramped padding, tiny tap targets, line lengths nobody can read.

Run /impeccable init first. It writes a PRODUCT.md recording who your product is for and what it sounds like, and every later command reads it. Skip that step and the advice stays generic.

/impeccable init

Then point it at the page you like least:

/impeccable audit Then run /impeccable critique on my homepage. Tell me the three things making it look AI-generated, in the order a stranger would notice them, and fix the worst one.

The catch: a clean run is not proof your site looks good. The author says so himself — it "does not replace inspecting the rendered experience", it just means you have stopped making the obvious mistakes. It also works by subtraction. It has no library of beautiful sites to copy, it only knows what to stop doing. And the live editing mode only runs against a site on your own computer; for a published site you get a read-only check. See it on GitHub →

3

21st MCP · real components instead of invented ones

Ask Claude for a pricing table and it writes one from memory, which is how you end up with something that almost works. 21st gives it a catalogue to search instead — over 12,000 React components, marketing blocks, templates and shadcn themes — and it installs the one you pick with its dependencies, into your project, matching your existing setup.

It used to be called Magic MCP. That package still exists but it is now just a redirect, so install it with the 21st CLI line in the prompt above and ignore any tutorial older than this year.

Search 21st for a pricing table with a monthly and annual toggle. Show me three options with what is different about each, wait for me to pick one, then install it and match it to the fonts and colours already in my project.

The catch: this is the one with a real limit. Searching and browsing all 12,000 is free, but the free tier lets you actually copy two components a day. After that you are paying. The AI generation feature is a separate paid credit add-on on top of that. Two a day is genuinely enough to build something over a week, but do not plan a whole site for a Sunday afternoon. Old Magic API keys were also reset, so if you set this up before this year, get a new one. See 21st.dev →

4

Claude Code Setup · Anthropic's own setup check

This one is made by the people who make Claude Code. It reads your project — your dependency files, your folder structure, your existing CLAUDE.md and test config — and comes back with the top one or two things worth adding in each category: MCP servers, skills, hooks, sub-agents and slash commands. Instead of installing whatever went viral this week, you find out what your project is actually short of.

After install nothing looks different. The change is that you can ask Claude what to set up instead of guessing.

Recommend automations for this project. Which hooks, skills, MCP servers, sub-agents and slash commands would actually help me here, and why? One plain-English sentence each, and tell me which one to set up first.

The catch: it reads, it does not build. Anthropic's own documentation says it plainly — the skill is read-only, it analyses and outputs recommendations and it creates or modifies nothing. You still say yes to each suggestion and get Claude to set it up in a separate step. It also holds itself to one or two ideas per category so you are not buried. If you want more, ask for one type at a time — "what hooks should I use for this repo?" gets you a longer list. See the plugin on GitHub →


None of this is permanent. If you want to start clean, paste this and Claude removes all four and puts your settings back.

Remove the four add-ons you installed for me and put things back the way they were. Show me a checklist as you go. 1. Uninstall Impeccable. Check whether it left an edit hook in my Claude Code settings and remove that too. Leave any PRODUCT.md file alone but tell me where it is so I can decide. 2. Remove the Humanizer skill. If it went in with npx skills add, remove it the same way; if it went in as a plugin, remind me to remove it from the /plugin menu myself. 3. Remove the 21st MCP server from my Claude Code MCP config, and delete the API_KEY_21ST environment variable from my shell profile. 4. Remind me to remove claude-code-setup from the /plugin menu inside Claude Code myself. Do not delete any components or code that 21st installed into my project. When you are done, tell me in one line whether anything is left over.

Keep whatever solved a real problem and bin the rest. Most people end up keeping Humanizer and Claude Code Setup and dropping the other two once the novelty wears off. That is a perfectly good place to land.


Ready to go deeper?

Where to go from here.