Install 5 Claude skills every beginner needs, and when to use each

Start here: paste this into Claude Code

If you don't have Claude Code yet, do the first two steps under “Before you start” below (Node.js and Claude Code). Then make a folder for your marketing work, start Claude in it, and paste the prompt. It installs all five, runs a first test that sends nothing anywhere, and hands you a cheat sheet.

The setup prompt (copy all of it) · lines 1-1 of 31. Copy all copies the whole prompt; read it in full on the page.

Hi Claude. Please be my patient setup helper. I run a business and I don't code: one step at a time, tell me exactly what to type or click, and wait for me before the next step.

How the pieces connect

This is the manual way: every step and every command. Claude follows it too.

The five don't plug into each other, but they line up nicely on one real job, like a new service page:

Words you'll see

• Skill: a folder with a SKILL.md file: instructions that teach Claude one job.
• Slash command: typing / and a skill's name in Claude Code (like /humanizer) to run that skill on purpose. Most skills also kick in on their own when what you ask fits them.
• Terminal: the window where you type commands (Terminal on a Mac, PowerShell on Windows).

• Node.js and npx: Node.js runs JavaScript programs on your computer; npx comes with it and downloads and runs a tool in one go.
• Skills CLI: the free command-line tool that installs, lists, updates and removes skills. You run it as npx skills.

• Global (-g) vs project: global means every folder on your computer (~/.claude/skills; the ~ is your home folder). Without -g, the skill goes in .claude/skills inside the folder you're in, and only works there.
• Tokens and limits: tokens are the chunks of text Claude reads and writes. Longer answers use more of them, and your plan's usage limit runs out faster.

Which one, when

From each skill's own README and SKILL.md, checked 2026-10-31.

Before you start: Node.js and Claude Code

Install Node.js (22.20 or later)

The Skills CLI needs Node.js 22.20 or later. Download the LTS version (the long-term support one) and run the installer. Then open a new terminal window and check the version.

Install Claude Code and log in

Skip this if claude --version already prints a version. Claude Code needs a paid plan (Pro or higher); the free Claude plan doesn't include it. The first time you run claude, it opens your browser to log in.

1. Humanizer: strip the AI tells out of your writing

Made by blader, MIT license. It's built on Wikipedia's Signs of AI writing, the field guide Wikipedia's editors use to catch undisclosed AI text. It checks for 26 patterns, strongest first: “it's not just X, it's Y”, one-line closers like “Let that sink in.”, deep-sounding sayings, staged run-ups, stock AI words like “testament” and “delve”, and dashes everywhere.

Two things I like about it. It doesn't make anything up: if a sentence needs a name, a number or a date it doesn't have, it asks you instead of inventing one. And it's upfront that it edits for readers, not to sneak past AI detectors; its README says detectors still flag most of its output.

Install it

This is the command from Humanizer's own README for Claude Code through the Skills CLI.

npx skills add blader/humanizer --global --agent claude-code

Use it

Type /humanizer, then paste your text. You get its first rewrite, a short note on anything that still sounds off, and the final version. To make it sound like you, give it two or three paragraphs you wrote yourself first. Point it at a file and it changes the writing only, leaving code, data and links alone.

Match your voice

/humanizer

Here's a sample of my writing for voice matching:
[paste 2-3 paragraphs you wrote yourself]

Now rewrite this text:
[paste the AI text]

2. Skill Creator: turn a job you repeat into your own skill

Made by Anthropic (the company behind Claude), Apache 2.0 license. Its job, in its own words: create new skills, improve existing ones, and test how well they work. You tell it the job, it drafts the SKILL.md, writes a few test prompts, runs them, shows you the results and rewrites the skill from your feedback.

The testing part runs small Python scripts and takes a while. If you just want the skill written, say so: its own instructions tell it to skip the formal tests when you'd rather just work through it together.

Install it

From Anthropic's skills repo, just this one skill.

npx skills add anthropics/skills --skill skill-creator -g -a claude-code

Or the plugin way

Claude Code's own docs install it as a plugin instead (a plugin is a bundle Claude Code installs from a marketplace). Type this inside Claude Code. Pick one way, not both. As a plugin, its slash command gets the plugin's name in front; asking for skill-creator by name works either way.

Use it

Tell it the job and where it should live: ~/.claude/skills for every folder, or .claude/skills for this project only.

Make a skill from a job you repeat

/skill-creator
I keep asking you to <the job, e.g. turn my inspection notes into a short homeowner summary>. Make it a skill in ~/.claude/skills. Ask me how I do it, one question at a time, then show me the SKILL.md before you save it. Skip the formal tests for now; we'll try it on one real job together.

3. Grill Me: get your plan questioned before anything gets built

Made by Matt Pocock, MIT license. He calls it one of his most popular skills, and it's for non-code plans too. You tell it what you want to do, and it interviews you in rounds: numbered questions, each with its own recommended answer (so “yes” takes the recommendation), until every decision in your plan is settled. It won't act on the plan until you confirm you're on the same page.

One thing most install videos miss: grill-me is a two-line skill that hands off to a second skill called grilling, which holds the actual questioning. You need both, which is why the command names both.

Install it (both parts)

npx skills add mattpocock/skills --skill grill-me --skill grilling -g -a claude-code

Or the whole set as a plugin

Matt's README installs every one of his skills (27 listed in his README, most of them for software work) as a plugin that updates itself. If you go this way, skip the command above: his README warns that installing both ways gives you every skill twice. His /setup-matt-pocock-skills step is for his engineering skills, not Grill Me.

Use it

It only starts when you type /grill-me: Claude won't fire it on its own. Answer each round; say “yes” to take its recommendations.

4. Caveman: shorter answers, so your limit lasts longer

Made by Julius Brussee, Apache 2.0 license. The joke in the video is “me read file, me fix bug”. The real skill is less cartoon than that: its rules say answer first, cut the greeting and the recap, short sentences, and no “me think” theater.

It never drops words like not, never or only, keeps numbers and commands exactly as they are, and switches back to full sentences for security warnings and anything you can't undo. Once on, it stays on for the whole session until you say “stop caveman” or “normal mode”.

The rules themselves cost about 1,160 tokens to load, and those numbers are from an older version of its rules. I like that they publish this. Use it on long sessions where you keep hitting your limit, not while you're still learning, because short answers are harder to follow.

Install the skill only

This is the “skill alone” route from Caveman's README, narrowed to the one caveman skill (the repo holds many others).

npx skills add JuliusBrussee/caveman --skill caveman -g -a claude-code

Skip the full install for now

Caveman's headline install (npx @caveman-ai/cli@latest) goes a lot further: it sets up every coding app it finds on your computer, sends usage stats by default, and one of its features (Auto, which picks the model for you) needs an account. That's a bigger decision than a beginner needs to make. The skill alone runs on your computer and sends nothing.

Turn it on and off

/caveman
...
stop caveman

Example (made up). Normal: “Sure! I'd be happy to help. The reason your contact form isn't sending emails is most likely that the email setting was left blank when the form was set up.” Caveman: “Form email not sending. Email setting blank. Fill it in, then send a test.”

5. Marketing Skills: 53 skills for copy, SEO, ads and email

Made by Corey Haines, MIT license. On 2026-10-31 the repo had 53 skill folders: copywriting, SEO audits, ads and ad creative, emails, landing pages (cro), pricing, referrals, schema, cold email and more.

The one to run first is product-marketing: it interviews you about your business, customers and how you talk, and saves it as .agents/product-marketing.md in your folder. Every other skill reads that file first, so you stop explaining your business every time.

Fifty-three skills is a lot to load everywhere, so I'd put them in one marketing folder only (no -g). Claude Code loads a short description of every skill into each conversation, and when there are too many it starts cutting descriptions, which makes it worse at picking the right one.

Install them in your marketing folder

Run this from inside ~/marketing. --skill '*' means all of them; -a claude-code makes sure they land where Claude Code reads them (its README warns they can end up in a folder Claude Code doesn't read otherwise).

Set up your business once

Start claude in ~/marketing and run this. With no website code in the folder, pick “start from scratch” and it walks through it with you, one section at a time.

Use them

Ask for the job in plain English and Claude picks the skill that fits, or call one by name: /copywriting, /seo-audit, /emails, /ads, /cro. Some skills point to paid tools for data; the README lists four sponsored partners and says they don't change what the core skills recommend. You don't need any of them to start.

Check they're all there

npx skills ls -g      # the four global ones
cd ~/marketing
npx skills ls         # the Marketing Skills in this folder

Then start claude in ~/marketing and type /skills: you should see all five. Claude Code picks up new skills without a restart. The one exception: if ~/.claude/skills didn't exist when your session started, type /reload-skills once.

First test: a made-up paragraph through Humanizer (nothing gets sent)

This runs on your Claude plan with nothing posted, sent or published. Paste it into Claude Code:

Prompt: first test

/humanizer

Example (made up): In today's fast-paced world, your roof is more than just a roof. It's a testament to your home's resilience. At Example Roofing Co., we don't just install roofs; we deliver peace of mind, quality, and excellence. Our team is passionate about elevating every homeowner's experience. Let that sink in.

Good: it should flag the “more than just a roof” and “don't just install roofs” lines, the “testament” and “passionate about elevating” filler, the “peace of mind, quality, and excellence” list of three and the “Let that sink in.” closer, and the rewrite is shorter and plain.

It may ask you for a real fact to put in place of the fluff (how long you've been in business, what you actually install). That's it refusing to make one up. Bad: Claude rewrites it without listing what it changed. Then the skill isn't loading: type /skills and check humanizer is there.

Then try /grill-me on something small you're actually planning. It costs you a few minutes of answering questions, and it's the quickest way to see what it does.

Real use: prompts for real jobs

1. A service page, start to finish

/grill-me
I want a new page on my website for <the service>. Grill me on who it's for, what it should get them to do, and what proof I actually have. Don't write anything yet.

(after the grilling)
/copywriting
Write the page from what we just settled. Use only facts I gave you: no made-up reviews, numbers or guarantees, and no promises about Google rankings. Then run /humanizer on it and show me both versions.

Keep them updated (and remove one)

Skills installed with the Skills CLI don't update themselves. Check now and then:

Check, update, remove

npx skills check                    # anything to update?
npx skills update -g                # update your global skills
cd ~/marketing && npx skills update -p   # update the Marketing Skills
npx skills remove --global caveman  # take one off (any skill name works)

The Skills CLI sends anonymous usage data by default. Set either of these to 1 to switch it off:

What it costs

Checked 2026-10-31 on claude.com/pricing and each repo. Prices change: check before you buy.

The real cost is your plan's usage limit. Every skill runs on it, and a long Grill Me session or a Skill Creator test run uses a good chunk. That's where Caveman earns its spot. And watch one thing: the skills are free, but a skill can point Claude at a paid tool (an SEO data service, an ad account). If one asks for a key or an account, stop and read why before you go on.

When it breaks

The official docs behind every claim

• Humanizer (blader/humanizer)
• Humanizer SKILL.md
• Wikipedia: Signs of AI writing
• Skill Creator SKILL.md (anthropics/skills)
• Anthropic skills repo
• Claude Code: Skills
• Matt Pocock's skills (README)
• grill-me SKILL.md
• grilling SKILL.md

• Caveman (JuliusBrussee/caveman)
• Caveman SKILL.md
• Marketing Skills (coreyhaines31/marketingskills)
• product-marketing SKILL.md
• Skills CLI (vercel-labs/skills)
• Skills CLI reference
• Claude Code: Advanced setup
• Claude: Plans and pricing
• Node.js: Download

What each page backs up is listed at the end of the full guide.

That's the five

Five free skills, five commands, and now you know which one to grab: Grill Me before you build, Marketing Skills to draft, Humanizer before it goes out, Skill Creator once you've done it twice, and Caveman when your limit's running low.

Want help setting this up? Receipts Group builds these systems.

Open the full guide as a page (every file in full, plus the table of contents).