<aside> 🤍

Hey, it's Cindy 🤍 This is the full walkthrough of the 7 Claude skills running my whole content engine: every install command, every API key, every skill file.

</aside>

If you caught my reel breaking down the 7 Claude skills running my whole content engine, this is the full walkthrough. Every install command, every API key, every skill file. No vague one-liners, no skipped steps.

By the end you'll have Claude installed, all 7 skills ready to call, and a real production system covering research, writing, voice consistency, video, audio, ad intelligence, and persistent memory.

Step 1: pick your Claude

There are three ways to use Claude. All three support skills. The skill content itself is identical everywhere, only the way you add it differs.

Surface What it is Use when
Claude.ai Browser app at claude.ai Easiest to start, no download. Works for skills that don't need to touch files on your computer.
Claude Desktop Mac/Windows app Recommended for most people. Reads and writes files on your computer, so almost every skill works.
Claude Code Terminal version (CLI) The most powerful. Run video renders and audio stitching directly from chat.

Quick rule: if you've never opened a terminal and don't want to start, use Claude Desktop. It covers about 95% of this guide with a friendlier interface.

Install Claude Desktop (recommended)

  1. Go to claude.ai/download
  2. Run the installer
  3. Open the app, log in with your Claude account

Done.

Install Claude Code (only if you want full power)

On Mac: Press Cmd+Space, type "Terminal," hit Enter. Install Node.js from nodejs.org if you don't have it. Then in Terminal:

npm install -g @anthropic-ai/claude-code
claude

On Windows: Open PowerShell. Install Node.js from nodejs.org with "Add to PATH" checked. Then run the same two commands above. Verify with claude --version.

Step 2: how skills work

A skill is a folder with one markdown file inside (SKILL.md). The format is identical across all three Claudes, so you build the SKILL.md once and use it anywhere.

Each one starts with YAML frontmatter:

---
name: voice-dna
description: Analyze writing samples and extract a reusable voice profile. Use when the user wants to capture their writing voice.
tools: Read, Write
---

(skill instructions go here)