agentleFS
giandemoncell-proggiandemoncell-prog/claude-skills/claude-code-setup/SKILL.md

claude-code-setup

Skill0 starsChanged 6 months agoMITView on GitHub

Guide the initial setup of Claude Code on a new machine or for a new user. Use whenever someone asks how to install Claude Code, configure it for the first time, set up their API key, create a CLAUDE.md, configure settings.json, set up memory, install plugins or skills, or get started with Claude Code from scratch. Also triggers for "set up Claude Code", "configure Claude CLI", "first time Claude Code", "onboard to Claude Code".

  • Pipes a download into a shell
  • Reads credentials
  • Installs packages

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. jt247/claude-code-setup★ 2same name
    2. elearningplugins/brians-agent-skills★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repositoryOne other file it gives its agents.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask which platform first, then follow the relevant path.

    line 15
  2. Very specific:

    Run /init in the project root — Claude scans the codebase and drafts it automatically.

    line 93

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Claude Code Initial Setup

Guide a complete first-time setup of Claude Code: installation, API key, project context, settings, memory system, and skills.


Phase 1: Install

Ask which platform first, then follow the relevant path.

macOS

brew install claude
# or via npm:
npm install -g @anthropic-ai/claude-code

Linux / ChromeOS (Linux container)

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

Requires Node.js ≥ 18. Install via nvm if needed:

curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.7/install.sh | bash
nvm install --lts

Windows

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

Or use WSL2 and follow the Linux path. Claude Code works natively on Windows via PowerShell.

Verify: claude --version


Phase 2: API Key

Two options — pick based on whether they have a key already.

Option A — interactive (easiest):

claude  # first run prompts for the key automatically

Option B — environment variable:

# Add to ~/.bashrc / ~/.zshrc / PowerShell profile
export ANTHROPIC_API_KEY="sk-ant-..."

On Windows (PowerShell profile):

$env:ANTHROPIC_API_KEY = "sk-ant-..."
# To persist across sessions, add to $PROFILE

Get a key at: console.anthropic.com → API Keys


Phase 3: First Run

cd /path/to/your/project
claude

Key commands to know from the start:

CommandWhat it does
/helpShow all commands
/initCreate a CLAUDE.md for the current project
/configOpen settings (model, theme, etc.)
!<cmd>Run a shell command and pipe output into context
#Auto-save a learning to CLAUDE.md mid-session
Ctrl+CCancel current operation
Ctrl+DExit

Phase 4: CLAUDE.md (Project Context)

CLAUDE.md tells Claude about your project so it doesn't have to re-discover things every session.

Run /init in the project root — Claude scans the codebase and drafts it automatically. Then review and trim.

What belongs in CLAUDE.md:

  • Build / test / run commands
  • Directory structure overview
  • Non-obvious conventions or gotchas
  • Required environment variables

What does NOT belong:

  • Things obvious from reading the code
  • Generic best practices
  • Anything already in .gitignore patterns

File hierarchy (all are auto-loaded):

~/.claude/CLAUDE.md          # global — applies to all projects
<project>/CLAUDE.md          # project — checked into git, shared with team
<project>/.claude.local.md   # local — gitignored, personal overrides

Phase 5: Settings

Settings live in JSON files — edit them via /config or directly.

~/.claude/settings.json          # global (all projects)
<project>/.claude/settings.json  # project-level overrides

Most useful settings to configure on first setup:

{
  "model": "claude-sonnet-4-6",
  "theme": "dark",
  "autoUpdates": true,
  "permissions": {
    "allow": [
      "Bash(git *)",
      "Bash(npm *)",
      "Bash(python *)"
    ]
  }
}

Permission modes (toggle with /permission):

  • default — asks before most tool calls
  • acceptEdits — auto-approves file edits, asks for shell
  • bypassPermissions — auto-approves everything (use only in trusted projects)

Phase 6: Memory System (optional but recommended)

Claude Code has a file-based persistent memory at ~/.claude/projects/<project-slug>/memory/.

Set it up by adding to ~/.claude/CLAUDE.md:

# Memory
Persistent memory lives at ~/.claude/projects/<project>/memory/.
Always read MEMORY.md at the start of a session to recall prior context.

Each memory file has frontmatter:

---
name: short-slug
description: one-line summary
metadata:
  type: user | feedback | project | reference
---
Content here.

MEMORY.md is the index — one line per memory file, always kept ≤ 200 lines.

Types:

  • user — who the user is, their role, preferences
  • feedback — corrections and confirmed approaches
  • project — goals, decisions, deadlines, architecture choices
  • reference — pointers to external resources (Linear, Notion, dashboards)

Phase 7: Skills & Plugins

Install a skill (adds capabilities invoked by natural language):

claude skill install https://github.com/<user>/<skill-repo>

Install a plugin (adds commands, agents, MCP servers):

claude plugin install @anthropic/claude-md-management
claude plugin install @anthropic/code-review

List installed: claude skill list / claude plugin list

Recommended for most setups:

  • @anthropic/claude-md-management — audit and improve CLAUDE.md files
  • @anthropic/code-review — review diffs before committing

Phase 8: IDE Integration (optional)

VS Code: Install the "Claude Code" extension from the marketplace. Opens a Claude panel inside VS Code, shares file context automatically.

JetBrains (IntelliJ, PyCharm, WebStorm, etc.): Install "Claude Code" from the JetBrains Marketplace.


Checklist

  • claude --version works
  • API key set and claude opens without errors
  • CLAUDE.md created in the project root (/init)
  • Global ~/.claude/CLAUDE.md created with personal preferences
  • ~/.claude/settings.json configured (model, permissions)
  • Memory directory exists: ~/.claude/projects/<slug>/memory/
  • At least one useful plugin or skill installed
  • IDE extension installed (if applicable)

Quick Reference Card

Print or save this for daily use:

claude                  start a session in current dir
claude "do X"          one-shot task, no interactive session
claude --continue      resume last conversation
/init                  create CLAUDE.md for this project
/config                open settings
/help                  list all commands
# <note>              save a learning to CLAUDE.md
! <cmd>               run shell command in context
Ctrl+C                 cancel
Ctrl+D                 exit

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.