Agent skill

New Mac Setup

by swyxio in swyxio/skills

Fully automated new Mac setup for fullstack web developers and AI engineers.

MITAuto-check passedDevOps & Cloud

Install New Mac Setup

skills CLI
$ npx skills add swyxio/skills --skill new-mac-setup -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install swyxio/skills new-mac-setup --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/swyxio/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/new-mac-setup .claude/skills/new-mac-setup && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
new-mac-setup
GitHub stars
175
Token cost
~4.3k tokens
SKILL.md length
1,708 words
Files
11 (incl. scripts)
Skills in repo
89
Repo updated
First seen
Licence
MIT

At a glance

Fully automated new Mac setup for fullstack web developers and AI engineers.

  • Works in 3 steps: Interview the User → Generate the Scripts → Execute
  • Someone says set up my Mac
  • SKILL.md covers Philosophy, How to Use This Skill, Lessons Learned (Bugs to Avoid) and Default Package Lists, plus 6 more sections
  • Runs Shell scripts from its folder; calls brew, uv and bash; needs HF_TOKEN

What it does

New Mac Setup is an agent skill from swyxio/skills. Fully automated new Mac setup for fullstack web developers and AI engineers. Generates and executes idempotent shell scripts to install dev tools, CLI utilities, GUI apps, AI/ML tooling, shell config, and macOS preferences — all via Homebrew, fnm, uv, and defaults commands. Use this skill whenever someone says "set up my Mac", "new Mac setup", "configure my dev machine", "install my dev tools", "fresh Mac install", "developer environment setup", or anything about bootstrapping a macOS machine for development…

Its SKILL.md is about 4.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 11 other files, including scripts (for example `README.md`, `scripts/00-run-all.sh` and `scripts/01-xcode-and-homebrew.sh`). Compatibility notes: Requires macOS on Apple Silicon (M1/M2/M3/M4). Scripts use Homebrew, which handles all dependencies. Bash 3.2+ (ships with macOS). Internet connection…

It sits in DevOps & Cloud, covering Shell scripting and Containers. It works with Homebrew, Python, macOS and Bash. The repository describes itself as: Agent skills for Claude Code and other AI agents. The licence is MIT.

When your agent uses it

  • Someone says set up my Mac
  • Configure my dev machine
  • Install my dev tools
  • Fresh Mac install

Example prompts

  • “set up my Mac”
  • “new Mac setup”
  • “configure my dev machine”
  • “/new-mac-setup”

Requirements

  • Python 3
  • Node.js
  • A Bash shell
  • Docker
  • Compatibility (from SKILL.md): Requires macOS on Apple Silicon (M1/M2/M3/M4). Scripts use Homebrew, which handles all dependencies. Bash 3.2+ (ships with macOS). Internet connection required for package downloads.

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. Interview the User
  2. Generate the Scripts
  3. Execute

What it can do on your machine

Read from SKILL.md and the folder at commit 038ef34. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 8 files in scripts/ (Shell), which the agent can run.

    Shell commands in SKILL.md call:

    • brew
    • uv
    • bash
    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • github.com
    • wispr.com
    • superwhisper.com
    • telestream.net
    • tella.tv
    • appquitter.com
    • clipbook.app

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • HF_TOKEN

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

  • Compatibility

    Requires macOS on Apple Silicon (M1/M2/M3/M4). Scripts use Homebrew, which handles all dependencies. Bash 3.2+ (ships with macOS). Internet connection required for package downloads.

    From compatibility in the SKILL.md frontmatter.

Context cost

New Mac Setup loads about 4.3k tokens when it runs. Until then it costs about 208 tokens; SKILL.md has 1,708 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~208
When it runs · the whole SKILL.md, loaded when a task matches
~4.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from swyxio/skills at commit 038ef34, republished under its MIT licence (© swyxio). 1,708 words, ~4,317 tokens.

Download SKILL.mdSave it as .claude/skills/new-mac-setup/SKILL.md (or your agent's skills folder). This skill also uses 10 other files; get the full folder from GitHub.
name
new-mac-setup
description
Fully automated new Mac setup for fullstack web developers and AI engineers. Generates and executes idempotent shell scripts to install dev tools, CLI utilities, GUI apps, AI/ML tooling, shell config, and macOS preferences — all via Homebrew, fnm, uv, and defaults commands. Use this skill whenever someone says "set up my Mac", "new Mac setup", "configure my dev machine", "install my dev tools", "fresh Mac install", "developer environment setup", or anything about bootstrapping a macOS machine for development. Also trigger when someone mentions setting up Homebrew, Oh-My-ZSH, Node.js, Python, Docker, or terminal configuration on a new Mac — even if they don't call it a "setup". This skill is opinionated and based on real-world experience setting up M-series Macs for fullstack JS/TS + Python + AI development.
compatibility
Requires macOS on Apple Silicon (M1/M2/M3/M4). Scripts use Homebrew, which handles all dependencies. Bash 3.2+ (ships with macOS). Internet connection required for package downloads.
license
MIT
metadata.author
swyxio
metadata.version
2.0
metadata.last-updated
2026-06-13
metadata.hardware
Apple Silicon (M-series)
metadata.primary-stack
TypeScript, Python, AI/ML

New Mac Setup

This skill generates and runs a complete, idempotent Mac setup for fullstack web development and AI engineering. It produces 8 shell scripts that can be run individually or via a master runner, plus dotfiles and macOS preference automation.

The scripts are designed to be re-runnable — they check whether each tool is already installed before attempting installation, so you can safely run them again if something fails partway through.

Philosophy

The setup is opinionated. The core opinions:

  • Terminal: Ghostty (fast, GPU-accelerated, Zig) + cmux (vertical tabs, split panes, socket API for AI agents). cmux reads Ghostty's config, so one config file serves both.
  • Shell: ZSH with Oh-My-ZSH, powerlevel10k theme, zsh-autosuggestions, zsh-syntax-highlighting
  • Node: fnm (not nvm — fnm is faster), pnpm and bun for package management/runtime
  • Python: uv from Astral (not pyenv, not pip, not conda — uv is dramatically faster and handles both venvs and package installs)
  • Docker: Colima (not Docker Desktop — lighter weight, CLI-native, free)
  • Editor: Cursor (AI-native editor)
  • AI tools: Claude Code, Codex CLI, Antigravity CLI (agy via the antigravity Homebrew cask), Railway CLI, Ollama for local models
  • Transcription/diarization: ffmpeg + yt-dlp + MLX Whisper for fast local ASR, plus a Python 3.11 pyannote.audio environment for proper speaker diarization when HF_TOKEN is configured. Diarization should default to GPU/cloud paths; do not burn local CPU on long diarization unless explicitly requested.
  • Agent notifications: peon-ping shared across Claude Code, Codex, and Cursor, tuned to notify only when useful
  • Browser: Dia (from The Browser Company, successor to Arc)
  • Launcher: Raycast (replaces Alfred, Spotlight, Caffeine, window management)
  • Voice: Wispr Flow for voice-to-text
  • Screenshots: Shottr (includes OCR) by default; also recommend Screendrop for local-first screenshot/screen recording, annotation, capture history, and optional Cloudflare-backed sharing.

How to Use This Skill

Step 1: Interview the User

Before generating scripts, ask the user a few questions to customize the setup. Key things to learn:

  1. Git identity: name and email for git config
  2. Hardware: Which Mac model / how much RAM? (affects which Ollama models to pull)
  3. What to skip: Do they want everything, or should certain categories be excluded? (e.g., "no Elixir", "no PostgreSQL", "I use Docker Desktop not Colima")
  4. Additions: Any apps or tools not in the default list?
  5. Terminal preference: Ghostty + cmux is the default, but they may want something else

For RAM-based Ollama model recommendations:

  • 8GB: qwen3.5:4b, qwen2.5-coder:3b
  • 16GB: qwen3.5:9b, qwen2.5-coder:7b
  • 24GB: qwen3.5:27b, qwen2.5-coder:14b (best sweet spot)
  • 32GB+: qwen3.5:35b, qwen2.5-coder:32b
Step 2: Generate the Scripts

Generate 8 scripts into the user's chosen directory. Each script is standalone and idempotent. Use the templates in scripts/ as the base, customizing per the user's answers.

The scripts should run in this order:

01-xcode-and-homebrew.sh   # Xcode CLI tools + Homebrew (15-25 min)
02-shell-setup.sh          # Oh-My-ZSH + plugins + fonts
03-brew-packages.sh        # All brew formulae + cask apps
04-dev-environment.sh      # Node (fnm), Python (uv), Git, Docker
05-ai-tools.sh             # Claude Code, Codex CLI, Antigravity CLI, Ollama models, llama.cpp
06-dotfiles.sh             # .zshrc + Ghostty config
07-macos-settings.sh       # System preferences via defaults commands
00-run-all.sh              # Master runner (runs 01-07 in order)
Step 3: Execute

If possible, execute the scripts directly. If running in a VM/sandbox that can't reach the user's Mac, write the scripts to the workspace folder and put a one-liner in the clipboard:

bash
cd /path/to/scripts && chmod +x ./*.sh && bash ./00-run-all.sh

Lessons Learned (Bugs to Avoid)

These are real issues encountered during testing. The scripts in scripts/ already incorporate these fixes, but if you're generating fresh scripts, keep these in mind:

  1. fnm needs sourcing before npm works. After installing Node via fnm, the current shell doesn't have npm in PATH until you run eval "$(fnm env --use-on-cd)". Every script that uses npm/node must source fnm first.

  2. Don't use set -e in the master runner. If one script fails (e.g., a brew cask 404s), set -e kills the entire pipeline. Individual scripts can use set -e if they handle errors gracefully, but the master runner should not.

  3. Source brew and fnm in the master runner. Add these lines near the top of 00-run-all.sh so all child scripts inherit them:

    bash
    eval "$(/opt/homebrew/bin/brew shellenv)" 2>/dev/null || true
    eval "$(fnm env --use-on-cd)" 2>/dev/null || true
  4. Smart quotes break shell commands. If writing commands to the clipboard, avoid curly/smart quotes. Use simple ASCII quotes only, or avoid quotes entirely where possible. The safest clipboard commands are single simple statements like bash ./07-macos-settings.sh.

  5. Zoom and some casks require sudo. The Zoom installer triggers a Password: prompt. The user needs to be warned that some cask installs will pause for their password.

  6. brew install yarn --ignore-dependencies is needed if Node is managed by fnm (not brew). Otherwise brew tries to install its own Node as a yarn dependency.

  7. Ghostty config location: ~/.config/ghostty/config. cmux reads this same file.

Default Package Lists

Homebrew Formulae (CLI tools)
# Core dev tools
gh, git, fnm, pnpm, bun, z, diff-so-fancy

# Languages & runtimes
elixir, erlang, python@3.13

# Docker (no Docker Desktop)
colima, docker, docker-completion

# Media & processing
ffmpeg, yt-dlp, tesseract, libsndfile

# Build dependencies
openssl@3, readline, sqlite, xz, zstd

# Databases
postgresql@14, rabbitmq

# Misc CLI
honcho, pipx, flyctl, entr, tig, mas, terminal-notifier, googleworkspace-cli

# Google Workspace
googleworkspace-cli installs the `gws` binary; auth still requires `gws auth setup` and `gws auth login`.

# Libraries
cairo, glib, harfbuzz, libvmaf, webp
Homebrew Casks (GUI apps)
# Terminal
ghostty

# Editors
cursor, visual-studio-code

# Browser
thebrowsercompany-dia

# Communication
slack, discord, zoom

# Productivity
raycast, rectangle, obsidian, notion, notion-calendar

# AI & ML
ollama, antigravity

# Media
vlc, audacity, tella, descript

# Utilities
shottr, notunes, caffeine, stretchly, quickshade, pure-paste, 1password

# Dev tools
beeper, superhuman, gcloud-cli

Plus cmux via: brew tap manaflow-ai/cmux && brew install --cask cmux

gcloud-cli installs Google Cloud CLI (gcloud). Keep /opt/homebrew/share/google-cloud-sdk/bin on PATH so additional SDK components are available after install.

Claude-Suggested Additions (March 2026)

These tools were suggested by Claude during the initial setup session and accepted by the user. They are now part of the default install in 03-brew-packages.sh:

  1. fzf — Fuzzy finder that transforms shell history (Ctrl+R), file search, and git branch selection. Pairs perfectly with zsh-autosuggestions. brew install fzf
  2. ripgrep (rg) — Blazingly fast grep replacement. Respects .gitignore, searches recursively by default. Essential for any developer. brew install ripgrep
  3. bat — cat with syntax highlighting, line numbers, and git integration. Makes reading code files in terminal beautiful. brew install bat
  4. zoxide — Drop-in z replacement with a smarter frecency algorithm and fuzzy matching. Same muscle memory, better results. brew install zoxide
  5. Orbstack — Even lighter than Colima for Docker containers and Linux VMs. Has a nice GUI and near-instant startup. brew install --cask orbstack
Global npm Packages
undollar, npm-check-updates, trash-cli,
@anthropic-ai/claude-code, @openai/codex, @railway/cli
Antigravity CLI

Install Google Antigravity through Homebrew:

bash
brew install --cask antigravity

The cask installs the desktop app and exposes agy as the Antigravity CLI. Prefer this over Gemini CLI for new setups: Google announced on May 19, 2026 that consumer Gemini CLI access for free, Google AI Pro, and Ultra users stops serving requests on June 18, 2026. Enterprise and paid API-key Gemini CLI access can remain available, but this new-Mac path should default to Antigravity CLI.

Show full SKILL.md (757 more words)Show less
Transcription And Diarization Defaults

Install the local transcription stack on new AI/dev Macs because it is useful for meetings, podcasts, YouTube/video workflows, and searchable archives.

Add this to 03-brew-packages.sh / 04-dev-environment.sh generation:

bash
brew install ffmpeg yt-dlp libsndfile
uv tool install mlx-whisper || true

mkdir -p "$HOME/.local/share/transcribe-anything"
uv venv --python 3.11 "$HOME/.local/share/transcribe-anything/.venv-pyannote"
uv pip install --python "$HOME/.local/share/transcribe-anything/.venv-pyannote/bin/python" \
  "pyannote.audio" soundfile

Guidance for generated docs:

  • mlx_whisper is the preferred local ASR path on Apple Silicon when available.
  • pyannote.audio direct is the preferred diarization path when HF_TOKEN is configured and the user has accepted Hugging Face model terms, but run it on CUDA/cloud GPU for long files.
  • Users must accept terms for pyannote/speaker-diarization-community-1 and pyannote/segmentation-3.0, then set HF_TOKEN in their shell or secret manager. Never bake tokens into generated setup scripts.
  • CPU pyannote on macOS is opt-in only for short tests. For real meeting/podcast diarization, use CUDA/cloud GPU or a managed diarization API such as Deepgram/AssemblyAI.
  • Do not rely on simple Resemblyzer/librosa clustering of Whisper segments for production diarization; it commonly collapses multi-speaker meetings into one speaker.
peon-ping Defaults

When setting up AI tools on a new Mac, also install and configure peon-ping with these defaults:

  • Install globally with the shared runtime under ~/.claude/hooks/peon-ping/ so Claude Code, Codex, and Cursor can all use the same install.
  • Register Claude Code hooks normally via the installer.
  • Register Codex manually in ~/.codex/config.toml:
    toml
    notify = ["bash", "/Users/$USER/.claude/hooks/peon-ping/adapters/codex.sh"]
  • Keep Cursor hooked up if ~/.cursor/ exists.
  • Use default_pack: "peon" as the fallback pack.
  • Install this rotation pool: glados, jarvis, r2d2, peasant, sc_kerrigan, sc_scv, sc_marine, sc_raynor, sc_ghost, sc_terran, protoss, sc2_alarak, sc2_abathur, ra2_eva_commander, ra2_kirov, ra2_yuri, ra_soviet, ccg_gla_worker, ccg_us_dozer, ccg_china_dozer
  • Set pack_rotation_mode to round-robin.
  • Set volume to 0.2.
  • Keep desktop_notifications enabled, but use notification_style: "standard" rather than large overlays.
  • Install terminal-notifier via Homebrew so standard macOS notifications work reliably and support click-to-focus behavior.
  • Set suppress_sound_when_tab_focused: true.
  • Set silent_window_seconds: 30 so task.complete only fires for longer-running work.
  • Categories:
    • session.start: false
    • task.acknowledge: false
    • task.complete: true
    • task.error: true
    • input.required: true
    • resource.limit: true
    • user.spam: false
  • Goal: alerts only for meaningful attention events, with completion sounds reserved for work that took long enough to matter.
Ollama Models (for 24GB RAM)
qwen3.5:27b                    # General purpose (256K context, multimodal)
qwen2.5-coder:14b              # Code-focused
deepseek-r1:8b                 # Reasoning
macOS Defaults (automated)
bash
# Finder: show extensions, show dotfiles, show path bar, list view
# Dock: auto-hide, no recents, no delay, minimize to app icon
# Keyboard: no autocorrect, no smart quotes, fast repeat, no press-and-hold
# Trackpad: no natural scrolling, tap to click
# Screenshots: PNG, Desktop, no shadow
# Menu bar: auto-hide
macOS Settings (manual — guide the user)

These can't be automated via defaults write:

  1. Spotlight: disable all except Apps + System Settings
  2. Siri: disable
  3. Screenshot shortcut: remap to Cmd+E
  4. Cmd+Q: remap to double-tap (prevent accidental quits)
  5. Trackpad: disable dictionary lookup
  6. Finder: set new windows to ~/Work
  7. Dock: remove all icons except Finder and Trash
  8. Cursor size: set to large in Accessibility (good for presentations)

Apps to Download Manually

These aren't in Homebrew or need manual install:

  • Wispr Flow — voice-to-text (2025 pick)
  • SuperWhisper — voice-to-text (2024 pick, still good)
  • Screendrop — local-first screenshots, screen recordings, annotation, capture history, and optional Cloudflare-backed sharing; recommended alongside Shottr
  • Screenflow 11 — screen recording
  • Tella.tv — screen recording; preferred replacement for Loom
  • App Quitter — close apps when windows close
  • Clipbook or Alfred — clipboard manager

Post-Install: Open Apps That Need Login

After all scripts finish, open these apps to sign in and configure them. The skill should auto-open them for the user:

bash
# Apps that need login/activation after install
open -a "Slack"
open -a "Discord"
open -a "Raycast"
open -a "Shottr"
open -a "1Password"
open -a "Spotify"
open -a "Zoom"
open -a "Dia"
open -a "GitHub Desktop" 2>/dev/null
open -a "Claude" 2>/dev/null
echo "🔑 Sign into each app above, then continue setup."

Browser Extensions (install in Dia/Chrome)

Essential:

  • uBlock Origin, Privacy Badger, Video Speed Controller (highly recommended)
  • Refined GitHub, React Developer Tools, Code Copy
  • 1Password / LastPass

Nice to have:

  • Morpheon Dark, bypass-paywalls-chrome, Twitter-Links-beta
  • enhanced-history, Display Anchors, Octolinker, little-rat, RescueTime

Suggested Additions

Things worth considering that aren't in the original blog posts but complement this setup well:

  1. mise (mise.jdx.dev) — universal version manager for Node, Python, Ruby, Go, etc. Could replace fnm + uv for version management (swyx mentioned exploring this)
  2. zoxide — smarter z alternative with fuzzy matching
  3. bat — cat replacement with syntax highlighting
  4. eza — modern ls replacement
  5. fd — faster find alternative
  6. ripgrep — faster grep (rg)
  7. fzf — fuzzy finder for shell history, files, everything
  8. starship — cross-shell prompt (alternative to powerlevel10k, works with fish too)
  9. Bartender or Ice — menu bar icon management (declutter)
  10. Hand Mirror — quick webcam check from menu bar (great before calls)
  11. Tailscale — mesh VPN for accessing home machines
  12. Orbstack — another Docker Desktop alternative (even lighter than Colima)
  13. Aerospace — tiling window manager (if Rectangle isn't enough)

Dotfiles Reference

The .zshrc should include:

  • Oh-My-ZSH with powerlevel10k theme
  • Plugins: git, zsh-autosuggestions, zsh-syntax-highlighting, z
  • Homebrew, fnm, and uv PATH setup
  • z directory jumping source
  • Git aliases (gs, gd, gc, gp, gl, gco, gcb)
  • npm/pnpm aliases (ni, nr, pi, pr, ncu)
  • Python aliases (pip → uv pip, venv → uv venv)
  • Docker aliases (dstart → colima start, dstop → colima stop)
  • Editor set to Cursor

The Ghostty config should include:

  • Font: "Meslo LG M for Powerline" at 14pt
  • Theme: dark:GruvboxDark,light:GruvboxLight
  • Shell integration: zsh
  • Block cursor, no blink
  • Global hotkey: Cmd+` for quick terminal
  • Clipboard read/write enabled
  • Mouse hide while typing

© swyxio, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 10 other files (scripts) in new-mac-setup of swyxio/skills.

  • SKILL.md
  • LICENSE
  • README.md
  • scripts/00-run-all.sh
  • scripts/01-xcode-and-homebrew.sh
  • scripts/02-shell-setup.sh
  • scripts/03-brew-packages.sh
  • scripts/04-dev-environment.sh
  • scripts/05-ai-tools.sh
  • scripts/06-dotfiles.sh
  • scripts/07-macos-settings.sh

Open the folder on GitHubat commit 038ef34

Compare with similar skills

New Mac Setup next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

New Mac Setup compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
New Mac Setup this skillswyxio/skills175—~4.3kAutomated safety check: PassMIT
Environment Setup AssistantArabelaTso/Skills-4-SE253—~3kAutomated safety check: NotesApache-2.0
Headless Codex CLI AutomationXiaomiMiMo/MiMo-Code14k—~2.7kAutomated safety check: PassMIT
Deploy To Tempsgotempsh/temps828—~1.3kAutomated safety check: NotesApache-2.0
Writing Dockerfilesancoleman/ai-design-components526—~3.2kAutomated safety check: NotesMIT
Env Troubleshoot312362115/claude107—~900Automated safety check: WarnMIT

Similar skills

  • Environment Setup Assistant

    ArabelaTso/Skills-4-SE

    Generate setup scripts and instructions for development environments across platforms.

    253 GitHub stars~3k tokensUpdated 1 mo ago
    DevOps & CloudAuto-check: notes
  • Headless Codex CLI Automation

    XiaomiMiMo/MiMo-Code

    Runs OpenAI Codex CLI as a non-interactive worker for CI, Docker, Kubernetes or remote servers, with sandbox modes and JSONL-friendly output.

    14k GitHub stars~2.7k tokensUpdated today
    DevOps & CloudAuto-check passed
  • Deploy To Temps

    gotempsh/temps

    Deploy applications to the Temps platform with automatic framework detection, Dockerfile generation, and container orchestration.

    828 GitHub stars~1.3k tokensUpdated today
    DevOps & CloudAuto-check: notes
  • Writing Dockerfiles

    ancoleman/ai-design-components

    Writing optimized, secure, multi-stage Dockerfiles with language-specific patterns (Python, Node.js, Go, Rust), BuildKit features, and distroless images.

    526 GitHub stars~3.2k tokensUpdated 10 mo ago
    DevOps & CloudAuto-check: notes
  • Env Troubleshoot

    312362115/claude

    环境排障技能:结构化排查开发环境问题. An agent skill from 312362115/claude.

    107 GitHub stars~900 tokensUpdated 4 mo ago
    DevOps & CloudAuto-check: warnings
  • Containerization Assistant

    ArabelaTso/Skills-4-SE

    Generate Dockerfiles, Docker Compose configurations, and Kubernetes manifests for containerizing applications.

    253 GitHub stars~2.9k tokensUpdated 1 mo ago
    DevOps & CloudAuto-check: notes

More from swyxio/skills

All 89 skills in this repo
  • Programmatic Agents

    swyxio/skills

    Run a selected coding-agent CLI programmatically, with latency, error, usage, cost, and trace logging.

    175 GitHub stars~2.2k tokensUpdated 4 days ago
    Auto-check passed
  • Design, implement, audit, or refresh protected username and handle namespaces for public products.

    175 GitHub stars~1.1k tokensUpdated 4 days ago
    Auto-check passed
  • Youtube API

    swyxio/skills

    Manage YouTube videos programmatically via the YouTube Data API v3 — upload video files, upload custom thumbnails, update video metadata (titles, descriptions, tags), and query video/channel info…

    175 GitHub stars~2.2k tokensUpdated 4 days ago
    Auto-check passed
  • Batch YouTube Studio upload workflow for videos sourced from Airtable, Google Drive, Loom, YouTube, or local files.

    175 GitHub stars~1.5k tokensUpdated 4 days ago
    Auto-check: warnings
  • Reconstruct and visually analyze paired agent, game, or policy trajectories to determine whether changed actions produced their intended effects.

    175 GitHub stars~1.8k tokensUpdated 4 days ago
    Auto-check passed
  • Forge

    swyxio/skills

    Operate or diagnose SmolForge repositories and Forge Deploy/Sites when the task requires Forge-specific CLI, authentication, manifest, or release behavior on forge.smol.ai or .sites.smol.ai.

    175 GitHub stars~1.3k tokensUpdated 4 days ago
    Auto-check passed

Questions about New Mac Setup

What does New Mac Setup do?

Fully automated new Mac setup for fullstack web developers and AI engineers. New Mac Setup is an agent skill from swyxio/skills. Fully automated new Mac setup for fullstack web developers and AI engineers.

When should I use New Mac Setup?

New Mac Setup fits situations like: someone says set up my Mac; configure my dev machine; install my dev tools; fresh Mac install.

How do I install New Mac Setup in Claude Code?

Run `npx skills add swyxio/skills --skill new-mac-setup -a claude-code`. Or copy the skill folder (new-mac-setup in swyxio/skills) into .claude/skills/new-mac-setup in your project. Claude Code loads it when a task matches its description.

How do I install New Mac Setup in Codex?

Run `npx skills add swyxio/skills --skill new-mac-setup -a codex`. Or copy the skill folder (new-mac-setup in swyxio/skills) into .agents/skills/new-mac-setup in your project. Codex loads it when a task matches its description.

Can I use New Mac Setup in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add swyxio/skills --skill new-mac-setup -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/new-mac-setup, .gemini/skills/new-mac-setup, .github/skills/new-mac-setup and .opencode/skills/new-mac-setup in your project.

What does New Mac Setup need to run?

Going by SKILL.md and its folder, New Mac Setup needs a shell for the scripts in its folder, the command-line tools its instructions call (brew, uv, bash and git) and credentials named HF_TOKEN. Our summary lists: Python 3; Node.js; A Bash shell; Docker. Compatibility (from SKILL.md): Requires macOS on Apple Silicon (M1/M2/M3/M4). Scripts use Homebrew, which handles all dependencies. Bash 3.2+ (ships with macOS). Internet connection required for package downloads. .

Does New Mac Setup access the network?

SKILL.md names 7 domains. As links in the text: github.com, wispr.com, superwhisper.com, telestream.net, tella.tv, appquitter.com and clipbook.app. This is read from the text; nothing was executed.

Is New Mac Setup safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does New Mac Setup use?

New Mac Setup is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does New Mac Setup use?

About 4.3k tokens (SKILL.md is roughly 17k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to New Mac Setup?

Skills that share tags, products or a category with New Mac Setup: Environment Setup Assistant (ArabelaTso/Skills-4-SE, 253 stars), Headless Codex CLI Automation (XiaomiMiMo/MiMo-Code, 14k stars), Deploy To Temps (gotempsh/temps, 828 stars) and Writing Dockerfiles (ancoleman/ai-design-components, 526 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains New Mac Setup?

swyxio (a GitHub user) maintains it in swyxio/skills, which has 175 GitHub stars. The repository holds 89 skills in this directory. The repository was last updated on October 5, 2026.

Source: swyxio/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.