Install the "altic-studio" agent skill from https://github.com/altic-dev/altic-mcp/tree/main/skills/altic-studio into .claude/skills/altic-studio/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "altic-studio", then confirm the skill loads.
Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
skills CLI
$ npx skills add altic-dev/altic-mcp --skill altic-studio -a codex
Project install goes to .agents/skills/; add -g for ~/.codex/skills/.
Install the "altic-studio" agent skill from https://github.com/altic-dev/altic-mcp/tree/main/skills/altic-studio into .agents/skills/altic-studio/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "altic-studio", then confirm the skill loads.
Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
skills CLI
$ npx skills add altic-dev/altic-mcp --skill altic-studio -a cursor
Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.
Install the "altic-studio" agent skill from https://github.com/altic-dev/altic-mcp/tree/main/skills/altic-studio into .cursor/skills/altic-studio/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "altic-studio", then confirm the skill loads.
Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
skills CLI
$ npx skills add altic-dev/altic-mcp --skill altic-studio -a gemini-cli
Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.
Install the "altic-studio" agent skill from https://github.com/altic-dev/altic-mcp/tree/main/skills/altic-studio into .gemini/skills/altic-studio/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "altic-studio", then confirm the skill loads.
Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
skills CLI
$ npx skills add altic-dev/altic-mcp --skill altic-studio -a github-copilot
Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.
Install the "altic-studio" agent skill from https://github.com/altic-dev/altic-mcp/tree/main/skills/altic-studio into .github/skills/altic-studio/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "altic-studio", then confirm the skill loads.
GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
skills CLI
$ npx skills add altic-dev/altic-mcp --skill altic-studio -a opencode
OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
Install the "altic-studio" agent skill from https://github.com/altic-dev/altic-mcp/tree/main/skills/altic-studio into .opencode/skills/altic-studio/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "altic-studio", then confirm the skill loads.
OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
Skill name
altic-studio
GitHub stars
172
Token cost
~3.3k tokens
SKILL.md length
1,324 words
Files
36 (incl. scripts)
Skills in repo
1
Repo updated
First seen
Licence
Apache-2.0
At a glance
macOS automation skill for AppleScript actions and Chrome browser control via MCP CDP tools.
Works in 5 steps: AppleScript mode for macOS apps and… → MCP CDP mode for Google Chrome browser… → MCP file mode for safe Finder and… → …
Tasks that involve Browser automation
SKILL.md covers Mode A: AppleScript (macOS apps), Mode B: Reminders, Calendar,…, Mode C: Chrome Browser Control… and Mode D: File Finder and File…, plus 4 more sections
Runs AppleScript and Swift scripts from its folder; calls swift and osascript
What it does
Altic Studio is an agent skill from altic-dev/altic-mcp. macOS automation skill for AppleScript actions and Chrome browser control via MCP CDP tools.
Its SKILL.md is about 3.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 36 other files, including scripts (for example `scripts/README.md`).
It sits in Productivity & Automation, covering Browser automation, Desktop control and MCP servers. It works with Model Context Protocol and macOS. The repository describes itself as: Turn Claude into a better version of Siri. The licence is Apache-2.0.
When your agent uses it
Tasks that involve Browser automation
Tasks that involve Desktop control
Tasks that involve MCP servers
Example prompts
“Use the altic-studio skill to maco automation skill for AppleScript actions and Chrome browser control via MCP CDP tools”
“/altic-studio”
Requirements
Python 3
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
1AppleScript mode for macOS apps and system actions
2MCP CDP mode for Google Chrome browser control
3MCP file mode for safe Finder and filesystem operations
4MCP clipboard mode for text, file, and image pasteboard operations
5MCP window/workspace mode for arranging macOS apps and windows
What it can do on your machine
Read from SKILL.md and the folder at commit 8b6e19f. 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 19 files in scripts/ (AppleScript and Swift, from the files we listed), which the agent can run.
Shell commands in SKILL.md call:
swift
osascript
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Altic Studio loads about 3.3k tokens when it runs. Until then it costs about 26 tokens; SKILL.md has 1,324 words of instructions outside code blocks.
Always· name and description, kept in context so the agent knows when to use it
~26
When it runs· the whole SKILL.md, loaded when a task matches
~3.3k
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.
Download SKILL.mdSave it as .claude/skills/altic-studio/SKILL.md (or your agent's skills folder). This skill also uses 35 other files; get the full folder from GitHub.
name
altic-studio
description
macOS automation skill for AppleScript actions and Chrome browser control via MCP CDP tools.
license
Apache-2.0
Altic Studio
altic-studio provides two automation modes:
AppleScript mode for macOS apps and system actions
MCP CDP mode for Google Chrome browser control
MCP file mode for safe Finder and filesystem operations
MCP clipboard mode for text, file, and image pasteboard operations
MCP window/workspace mode for arranging macOS apps and windows
It also includes Swift utility scripts for active-display screenshots, clipboard
file/image operations, and window/workspace management on macOS.
Mode A: AppleScript (macOS apps)
Always execute AppleScript through Bash with osascript.
Always run from workspace root as the working directory.
Quote script paths and arguments.
Prefer direct script invocation; do not route through Python wrappers unless explicitly requested.
Swift command template (for active-display screenshots):
bash
swift "skills/altic-studio/scripts/capture-active-screen.swift" "/tmp/active-screen.png"
Swift command template (for window management):
bash
swift "skills/altic-studio/scripts/window-manager.swift" "list_windows" '{"include_minimized":false}'
Mode B: Reminders, Calendar, And Notes (MCP)
Use MCP tools for structured Messages, Contacts, Reminders, Calendar, and Notes workflows. These
newer tools return JSON envelopes with ok, action, data, and error.
Delete tools default to dry_run=true; only delete after explicit user
confirmation.
Call list/search tools before mutating when the target is ambiguous.
Treat identifier as either an app-provided id or an exact title/name match.
If a mutation returns multiple matches, ask the user to disambiguate.
Keep destructive actions in dry-run mode until the user explicitly confirms.
Validate dates before calling tools: dates use YYYY-MM-DD, date-times use
YYYY-MM-DD HH:MM.
For send_file_message, prefer recipient_type="chat" after list_chats
when continuing an existing group thread; use recipient_type="handle" for a
direct phone number or email handle.
Mode C: Chrome Browser Control (MCP CDP)
Use MCP tools for deterministic Chrome automation:
chrome_open_session
chrome_navigate
chrome_wait_for
chrome_click
chrome_type
chrome_extract
chrome_screenshot
chrome_close_session
chrome_list_sessions
capture_active_screen
Execution pattern:
Open a Chrome session.
Navigate and wait for stable selectors.
Interact with click and type actions.
Verify state with extraction.
Capture screenshots on checkpoints or failures.
Close session.
Mode D: File Finder and File Operations (MCP)
Use MCP file tools instead of shell commands when the user asks to find, inspect,
copy, move, rename, reveal, or trash files. These tools return JSON for
successful lookups and operations, and Error: ... strings for failures.
If the user refers to selected files, the current Finder window, or "this file",
call get_finder_selection first.
For ambiguous file names, call find_files, then get_file_info; ask for
disambiguation when multiple plausible matches remain.
Prefer dry_run=true before copy_file, copy_directory, move_file,
rename_file, or trash_file when the target or destination is ambiguous.
Do not overwrite unless the user explicitly asks for replacement; default
overwrite=false.
Use trash_file, not permanent deletion.
Use reveal_in_finder after file operations when the user wants to see the
result in Finder.
Show full SKILL.md (530 more words)Show less
Mode E: Clipboard Operations (MCP)
Use MCP clipboard tools instead of shell commands when the user asks to inspect,
copy, paste, clear, or save clipboard contents. These tools return JSON for text
and file operations, Error: ... strings for failures, and image content for
saved clipboard images.
Available tools:
get_clipboard_text - args: [max_chars]
set_clipboard_text - args: <text>
clear_clipboard - args: none
get_clipboard_files - args: none
set_clipboard_files - args: <paths>
save_clipboard_image - args: [output_path]
set_clipboard_image - args: <path>
Clipboard workflow rules:
Ask before overwriting clipboard contents unless the user explicitly asks to
copy, set, clear, or replace the clipboard.
Use get_clipboard_text first when the user asks what text is currently copied.
Use get_clipboard_files when the user says they copied files in Finder or
wants to paste copied files somewhere else.
Use save_clipboard_image when the user wants to inspect, store, or transform
an image currently on the clipboard.
Use set_clipboard_files with existing paths only; resolve ambiguous file
names with find_files before changing the clipboard.
Use set_clipboard_image only for existing image files.
Mode F: Window and Workspace Operations (MCP)
Use MCP window tools when the user asks to arrange the workspace, focus an app or
window, tile apps side by side, resize windows, minimize windows, hide apps, quit
apps, or inspect the frontmost app. These tools return JSON for successful
operations and Error: ... strings for failures.
Altic Studio 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.
Give an AI agent its own real browser over MCP tool calls - launch, navigate, click, fill, screenshot, extract text, run JS - with a kernel-level real-device fingerprint and a persistent profile, so…
Diagnoses why the Claude in Chrome MCP tools report the browser extension as not connected, with macOS-specific checks and a fix for the Claude.app native host conflict.
macOS automation skill for AppleScript actions and Chrome browser control via MCP CDP tools. Altic Studio is an agent skill from altic-dev/altic-mcp. macOS automation skill for AppleScript actions and Chrome browser control via MCP CDP tools.
When should I use Altic Studio?
Altic Studio fits situations like: tasks that involve Browser automation; tasks that involve Desktop control; tasks that involve MCP servers.
How do I install Altic Studio in Claude Code?
Run `npx skills add altic-dev/altic-mcp --skill altic-studio -a claude-code`. Or copy the skill folder (skills/altic-studio in altic-dev/altic-mcp) into .claude/skills/altic-studio in your project. Claude Code loads it when a task matches its description.
How do I install Altic Studio in Codex?
Run `npx skills add altic-dev/altic-mcp --skill altic-studio -a codex`. Or copy the skill folder (skills/altic-studio in altic-dev/altic-mcp) into .agents/skills/altic-studio in your project. Codex loads it when a task matches its description.
Can I use Altic Studio 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 altic-dev/altic-mcp --skill altic-studio -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/altic-studio, .gemini/skills/altic-studio, .github/skills/altic-studio and .opencode/skills/altic-studio in your project.
What does Altic Studio need to run?
Going by SKILL.md and its folder, Altic Studio needs AppleScript and Swift for the scripts in its folder and the command-line tools its instructions call (swift and osascript). Our summary lists: Python 3.
Does Altic Studio access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Altic Studio 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 Altic Studio use?
Altic Studio is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Altic Studio use?
About 3.3k tokens (SKILL.md is roughly 13k 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 Altic Studio?
Skills that share tags, products or a category with Altic Studio: Browser MCP Agent (antibrow/anti-detect-browser-skills, 914 stars), Isolated Linux Agent Workspace (agent-sh/agent-workspace-linux, 185 stars), Computer Use (xuzhougeng/wisp-science, 1k stars) and CLI Anything Safari (HKUDS/CLI-Anything, 52k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Altic Studio?
altic-dev (a GitHub user) maintains it in altic-dev/altic-mcp, which has 172 GitHub stars. The repository was last updated on July 13, 2026.
Source: altic-dev/altic-mcp on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.