Agent skill

App Control

by vellum-ai in vellum-ai/vellum-assistant

Drive a specific named macOS app via raw input bypassing the Accessibility tree

MITAuto-check passedFrontend & Design

Install App Control

skills CLI
$ npx skills add vellum-ai/vellum-assistant --skill app-control -a claude-code

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

GitHub CLI
$ gh skill install vellum-ai/vellum-assistant app-control --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/vellum-ai/vellum-assistant.git skills-src && mkdir -p .claude/skills && cp -r skills-src/assistant/src/config/bundled-skills/app-control .claude/skills/app-control && 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
app-control
GitHub stars
1.4k
Token cost
~868 tokens
SKILL.md length
402 words
Files
11
Skills in repo
108
Repo updated
First seen
Licence
MIT

At a glance

Drive a specific named macOS app via raw input bypassing the Accessibility tree

  • Tasks that involve Accessibility
  • SKILL.md covers Cadence, Always observe before acting, Input choice and Coordinate caveat, plus 2 more sections
  • Runs TypeScript scripts from its folder

What it does

App Control is an agent skill from vellum-ai/vellum-assistant. Drive a specific named macOS app via raw input bypassing the Accessibility tree

Its SKILL.md is about 870 tokens, which your agent loads only when the skill is triggered. The skill folder holds 11 other files (for example `TOOLS.json`, `tools/app-control-click.ts` and `tools/app-control-combo.ts`). Compatibility notes: Designed for Vellum personal assistants

It sits in Frontend & Design, covering Accessibility. It works with macOS. The repository describes itself as: An AI Assistant that’s easy to setup, does your work 24/7, knows your preferences and gets better over time. The licence is MIT.

When your agent uses it

  • Tasks that involve Accessibility

Example prompts

  • “/app-control”

Requirements

  • Node.js
  • Compatibility (from SKILL.md): Designed for Vellum personal assistants

What it can do on your machine

Read from SKILL.md and the folder at commit 844117a. 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 script files (TypeScript), which the agent can run.

    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.

  • Compatibility

    Designed for Vellum personal assistants

    From compatibility in the SKILL.md frontmatter.

Context cost

App Control loads about 868 tokens when it runs. Until then it costs about 23 tokens; SKILL.md has 402 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~23
When it runs · the whole SKILL.md, loaded when a task matches
~868

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from vellum-ai/vellum-assistant at commit 844117a, republished under its MIT licence (© vellum-ai). 402 words, ~868 tokens.

Download SKILL.mdSave it as .claude/skills/app-control/SKILL.md (or your agent's skills folder). This skill also uses 10 other files; get the full folder from GitHub.
name
app-control
description
Drive a specific named macOS app via raw input bypassing the Accessibility tree
compatibility
Designed for Vellum personal assistants
metadata.emoji
🎯

This skill exposes the app_control_* proxy tools for driving a single named macOS application via raw input — keyboard, mouse, screenshot — that bypasses the system Accessibility tree. Use it only when explicitly directed to a specific app where the AX tree is unhelpful (emulators, games, OpenGL canvases, custom-rendered Electron apps). For general macOS UI navigation prefer the computer-use skill.

Tools in this skill are proxy tools — execution is forwarded to the connected macOS client, never handled locally by the assistant.

Cadence

Take 2-3 actions per turn, then yield with a short narration so the user can interject. Do not chain long sequences without surfacing what you are doing.

Always observe before acting

Call app_control_observe before your first input action whenever the screen state matters (e.g. you need to know what is on screen, where a UI element is, or whether the app is even running). Re-observe after actions that may have moved the window or changed visibility.

observe waits a short settle delay (default ~200ms) before capturing so the target app and the WindowServer can flush pending input and composite a fresh frame. If the captured screenshot looks one input behind the latest state (common with emulators or other slow-feedback apps), pass a larger settle_ms. For static UIs where you just want a quick snapshot, pass settle_ms: 0 to skip the wait.

Show full SKILL.md (181 more words)Show less

Input choice

  • Prefer app_control_sequence over multiple back-to-back app_control_press calls when sending an ordered batch of presses (e.g. menu navigation, repeated movement). Sequence runs in a single round-trip — the target app is activated once at the start and the keys are sent serially without any window for keyboard focus to drift to another app between presses. Each step may carry its own duration_ms (hold) and gap_ms (pause after).
  • Prefer app_control_combo over rapid sequential app_control_press for simultaneous inputs (e.g. cmd+shift+4). combo holds every key at once; sequential presses interleave key-down and key-up events.
  • Use app_control_type for literal text into a focused field.

Coordinate caveat

app_control_click and app_control_drag use window-relative coordinates. The window may move or resize between observation and click — if you are uncertain whether the window has shifted, re-observe first.

App targeting

Use bundle IDs (e.g. com.example.app) when possible — they are the most reliable identifier. Fall back to localized process names if a bundle ID is unavailable.

Ending the session

Call app_control_stop when you are done. Do not auto-quit the controlled app — stop only ends the app-control session, leaving the app running.

© vellum-ai, 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 in assistant/src/config/bundled-skills/app-control of vellum-ai/vellum-assistant.

  • SKILL.md
  • TOOLS.json
  • tools/app-control-click.ts
  • tools/app-control-combo.ts
  • tools/app-control-drag.ts
  • tools/app-control-observe.ts
  • tools/app-control-press.ts
  • tools/app-control-sequence.ts
  • tools/app-control-start.ts
  • tools/app-control-stop.ts
  • tools/app-control-type.ts

Open the folder on GitHubat commit 844117a

Compare with similar skills

App Control 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.

App Control compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
App Control this skillvellum-ai/vellum-assistant1.4k—~868Automated safety check: PassMIT
Jarvis Setupethanplusai/jarvis843—~2.5kAutomated safety check: NotesCustom licence
UI Review TahoeKartikLabhshetwar/better-shot2.4k2 repos~1.7kAutomated safety check: PassCustom licence
AccessibilityVeryGoodOpenSource/vgv-ai-flutter-plugin170—~4.2kAutomated safety check: PassMIT
Gui Debugnatsukium/dotfiles106—~909Automated safety check: PassCC0-1.0
Desktop A11y SpecialistCommunity-Access/accessibility-agents423—~1.3kAutomated safety check: PassMIT

Similar skills

  • Jarvis Setup

    ethanplusai/jarvis

    A skill your agent uses when helping someone install, configure, or debug a fresh clone of JARVIS (this repo) — especially "the mic doesn't work", "JARVIS says his language systems are down", any…

    843 GitHub stars~2.5k tokensUpdated 29 days ago
    Frontend & DesignAuto-check: notes
  • UI Review Tahoe

    KartikLabhshetwar/better-shot

    Comprehensive UI/UX review for macOS Tahoe apps. An agent skill from KartikLabhshetwar/better-shot.

    2.4k GitHub starsUsed in 2 repos~1.7k tokens
    Frontend & DesignAuto-check passed
  • Accessibility

    VeryGoodOpenSource/vgv-ai-flutter-plugin

    Audits or remediates Flutter widgets against WCAG 2.2 conformance levels A, AA, or AAA across iOS, Android, Web, macOS, Windows, and Linux, covering Semantics labels and screen reader output under…

    170 GitHub stars~4.2k tokensUpdated 3 days ago
    Frontend & DesignAuto-check passed
  • Gui Debug

    natsukium/dotfiles

    Verify a rendering or window-chrome change in any macOS GUI app unattended — find its CGWindowID via JXA, capture that window alone (with per-pixel alpha) using screencapture -l, and read exact RGBA…

    106 GitHub stars~909 tokensUpdated today
    Frontend & DesignAuto-check passed
  • Desktop A11y Specialist

    Community-Access/accessibility-agents

    Desktop a11y APIs: UI Automation, MSAA/IAccessible2, NSAccessibility.

    423 GitHub stars~1.3k tokensUpdated 15 days ago
    Frontend & DesignAuto-check passed
  • Apple Hig Helper

    shepherdjerred/monorepo

    Apple Human Interface Guidelines - comprehensive design guidance for iOS, macOS, visionOS, watchOS, tvOS, and Apple technologies with summaries of 174 topics.

    112 GitHub stars~4.6k tokensUpdated today
    Frontend & DesignAuto-check passed

More from vellum-ai/vellum-assistant

All 108 skills in this repo
  • Vellum GitHub App Setup

    vellum-ai/vellum-assistant

    Create and configure a GitHub App so the assistant can push commits, open PRs, and comment under its own bot identity.

    1.4k GitHub stars~3.1k tokensUpdated today
    Auto-check passed
  • Discord App Setup

    vellum-ai/vellum-assistant

    Connect a Discord bot to the assistant via the Discord Gateway with guided application creation and intent configuration

    1.4k GitHub stars~4.2k tokensUpdated today
    Auto-check passed
  • Sentry App Setup

    vellum-ai/vellum-assistant

    Create and configure a Sentry internal integration so the assistant can manage issues, alerts, and releases under its own identity

    1.4k GitHub stars~1.3k tokensUpdated today
    Auto-check passed
  • Memory Corpus Ingest

    vellum-ai/vellum-assistant

    Ingest a large dataset into memory as a skimmed map. An agent skill from vellum-ai/vellum-assistant.

    1.4k GitHub stars~3k tokensUpdated today
    Auto-check: notes
  • Plugin Builder

    vellum-ai/vellum-assistant

    A skill your agent uses when the user wants to build, scaffold, ship, or edit a Vellum plugin that bundles multiple surfaces (hooks, tools, skills, and more) into one installable package.

    1.4k GitHub stars~3.1k tokensUpdated today
    Auto-check passed
  • Slack App Setup

    vellum-ai/vellum-assistant

    Connect a Slack app to the Vellum Assistant via Socket Mode.

    1.4k GitHub stars~2.5k tokensUpdated today
    Auto-check: warnings

Works with

Questions about App Control

What does App Control do?

Drive a specific named macOS app via raw input bypassing the Accessibility tree. App Control is an agent skill from vellum-ai/vellum-assistant.

When should I use App Control?

App Control fits situations like: tasks that involve Accessibility.

How do I install App Control in Claude Code?

Run `npx skills add vellum-ai/vellum-assistant --skill app-control -a claude-code`. Or copy the skill folder (assistant/src/config/bundled-skills/app-control in vellum-ai/vellum-assistant) into .claude/skills/app-control in your project. Claude Code loads it when a task matches its description.

How do I install App Control in Codex?

Run `npx skills add vellum-ai/vellum-assistant --skill app-control -a codex`. Or copy the skill folder (assistant/src/config/bundled-skills/app-control in vellum-ai/vellum-assistant) into .agents/skills/app-control in your project. Codex loads it when a task matches its description.

Can I use App Control 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 vellum-ai/vellum-assistant --skill app-control -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/app-control, .gemini/skills/app-control, .github/skills/app-control and .opencode/skills/app-control in your project.

What does App Control need to run?

Going by SKILL.md and its folder, App Control needs TypeScript for the scripts in its folder. Our summary lists: Node.js. Compatibility (from SKILL.md): Designed for Vellum personal assistants.

Does App Control 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 App Control 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. Review the folder before installing.

What licence does App Control use?

App Control is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does App Control use?

About 868 tokens (SKILL.md is roughly 3.5k 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 App Control?

Skills that share tags, products or a category with App Control: Jarvis Setup (ethanplusai/jarvis, 843 stars), UI Review Tahoe (KartikLabhshetwar/better-shot, 2.4k stars), Accessibility (VeryGoodOpenSource/vgv-ai-flutter-plugin, 170 stars) and Gui Debug (natsukium/dotfiles, 106 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains App Control?

vellum-ai (a GitHub organization) maintains it in vellum-ai/vellum-assistant, which has 1,400 GitHub stars. The repository holds 108 skills in this directory. The repository was last updated on October 9, 2026.

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