66 skills · sorted by relevance
Build and run computer-use-demo in Docker, then use Playwright to test its Streamlit interface without opening a visible browser. Save conversation transcripts, API exchanges, and screenshots to inspect behavior after changes.
Control native macOS apps through named buttons, fields, and menus using accessibility data, which describes interface elements. The skill also guides window actions and checking fresh screenshots to confirm what actually changed.
This skill should be used when the user asks to "build a computer-use agent", "automate a GUI with an AI agent", "when to use computer use vs an API", "make browser automation reliable", or "design screenshot-driven agent actions".
The English summary is being prepared. Showing the original description.
Use native computer-use safely in Decisions workflows when the active harness exposes a CUA or computer-use runtime.
The English summary is being prepared. Showing the original description.
Let agents run disposable VMs for computer-use and GUI automation instead of controlling the host desktop.
The English summary is being prepared. Showing the original description.
Helps Claude work in desktop apps by viewing screenshots, clicking, typing, and scrolling. It covers access approval, choosing appropriate tools, and handling app restrictions for tasks in Notes, Finder, settings, and other native apps.
Guide remote Windows app control using UI Automation, which identifies controls by names and roles. Covers text entry, buttons, window management, screenshot checks, and handling desktop session problems when the connected backend supports these features.
Guide desktop actions on a connected Linux computer using accessibility information that identifies buttons and fields. It covers checking keyboard focus, verifying results with screenshots, and handling limitations in XWayland apps and remote desktop viewers.
Inspect and control the connected local computer through A0 CLI or a Launcher host gateway. The skill guides screenshots, native app input, window targeting, and checking results, with background actions where the connected system supports them.
Guide a first computer-use agent run from environment checks to a browser-only task and a viewer of the run history. Explain each stage so users can understand the output and review screenshots afterward.
Use when driving a desktop GUI through a computer-use driver — windows, menus, native apps, OS dialogs. You build a table of safe actions; Jev picks the next one in about 0.4 seconds.
The English summary is being prepared. Showing the original description.
操作 macOS 桌面应用，探测窗口和自动化接口、截图、读取或修改辅助功能元素、执行鼠标键盘动作，以及通过 CDP 操作内嵌 Chromium 页面。适用于桌面应用自动化与界面验收；普通网页任务优先使用已有浏览器工具。
The English summary is being prepared. Showing the original description.
Claude computer use is an Anthropic API tool that lets Claude see a desktop through screenshots and operate it with mouse and keyboard. Use when automating GUI workflows, browser automation without CSS selectors, desktop app testing, or any task that requires seeing and interacting with a graphical interface.
The English summary is being prepared. Showing the original description.
Read this skill before the first step of any request to do something in an app on the person's own computer (Notes, Finder, System Settings, any desktop app), to look at their screen, or for "computer use". Computer use (desktop control) lets Claude take screenshots of the person's desktop and control it with clicks, typing and scrolling through the Claude desktop app; its tools are named mcp__computer-use__* when the session runs in the desktop app and mcp__remote-devices__computer_* when a cloud session is linked to the person's computer; before a conversation is linked there may be no such tools, only an enable__mcp__remote-devices__Claude_Browser tool, which links it. It covers getting linked, picking the right tool, the access flow, and what to do when computer use is off or out of reach. It is not for websites, which go through Claude in Chrome or the built-in browser and their own skills.
The English summary is being prepared. Showing the original description.
Bindet das model-agnostische Computer-Use-Modul open-compute (Screenshot-Wahrnehmung, Windows-UIA-Elementklicks, sicherheitsgegatete Aktionen) fuer ALLE Agenten des Systems ein -- Claude Code, Codex und agy/Antigravity. Nutzen, wenn ein Dienst eine interaktive GUI- oder Browser-Aktion braucht, die kein reiner Text-/API-Weg loesen kann (Paradebeispiel: Tailscale-Reauth im Browser, sonstige Login-/Consent-Dialoge, Dialogfenster-Klicks). Standard ab 2026-08-02: open-compute statt Aufgeben oder Abwarten nutzen.
The English summary is being prepared. Showing the original description.
Orientation for custom (non-OpenAI) models running in the Codex app through the codex-router proxy. Explains that the app's native tools arrive as flattened codex_app__ and mcp__ names, that the router restores them so the app executes them, which companion skills to read before threads, browser, or computer-use work, and that a turn with no tool call ends the task. Use when the session uses a custom (non-OpenAI) model, for example deepseek-v4-flash or mimo-v2.5, when codex_app__ or mcp__ tool names appear in the tool list, when a tool result just arrived and more work remains, or when thread, browser, or computer-use work is requested.
The English summary is being prepared. Showing the original description.
Utilizes native Rust/Node and Python-based computer-use-mcp servers to control macOS, Windows, and Linux desktops.
The English summary is being prepared. Showing the original description.
MUST USE whenever the user wants to automate a real desktop or sandbox - clicking, typing, scrolling, screenshotting, running an OS shell command, or handing a high-level 'open browser and do X' task to an autonomous computer-use agent. Wraps the trycua/cua Python toolkit via its `cua` CLI - pynput-based, cross-platform (macOS / Linux / Windows). NO custom tools are registered; you call `cua` through pi's built-in bash and read screenshots back through the Read tool. Triggers: cua, computer use, computer-use, GUI automation, screenshot the desktop, click on the screen, type into the active app, scroll the page, control my computer, drive my browser, sandbox, docker sandbox, QEMU sandbox, Lume sandbox, ComputerAgent, cua do, cua sandbox, 컴퓨터 자동화, 스크린샷 찍어, 내 컴퓨터 조작, 브라우저 열어서, 샌드박스, 화면 자동화, 마우스로 클릭, 키보드 타이핑, computer use 위임, 자동으로 클릭, 자율 에이전트로 처리.
The English summary is being prepared. Showing the original description.
Read this skill before the first step of any request to do something in an app on the person's own computer (Notes, Finder, System Settings, any desktop app), to look at their screen, or for "computer use". Computer use (desktop control) lets Claude take screenshots of the person's desktop and control it with clicks, typing and scrolling through the Claude desktop app; its tools are named mcp__computer-use__* when the session runs in the desktop app and mcp__remote-devices__computer_* when a cloud session is linked to the person's computer; before computer use is turned on for a conversation there may be no such tools, only an enable__mcp__remote-devices__computer tool, which turns it on. It covers turning it on, picking the right tool, the access flow, and the safety rules for tiered apps, links and financial actions. It is not for websites, which go through Claude in Chrome or the built-in browser and their own skills.
The English summary is being prepared. Showing the original description.
|
The English summary is being prepared. Showing the original description.
Post an approved announcement or other user-authored message through the Discord desktop app using the logged-in user's account. Verify the destination and final text, obtain confirmation before entering it, and check that the message appears once.
Automate clicks, typing, scrolling, and dragging in desktop apps through Hermes. The skill starts with background actions that preserve the user's focus, checks results, and switches interaction methods when an action fails.
Guides implementation and maintenance of Claude applications using language-specific references and official SDKs, the libraries used to call the API. Covers tool integration, streaming responses, model migration, cost reviews, prompt audits, and evaluation workflows.
Control visible local apps and external browser windows through Orca, including clicks, typing, menus, dialogs, and screenshots. Use it for tasks that require interacting with a screen and cannot be completed through commands or APIs.