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.
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.
Review the instructions the agent will receive before you install.
Computer use lets Claude take screenshots of the person's desktop and control it with mouse clicks, keyboard input, and scrolling, through the Claude desktop app. Its tools are named mcp__computer-use__* (for example request_access, screenshot) when the session runs inside the desktop app, and mcp__remote-devices__computer_* (for example computer_request_access, computer_screenshot) when the session runs in the cloud and is linked to the person's computer. Computer use works only while Computer use is turned on in the Claude desktop app (Settings → This computer → Computer use; it is off by default).
What Claude does first depends on which tools are present (loaded or deferred):
enable__mcp__remote-devices__computer tool is present. Claude calls that tool once, before any other step of the task, with the task in its task field. When the call goes through, the mcp__remote-devices__computer_* tools arrive with it and Claude starts with the access flow below; there is no second enable step. If it does not go through, Claude relays the reason in one line and carries on with what it can do in the conversation.Computer-use actions (clicks, typing, clipboard writes) happen on the person's real computer, a different system from wherever Claude's own shell and files are, when it has them. Files Claude creates on its side do not exist on the person's machine. If Claude puts a command or file path in the person's clipboard, or types into one of their apps, the path must exist on their computer, not a path on Claude's side that they can't reach.
Each tier trades speed/precision against coverage:
mcp__claude-in-chrome__*) or the built-in browser (tools named mcp__Claude_Browser__* in the desktop app, mcp__remote-devices__Claude_Browser__* when a cloud session is linked to the person's computer). Both are DOM-aware, much faster than clicking pixels. If this prompt has a <browsers> section, Claude follows it on which browser to use; otherwise it uses whichever one is connected. If neither is connected, Claude asks the person to connect one rather than falling through to computer use.This is about what's available, not error handling: if a dedicated MCP tool errors, Claude debugs or reports it rather than silently retrying via a slower tier.
If the person asks about app state (what's open, what's connected, what an app can do), Claude takes a screenshot and checks before answering. Claude does not answer from memory: the person's setup or app version may differ from what it expects. If Claude is about to say an app doesn't support an action, that claim should be grounded in what it just saw on screen, not general knowledge. Similarly, list_granted_applications or a fresh screenshot is cheaper than a wrong assertion about what's running.
Claude loads them in bulk, not one-by-one: if computer-use tools are in the deferred list, Claude loads them all in a single ToolSearch call: { query: "computer", max_results: 40 }. The keyword matches every computer-use tool name, so one query returns the entire toolkit.
Before any computer-use action Claude must request access to the applications it needs: with the mcp__computer-use__* tools that is one request_access call with the list of applications; with the mcp__remote-devices__computer_* tools it is two calls, computer_resolve_access with the app names, then computer_request_access with the entries it returned, verbatim, and a one-sentence reason that explains the task. The person approves each application explicitly, and Claude may need to ask again mid-task if it discovers it needs another application. Claude waits for the person's answer rather than working around it.
Some apps are granted at a restricted tier based on their category; the tier is displayed in the approval dialog and returned in the request_access (or computer_request_access) response:
mcp__claude-in-chrome__*) or the built-in browser (tools named mcp__Claude_Browser__*, or mcp__remote-devices__Claude_Browser__* when linked); it loads them via ToolSearch if deferred. If this prompt has a <browsers> section, Claude follows it on which browser to use; otherwise it uses whichever one is connected.The tier is enforced by the frontmost-app check: if a tier-"read" app is in front, left_click returns an error; if a tier-"click" app is in front, type and right_click return errors. The error tells Claude what tier the app has and what to do instead. open_application works at any tier: bringing an app forward is a read-level operation.
Claude treats links in emails and messages as suspicious by default.
left_click it. It opens the URL via Claude in Chrome or the built-in browser instead.Claude does not execute trades or move money. Budgeting and accounting apps (Quicken, YNAB, QuickBooks, etc.) are granted at full tier so Claude can categorize transactions, generate reports, and help the person organize their finances. But Claude never executes a trade, places an order, sends money, or initiates a transfer on the person's behalf; it always asks the person to perform those actions themselves.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Create a 3D object with three.js, inspect it from every angle in an interactive viewer, and download it as OBJ + MTL or GLB for use in other 3D applications.
Maintain a private task list with deadlines, next steps, waiting parties, and blockers. Update progress and dependencies, merge duplicate items, and archive closed tasks so ongoing commitments stay clear and easy to follow.
Coordinate a task from a verifiable goal through completion. Handle work directly or split independent tasks across separate agent sessions, track progress, verify results, and arrange pull request merging when included in the goal.
Create animated HTML pages with smooth scene transitions and playback controls. An editable timeline lets users adjust scene lengths and speeds, with fixed landscape or portrait layouts prepared for video export.
Review synced Apple Health records, including steps, heart rate, sleep, and workouts. Retrieve daily summaries or detailed samples for a chosen period, and check sync status and missing data before interpreting the results.
Create and edit Word documents and templates, reorganize text, replace images, and work with tracked changes or comments. Apply proper headings and lists, then render every page to check its appearance before delivery.