$ loading_
Capture and automate macOS UI actions with Peekaboo CLI for scripting and testing.
This skill is classified as prompt-only and declares no secrets or remote endpoints, so its direct attack surface as a distributed skill is limited. However, the content describes an external macOS UI automation CLI with clipboard and script-driving capabilities; if the actual local tool is later connected, it should be re-audited based on its real permissions.
The material explicitly states that no keys or environment variables are required, and the README does not request API tokens or external account auth; as a prompt-only skill, there is no direct credential collection, storage, or exfiltration path shown.
It declares no remote endpoint hosts, and the system marks it as prompt-only; while the docs mention bridge/connectivity commands, the current material does not show any required external service or factual data transfer to third-party endpoints.
The README describes a Peekaboo CLI capable of clicking, typing, running `.peekaboo.json` scripts, and managing apps/windows, but this audit target itself is a prompt-only skill and does not directly spawn processes or execute code; no actual execution privilege is established at the material level.
The docs mention screenshots, clipboard read/write, system dialog handling, and window/menu interaction—high-privilege local interactions—but these are capabilities of the described external CLI; for the current prompt-only skill, there is no direct interface to files, screen contents, clipboard, or local resources.
The source is an open-source GitHub repository with very high community adoption (about 377k stars), which is a strong risk-reducing signal; however, the license is unspecified, maintenance status is unknown, and the skill references an external project/CLI, so if it is later installed or bound for real use, its version, release source, and dependency integrity should still be verified.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "peekaboo" skill from askskill: 1. Download https://raw.githubusercontent.com/openclaw/openclaw/main/skills/peekaboo/SKILL.md 2. Save it as ~/.claude/skills/peekaboo/SKILL.md 3. Reload skills and tell me it's ready
Use Peekaboo CLI to design a macOS automation flow: open Safari, visit a given URL, click the login button, and save screenshots of each step.
A runnable Peekaboo CLI script or step sequence that automates the desktop interaction and saves screenshots.
Help me write a macOS app UI regression test with Peekaboo CLI to verify the window opens, buttons are clickable, and key text appears.
A sample UI validation test script with check steps, assertion logic, and execution order.
Convert this manual macOS workflow into a Peekaboo CLI automation plan: launch the app, open settings, toggle a switch, and export the result file.
A step-by-step automation plan explaining how each UI action can be implemented with Peekaboo CLI.
Peekaboo is a full macOS UI automation CLI: capture/inspect screens, target UI
elements, drive input, and manage apps/windows/menus. Commands share a snapshot
cache and support --json/-j for scripting. Run peekaboo or
peekaboo <cmd> --help for flags; peekaboo --version prints build metadata.
Tip: run via polter peekaboo to ensure fresh builds.
Core
bridge: inspect Peekaboo Bridge host connectivitycapture: live capture or video ingest + frame extractionclean: prune snapshot cache and temp filesconfig: init/show/edit/validate, providers, models, credentialsimage: capture screenshots (screen/window/menu bar regions)learn: print the full agent guide + tool cataloglist: apps, windows, screens, menubar, permissionspermissions: check Screen Recording/Accessibility statusrun: execute .peekaboo.json scriptssleep: pause execution for a durationtools: list available tools with filtering/display optionsInteraction
click: target by ID/query/coords with smart waitsdrag: drag & drop across elements/coords/Dockhotkey: modifier combos like cmd,shift,tmove: cursor positioning with optional smoothingpaste: set clipboard -> paste -> restorepress: special-key sequences with repeatsscroll: directional scrolling (targeted + smooth)swipe: gesture-style drags between targetstype: text + control keys (--clear, delays)System
app: launch/quit/relaunch/hide/unhide/switch/list appsclipboard: read/write clipboard (text/images/files)dialog: click/input/file/dismiss/list system dialogsdock: launch/right-click/hide/show/list Dock itemsmenu: click/list application menus + menu extrasmenubar: list/click status bar itemsopen: enhanced open with app targeting + JSON payloadsspace: list/switch/move-window (Spaces)visualizer: exercise Peekaboo visual feedback animationswindow: close/minimize/maximize/move/resize/focus/listVision
see: annotated UI maps, snapshot IDs, optional analysisGlobal runtime flags
--json/-j, --verbose/-v, --log-level <level>--no-remote, --bridge-socket <path>peekaboo permissions
peekaboo list apps --json
peekaboo see --annotate --path /tmp/peekaboo-see.png
peekaboo click --on B1
peekaboo type "Hello" --return
--app, --pid, --window-title, --window-id, --window-index--snapshot (ID from see; defaults to latest)--on/--id (element ID), --coords x,y--no-auto-focus, --space-switch, --bring-to-current-space,
--focus-timeout-seconds, --focus-retry-count--path, --format png|jpg, --retina--mode screen|window|frontmost, --screen-index,
--window-title, --window-id--analyze "prompt", --annotate--capture-engine auto|classic|cg|modern|sckit--duration (drag/swipe), --steps, --delay (type/scroll/press)--profile human|linear, --wpm (typing)--direction up|down|left|right, --amount <ticks>, --smoothpeekaboo see --app Safari --window-title "Login" --annotate --path /tmp/see.png
peekaboo click --on B3 --app Safari
peekaboo type "[email protected]" --app Safari
peekaboo press tab --count 1 --app Safari
peekaboo type "supersecret" --app Safari --return
peekaboo list windows --app "Visual Studio Code" --json
peekaboo click --window-id 12345 --coords 120,160
peekaboo type "Hello from Peekaboo" --window-id 12345
…
Automate OpenClaw nightly releases, branch maintenance, and forward-porting to main.
Debug Node.js apps with inspect, breakpoints, heap, and CPU profiling.
Audit and harden OpenClaw hosts for security and operational health.
List chats, review message history, and send iMessage or SMS from CLI.
Summarize or transcribe URLs, videos, PDFs, and local files quickly.
Generate shareable code or text diffs for review and collaboration.
Capture macOS screenshots and analyze interface content with visual question answering.
Expose local browser session recordings to AI agents for debugging and analysis.
Complete release closeout with notarization, publishing, verification, and final checks.
Let AI agents control macOS apps and read UI elements automatically.
Automate web page workflows, login checks, tab handling, and recovery steps.
Let AI control macOS desktop apps in the background without interrupting work.