algal/sparky/peekaboo
Claude Code and agent skill by algal/sparky
- community
Checking that the SKILL.md file is still in the repository.
Capture and automate macOS UI with Peekaboo on the "arrow" node.
Install
npx vskill@latest install algal/sparky/peekabooSKILL.md
Peekaboo (via arrow)
Peekaboo runs on the macOS node "arrow" (Alexis's Mac). You are on Linux and cannot run it locally.
Capturing the active window (most common use)
This is what you want when someone says "look at my screen," "what am I working on," or "help me with this":
- Capture and encode in one step via
system.runon node "arrow":
`` peekaboo image --mode frontmost --path /tmp/peekaboo-capture.png && base64 -i /tmp/peekaboo-capture.png ``
- The base64-encoded image data is returned in the command output. Decode and
analyze the image, then respond.
Prefer --mode frontmost over --mode screen — it captures only the focused window, which is smaller and more relevant than the full widescreen display.
All commands use only system.run on node "arrow" (provided by the native Mac app). No other node commands are needed.
Full CLI reference
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.
Core commands
image: capture screenshots (screen/window/menu bar regions)see: annotated UI maps, snapshot IDs, optional analysislist: apps, windows, screens, menubar, permissionspermissions: check Screen Recording/Accessibility statusapp: launch/quit/relaunch/hide/unhide/switch/list appswindow: close/minimize/maximize/move/resize/focus/listmenu: click/list application menus + menu extras
Interaction commands
click: target by ID/query/coords with smart waitstype: text + control keys (--clear, delays)hotkey: modifier combos likecmd,shift,tpress: special-key sequences with repeatsscroll: directional scrolling (targeted + smooth)drag: drag & drop across elements/coords/Dockpaste: set clipboard -> paste -> restore
Common capture parameters
- Output:
--path,--format png|jpg,--retina - Targeting:
--mode screen|window|frontmost,--screen-index,
--window-title, --window-id
- Analysis:
--analyze "prompt",--annotate
Common targeting parameters
- App/window:
--app,--pid,--window-title,--window-id,--window-index - Snapshot targeting:
--snapshot(ID fromsee; defaults to latest) - Element/coords:
--on/--id(element ID),--coords x,y
Examples
Capture active window:
Capture a specific app's window:
Annotated UI map (for subsequent click targeting):
See -> click -> type flow:
Open a URL:
All commands run via system.run on node "arrow". To retrieve image results, append && base64 -i <path> to the capture command.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingopenclaw_configs/workspace/skills/peekaboo/SKILL.md
Popularity
- Repository stars
- 75
- Repository forks
- 9
- 7-day trend score
- 22
Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 17 Mar 2026, 7 months ago.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/algal/sparky/peekaboo)