Adom Desktop Control
Public Made by Adomby adom
Drive the user's real desktop from the cloud: their Chrome/Edge, headless pup, native UI, the Hydrogen editor, sibling Claude tabs, plus screen recording and video post.
Skills
The skills this repo ships, by tier, each with a quick health read. Install the user skills with:
adom-wiki skills install adom/adom-desktop-controlDrive an Adom user's REAL machine from the cloud through Adom Desktop: their logged-in Chrome/Edge (browser extension / CDP), headless pup browsers, native windows (UIA + SendInput), the Hydrogen web editor, and sibling Claude tabs, plus a screen-recording + video post-production pipeline. Use when you need to click/type/upload in the user's browser, drive a native app window, log a user in, record the screen, or produce a demo video. Trigger words: drive the browser, control chrome/edge, nbrowser, pup, automate the desktop, click a native window, UIA, record the screen, make a demo, speed up a video, type into the Claude tab, drive an OAuth login, upload a file via the browser.
When to delegate work to a sibling Claude tab on the user's machine vs do it yourself, and the access differences that decide it (Hydrogen/galliaApril bypass + relay access vs claude.ai cloud sandbox). Trigger words: drive another claude, sibling claude, claude code tab, delegate to claude, run a prompt in the claude tab.
Click, type, and read NATIVE app windows (Fusion, dialogs, non-web UI) on the user's desktop via Adom Desktop UIA and SendInput. Covers find_control/ui_click, click/type/press_key, screenshot-to-coordinate mapping, and window foreground. Trigger words: UIA, desktop_click, desktop_type, click a native window, drive a dialog, find_control, press_key, bring window to front, coordinate click.
What you CAN and (mostly) CANNOT drive in the Hydrogen web editor (hydrogen.adom.inc/<user>/<env>/edit) from the cloud, and why its embedded Claude Code panel input is unreachable by automation. Read before trying to type into a Hydrogen Claude tab. Trigger words: hydrogen editor, hydrogen web control, type into the claude tab, drive hydrogen, galliaApril editor, claude panel input.
Drive the user's REAL logged-in Chrome or Edge from the cloud via the Adom browser extension (CDP), in the background, no focus steal. Use to click/scroll/ read a page in their actual browser, upload a file, or log them in through OAuth using their existing sessions. Trigger words: nbrowser, drive my chrome, drive edge, real browser, logged-in browser, upload to a website, sign in with google, oauth login, CDP eval browser.
Drive a headless/throwaway Puppeteer (pup) Chrome window via Adom Desktop, for tasks that need no login or that you want to record cleanly without touching the user's real browser. Trigger words: pup, puppeteer browser, headless chrome, anonymous browser, browser_eval, browser_open_window, record a browser tab.
Record the user's screen to a video clip via Adom Desktop. THE right tool is WGC single-window capture (background, no picker, no banner, occlusion-safe), not whole-desktop capture. Covers the full recording verb surface, on-screen captions, and the gotchas that make or break it. Trigger words: record the screen, screen recording, desktop_record, record a window, WGC, record a demo, capture the screen, on-screen captions, desktop_caption, record the browser flow, record in the background.
Turn raw screen recordings + screenshots into a finished, narrated, captioned demo video with ffmpeg and the video-post tool: crop, speed up boring parts, brand-font captions, Ken Burns on stills, TTS voiceover, concat, and wiki-ready keyframes. Trigger words: speed up a video, edit a recording, make a demo video, add captions, voiceover, ffmpeg demo, video-post, concat clips, publish a demo to the wiki.
No dev skills in this repo.
How to build, debug, and test this app. Source-only (dev-skills/), never shipped in the tarball.
No publish skills in this repo.
The app-to-wiki publish glue. Source-only (publish-skills/), never shipped in the tarball.
Health: the size chip is green when right-sized, yellow when getting long, red when the model likely skims it. A green check is a passed preamble/structure signal; an amber mark is a gentle nudge, not a hard failure.