Computer Automation

web-infra-dev/midscene-skills

Takes control of your actual mouse and keyboard to automate desktop apps through screenshots and natural language commands, powered by Midscene.js. Works on native apps (Electron, Qt, anything that won't run in a browser) across macOS, Windows, and Linux, plus remote Windows machines over RDP. The workflow is straightforward: run one command at a time, wait for the screenshot, analyze what happened, then decide the next move. No DOM scraping, no accessibility tree, just pixel vision and AI reasoning. One honest catch: this literally commandeers your physical cursor in local mode, so you can't multitask while it runs. For web automation, use the browser skill instead. Only reach for this when you need to drive something that lives outside a browser window.

skills.sh installs

2.2K

GitHub stars

321

last updated

Aug 21, 2026

Sponsors

Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthlyAgent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any language

Recommended

More Frontend Development

1releasetobi/qmdManage releases for this project. Validates changelog, installs git hooks, and cuts releases. Use when user says "/release", "release 1.0.5", "cut a release", o2.2Kskills.sh installs

2app-iconcode-with-beto/skillsGenerate app icons for your React Native Expo app with iOS 26 support2.2Kskills.sh installs

3latex-postersk-dense-ai/scientific-agent-skillsCreate professional research posters in LaTeX using beamerposter, tikzposter, or baposter. Support for conference presentations, academic posters, and scientifi2.2Kskills.sh installs

4moshi-best-practicesrjyo/moshi-skillUse when preparing or verifying a host for Moshi remote coding. Trigger this for Easy Pair host setup, SSH or preferably Mosh readiness, non-interactive shell P2.1Kskills.sh installs

5nemotron-customizenvidia/skillsPlan, configure, and chain repo-native Nemotron customization steps into single-step or multi-step pipelines: curation, translation, SFT/PEFT (AutoModel or Mega2.1Kskills.sh installs

6r3f-postprocessingenzed/r3f-skillsReact Three Fiber post-processing - @react-three/postprocessing, bloom, DOF, screen effects. Use when adding visual effects, color grading, blur, glow, or creat2.1Kskills.sh installs