Semantic computer control for macOS that uses Accessibility API references instead of raw coordinates. You take a screenshot to get tagged elements like @e1 and @e2, then click or fill them without worrying about pixel positions. It falls back to coordinates when AX coverage is weak and batches actions to avoid round trips. The strict mode is clever: prevents focus stealing so you can automate apps in the background without your cursor jumping around. Needs Accessibility and Screen Recording permissions on first run. If you're automating Mac GUI tasks with Pi and want something more reliable than coordinate-based clicking, this is the right approach.

skills.sh installs
206
GitHub stars
26
last updated
Jun 3, 2026

Install

$ npx -y skills add aradotso/trending-skills --skill pi-computer-use --agent claude-code

Installs into .claude/skills of the current project.

Files

pi-computer-use

Skill by ara.so — Daily 2026 Skills collection.

pi-computer-use gives Pi agents a semantic computer-use surface for visible macOS windows. It prefers Accessibility (AX) targets (like @e1) over raw coordinates, returns semantic state after every action, and attaches screenshots only when AX coverage is too weak.


Installation

Via Pi (recommended)

pi install git:github.com/injaneity/pi-computer-use#v0.2.1

Pin to a specific version:

pi install -l git:github.com/injaneity/pi-computer-use#v0.2.1

Via npm

npm install @injaneity/pi-computer-use
# or pin a version
npm install @injaneity/pi-computer-use@0.2.1

Remove

pi remove git:github.com/injaneity/pi-computer-use#v0.2.1
npm remove @injaneity/pi-computer-use

First-Run Permissions

On first session, macOS will prompt for permissions for:

~/.pi/agent/helpers/pi-computer-use/bridge

Grant both:

  • Accessibility — required for AX ref targeting
  • Screen Recording — required for screenshots

How It Works

Three components:

Sponsors

Details

Repository
github.com/aradotso/trending-skills
First seen
Jun 3, 2026

More from aradotso/trending-skills

All 251

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
2mattpocock avatargrill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.5Mskills.sh installs
3shadcn avatarimproveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
5forrestchang avatarkarpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
6vercel-labs avatarfind-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs