Control desktop apps with the Orca computer-use CLI
Reading and operating desktop application windows by trial and error wastes time and risks the wrong clicks. This skill lets Claude, Codex, and Claude Code inspect accessibility trees and screenshots, then perform precise, safe UI actions across native apps and browsers.
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "computer-use" from https://skillstore.io/skills/stablyai-computer-use.md and its manifest at https://skillstore.io/api/skills/stablyai-computer-use/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.Your Agent should still show its plan and request any confirmation required by the security policy.
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Using "computer-use". Read the current state of the Spotify app and tell me what is playing.
Expected outcome:
The agent lists applications, selects the Spotify bundle, reads its accessibility tree, and reports the track title, artist, and playback controls that are visible, without changing playback.
Using "computer-use". In my Edge browser window, set the address bar to example.com and press Return.
Expected outcome:
The agent restores the browser window to the foreground, sets the address field value to example.com, presses Return, then reads the refreshed state to confirm the page began loading.
This skill is documentation for Orca's computer-use CLI. The 50 external_commands findings for 'Ruby/shell backtick execution' are false positives: every match is a Markdown inline-code backtick around a command name or flag, not runtime backtick execution. The four PowerShell/cmd.exe matches are prose describing shell-neutral examples, and the six 'blocker' matches (system reconnaissance and screen-capture) reflect the skill's legitimate, disclosed purpose of reading UI state; the skill explicitly instructs against destructive actions and against exposing secrets. No malicious intent, data exfiltration, or prompt injection was found.
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
https://skillstore.io/skills/stablyai-computer-use/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report[](https://skillstore.io/skills/stablyai-computer-use?utm_source=security_passport_badge)<a href="https://skillstore.io/skills/stablyai-computer-use?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/stablyai-computer-use/security.svg" alt="Skillstore security assessment" loading="lazy"></a><iframe src="https://skillstore.io/embed/skills/stablyai-computer-use.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>stablyai. (2026). computer-use security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/stablyai-computer-use/audits/1@techreport{stablyai-stablyai-computer-use-2026,
author = {stablyai},
title = {computer-use security audit report (audit version 1)},
institution = {Skillstore},
year = {2026},
number = {1},
url = {https://skillstore.io/skills/stablyai-computer-use/audits/1},
note = {Author version unspecified}
}cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "computer-use security audit report (audit version 1)"
version: "unspecified"
type: report
authors:
- name: "stablyai"
date-released: "2026-07-19"
url: "https://skillstore.io/skills/stablyai-computer-use/audits/1"
identifiers:
- type: other
value: "skillstore:stablyai-computer-use:audit:1"
description: "Skillstore immutable audit report identifier"
Ask the agent to report what is visible in an app such as Spotify or Slack by reading its accessibility tree and screenshot, without changing anything.
Have the agent set a browser address field, submit a search, or complete a form field by field, verifying focus after each step.
Direct the agent to click controls, set values, and press keys through the accessibility layer instead of fragile pixel coordinates.
Read the current state of the Spotify app and tell me what is playing. Do not change anything.
List my open browser windows, pick the one showing my email, and get its app state.
In my Edge browser window, set the address bar to example.com and press Return.
Open the compose form in my mail app, type the subject line I give you, then confirm the focused field after each step before continuing. Do not send the message.
Author
stablyaiLicense
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Repository
https://github.com/stablyai/orca/tree/5848550b5ebd08098cad3e2b9086fd2472a52944/skills/computer-useRef
e8ce3fcb20197aefea54f9fb43ccce4716e3209c
Maintenance freshness
7/19/2026
Usage
0 downloads · 0 views
File structure
📄 SKILL.md
Manage Linear Tickets Through Orca
Linear ticket work can become inconsistent across issue updates, workflow transitions, and completion records. This skill uses Orca to guide ticket discovery, execution, and documented closure.
Coordinate Orca Agent Workflows
Multi-agent coding tasks can lose ownership, status, and completion signals. This skill guides Claude, Codex, and Claude Code through Orca orchestration commands for supervised dispatch, gates, and worker completion.
Manage Orca Worktrees and Terminals
Orca projects often span worktrees, terminals, automations, and embedded browser tabs. This skill gives agents a precise CLI workflow for managing those Orca surfaces.
Configure Orca Workspace Environments
Per-workspace environment recipes can fail because CLI selection and provider lifecycle details vary. This skill loads Orca guidance matched to the active version.
Control iOS Simulators Through Orca
iOS testing often requires switching between agent tools, simulator controls, and evidence collection. This skill routes simulator interaction through Orca and loads guidance matched to the active CLI.
Reduce Cognitive Load with ADHD Mode
by fuzzywigg
Complex conversations can create too many choices, unclear priorities, and difficult restarts. This skill structures replies around one active task and clear recovery cues.
Build Accessible Tailwind Interfaces
by nextlevelbuilder
Building consistent, responsive interfaces requires many component, styling, and accessibility decisions. This skill provides shadcn/ui patterns, Tailwind guidance, and focused automation.
Audit Web Accessibility for WCAG Compliance
by 89jobrien
Accessibility gaps can block users and create compliance risk. This skill guides WCAG audits, screen reader checks, keyboard testing, and remediation planning.
Improve SwiftUI Code with Expert Guidance
by avdlee
SwiftUI projects can accumulate state, layout, accessibility, and performance problems. This skill provides focused review guidance and optional Instruments trace analysis to identify practical improvements.
Convert Images to Searchable PDFs
by zjsxply
Finished images often lose search and copy support when exported as flat PDFs. This skill adds an aligned text layer while preserving the visual design.
Create Accessible PowerPoint Decks
by DNYoussef
Manual presentation production can be slow and inconsistent. This skill guides Claude, Codex, or Claude Code through structured PPTX generation and validation.