Loading...
Loading...
Found 9 Skills
Use Orca's computer-use CLI to inspect and control local desktop apps through accessibility trees, screenshots, and safe UI actions. Use when an agent needs to list desktop apps, get an app state, read visible UI, click, type, press keys, scroll, drag, set values, or perform app accessibility actions. Triggers include "computer use", "orca computer", "list apps", "get app state", "read Spotify", "read Slack", "click app", "type text", "press key", "set value", "scroll app", "drag app", and desktop app interaction tasks.
Design and implement comprehensive evaluation systems for AI agents. Use when building evals for coding agents, conversational agents, research agents, or computer-use agents. Covers grader types, benchmarks, 8-step roadmap, and production integration.
Give an AI agent its own real browser over MCP tool calls - launch, navigate, click, fill, screenshot, extract text, run JS - with a kernel-level real-device fingerprint and a persistent profile, so the session stays logged in between runs and pages see one coherent device instead of a headless build. No Playwright or SDK code to write. Use when an agent should operate a site itself, when a computer-use / browser-use setup needs a captured real fingerprint rather than a synthetic one, when agent sessions keep losing their login, or when comparing hosted agent-browser services. Also for 'MCP browser', 'browser MCP server', 'let my agent browse the web', 'agent browser control', 'browser-use MCP', 'computer use browser', 'Browserbase alternative', 'Steel browser alternative', 'headless browser detected'. Node (npx) or Python; Windows x64, macOS Intel + Apple Silicon, Linux x64 / arm64. SDK and REST reference is anti-detect-browser; account isolation is multi-account-isolation.
Loads orchestrate mode — a disciplined delivery loop that enforces BDD specs in specs/, real integration tests (no mocks), PR CI and CodeRabbit babysitting, and mandatory end-user QA via computer-use or CLI dogfooding before anything is considered done. Use when starting any non-trivial implementation task, feature build, or delivery where you want the work driven from spec to proven-shipped state rather than stopping at "tests pass".
Drive a real browser to QA a feature end-to-end as a user would. Loads the right mix of Playwright MCP, Claude-in-Chrome, and computer-use, plus the failure modes to avoid. Use whenever you need to verify a UI feature works in a browser, capture PR screenshots, repro a customer bug visually, or do end-of-task dogfooding before declaring something "done". This is the QA stage of orchestrate mode.
Control terminal TUIs and web/Electron apps for testing, demos, QA, and computer-use tasks. Use when you need to automate a CLI, drive a browser, record a demo, or capture proof artifacts.
Build and run Gemini 2.5 Computer Use browser-control agents with Playwright. Use when a user wants to automate web browser tasks via the Gemini Computer Use model, needs an agent loop (screenshot → function_call → action → function_response), or asks to integrate safety confirmation for risky UI actions.
Build AI agents that interact with computers like humans do - viewing screens, moving cursors, clicking buttons, and typing text. Covers Anthropic's Computer Use, OpenAI's Operator/CUA, and open-source alternatives. Critical focus on sandboxing, security, and handling the unique challenges of vision-based control. Use when: computer use, desktop automation agent, screen control AI, vision-based agent, GUI automation.
Desktop automation CLI for AI agents (macOS, Linux, Windows). Screenshot, click, type, scroll, drag with native Zig backend. Use this skill when automating desktop apps with computer use models (GPT-5.4, Claude). Covers the screenshot-action feedback loop, coord-map workflow, window-scoped screenshots, and system prompts for accurate clicking.