66 skills · sorted by relevance
Manage Orca worktrees, separate working directories, along with terminals, repositories, and its embedded browser through the CLI. Use it to hand work to another agent, manage artifacts, run automations, and share skills within Orca.
Build Claude applications using guidance for the official Anthropic SDK. Choose an integration approach, implement streaming and tool use, and follow workflows for model migration, prompt audits, evaluation, and cost optimization.
Design agents that operate desktop or browser software through screenshots, mouse actions, and keyboard input. Compare ways to locate interface elements, diagnose coordinate errors, handle changing screens, and evaluate task completion, operating speed, and safety boundaries.
Operate desktop apps and isolated browsers on registered computers by inspecting interface controls, entering information, and checking results. The skill also covers screenshots and recording, with separate routing for the user's signed-in Chrome through Chromewhale.
Plan X content, improve opening lines and threads, and review account performance using post data. With a focus on AI and technology, the skill supports content reviews, weekly growth plans, and HTML diagnostic reports.
Build AI agents that inspect screenshots, choose actions, and operate a mouse and keyboard. Covers the observation and action loop, desktop control examples, and isolated environments that restrict access to files, credentials, and networks.
Build a computer-control loop where Cua Driver observes and acts, while TypeSafe Jev chooses from predefined actions. Validate each choice, execute one action at a time, and verify the result before continuing.
Read and operate desktop applications through their interfaces, including clicks, text entry, menus, and scrolling. Use it to inspect or edit app content when a dedicated connector, API, or command-line tool cannot handle the task.
Prepare a local LangBot environment for development and browser testing. The skill covers service startup, shared connection settings, browser access, proxy troubleshooting, and reusable login profiles, with guidance for Linux and WSL environments.
Drive native desktop apps through DeepChat's built-in Computer Use tools. Use when the user asks to operate, inspect, automate, or perform a GUI task in a real desktop application.
The English summary is being prepared. Showing the original description.
Connects AI agents to remote Windows desktop applications on Amazon WorkSpaces Applications (AppStream 2.0) through the managed Agent Access MCP server, and guides reliable desktop automation. Covers connecting an agent to the MCP endpoint (SigV4, streaming URL, and Active Directory SAML/Domain Join), BLOCKING vs POLLING connect modes, the computer-use tools (screenshot, click, type, key, scroll), screenshot-budget and action-batching discipline, MCP tool forwarding (forwarded___ tools), session lifecycle and expire-on-delete, and troubleshooting connection errors. Use when building or debugging an agent that drives a remote Windows desktop or GUI application via WorkSpaces Applications / AppStream — including "dcv session not ready", "client_disconnected", 400 signing-region, POLLING/connection_status, SAML assertion, or forwarded tool questions. Not for Amazon WorkSpaces Personal/Core virtual desktops or general AppStream fleet administration unrelated to agent access.
The English summary is being prepared. Showing the original description.
Use when a task needs an app on the user's own screen — a native desktop application (instrument control software, Origin, GraphPad, ImageJ, a reference manager, a spreadsheet), or a desktop browser window that needs window-level control. Read before the first `computer` call. Covers the observe-act-observe loop, why element indexes go stale, which action to prefer for which control, what "unverified" means and why it must never be reported as success, and the recovery for each error code. Not for page-level web automation (use the browser connector) and not for anything that can be done from the shell.
The English summary is being prepared. Showing the original description.
Two scopes: (1) drives Kimi.app via computer-use for Work/Agent data-plugin queries (天眼查、同花顺 iFinD、SEC、IMF etc.) and Chat's built-in 深度研究 report; (2) kimi-cu macOS desktop-automation playbook — AX set_value / keyboard / click channel selection, foregrounding, AX-tree recovery, form & dialog recipes. Use for "用 Kimi 查" / "操作 Kimi 客户端" / "Kimi 插件" / "Kimi 深度研究" / driving any macOS desktop app (Electron/webview/native) via kimi-cu. Not for kimi.com browser automation (use kimi-webbridge) or direct iFinD API access.
The English summary is being prepared. Showing the original description.
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.
The English summary is being prepared. Showing the original description.
Use Avibe's local Computer Use CLI for carefully bounded desktop observation and actions.
The English summary is being prepared. Showing the original description.
Delegate broad computer-use tasks to ARK CUA for Volcengine AgentPlan users through an authenticated cloud desktop, and synchronize explicit credentials to a caller-owned CUA through Credential Agent. Use for web or desktop-app operation, file workflows, reusable task contexts, artifacts, temporary CUA App URLs, desktop shutdown/start/recovery, inspection, or exact browser, environment, secret, Credential Set, and managed-file credential setup/sync/status/reset. Do not use when local reasoning or a purpose-built local/API tool can complete the request more directly.
The English summary is being prepared. Showing the original description.
Run your first computer-use test in minutes.
The English summary is being prepared. Showing the original description.
Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).
The English summary is being prepared. Showing the original description.
Goal-driven E2E testing where a browser agent (Playwright MCP / computer-use) reads a natural-language goal and explores the app via the accessibility tree to assert outcomes — no pre-written script. Covers when intent-driven beats scripted, making agent runs deterministic (pinned model, temperature 0, seeded data, bounded steps, explicit success assertion, snapshot-not-pixel), cost/latency control, the accessibility-tree-first interaction model, CI gating, and graduating a stable run into a scripted Playwright test. Use when: "agentic browser test," "goal-driven browser test," "let an agent explore the app," "natural-language E2E," "browser agent smoke test," "Playwright MCP test." Not for: Writing/maintaining deterministic scripted Playwright tests — that is playwright-automation. Testing your product's OWN LLM features — that is ai-system-testing. Related: playwright-automation, ai-system-testing, exploratory-testing, test-reliability, qa-project-context.
The English summary is being prepared. Showing the original description.
Systematically QA test any application — web apps, native macOS apps, Electron apps, CLI tools, interactive REPLs, or anything on screen. Three modes: browser (chromux/CDP, fast, DOM-level), computer (MCP computer-use, screenshot + pixel clicks, any app), and cli (tmux, send-keys + capture-pane for interactive terminals). Auto-selects mode or accepts --browser / --computer / --cli override. Use when asked to "qa", "QA", "test this site", "test this app", "find bugs", "test and fix", "fix what's broken", "dogfood", "exploratory test", "bug hunt", "QA this app", "사이트 테스트", "앱 테스트", "브라우저 QA", "화면 보고 테스트해줘", "네이티브 앱 테스트", "screen test". Three tiers: Quick (critical/high only), Standard (+ medium), Exhaustive (+ cosmetic). Produces before/after health scores, fix evidence, and a ship-readiness summary.
The English summary is being prepared. Showing the original description.
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, Claude computer, OpenAI Operator, browser agent, visual agent, RPA with AI, " mentioned.
The English summary is being prepared. Showing the original description.
Submit expense reimbursements through Benepass (app.getbenepass.com). For users whose employer uses Benepass as their benefits platform. Handles login, benefit selection, form filling, receipt upload, and submission. Requires browser/computer-use capabilities.
The English summary is being prepared. Showing the original description.
Verify NowStack Mobile iOS/Expo changes in the Apple Simulator with `xcrun simctl`. Covers single or parallel Metro/device flows, deep-link navigation, preview routes, and OTP sign-in. Use for `ns ios verification`, "test on simulator", or changed `mobile-app/**`; never use computer-use.
The English summary is being prepared. Showing the original description.
Drive a native desktop app through Interpreter's builtin-cua-driver. Use get_app_state, click/type/scroll/drag, and verify by calling get_app_state again when the user asks to operate a real desktop app, browser chrome, native dialog, menu, secure prompt, file chooser, or hidden/background window.
The English summary is being prepared. Showing the original description.