open-computer-useGuidance for installing, configuring, and operating Open Computer Use, an open-source Computer Use MCP service for macOS, Linux, and Windows.
Install via ClawdBot CLI:
clawdbot install ifuryst/open-computer-useGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://github.com/iFurySt/open-codex-computer-useAudited Jun 5, 2026 · audit v1.0
Generated Oct 8, 2026
QA teams connect Open Computer Use to an MCP-capable agent so it can drive native desktop apps, click through workflows, and verify app state after each action. Element indexes from get_app_state make tests more stable than pixel-based coordinate automation.
Support agents use computer-use tools to reproduce bugs, gather app state, and safely perform repetitive tasks like opening tickets or filling internal forms for macOS, Linux, and Windows users. Human approval rules prevent risky actions such as sending messages or changing settings.
Organizations leverage accessibility element indexes and app state introspection to automate tasks in assistive desktop environments. The agent can navigate applications using labeled elements rather than screen coordinates, improving reliability and inclusiveness.
Finance teams automate structured data entry into legacy desktop applications, using click, type_text, and press_key to populate records and reconcile information. The skill's operating rules require explicit approval before purchases or sensitive data exposure.
Clinicians' support staff use the agent to navigate desktop EHR or scheduling applications, read app state, and perform routine non-clinical navigation tasks. Strict approval gates ensure no messages, deletions, or system changes happen without human consent.
The core open-computer-use CLI and MCP server are freely available under an open-source license, driving adoption across Codex, Claude Code, Gemini CLI, and opencode users. The maintainers monetize through paid support contracts, priority issue resolution, and enterprise onboarding assistance.
Offer a hosted control plane that pairs Open Computer Use agents with centralized policy, approval workflows, and audit logging for desktop actions. Enterprises pay per managed desktop or per automation run rather than maintaining local MCP setups.
Package Open Computer Use with prebuilt MCP tool sequences and approval rules tailored to industries like healthcare, finance, or QA. Customers buy ready-to-deploy automation bundles instead of building computer-use scripts from scratch.
💬 Integration Tip
Install the CLI globally and run `open-computer-use doctor` first to confirm permissions and MCP registration; then add the `mcpServers` JSON block to your client and prefer accessibility indexes from `get_app_state` over coordinate clicks for more reliable automation.
Scored Oct 8, 2026
Control desktop applications on Windows — launch, close, focus, resize, move windows, simulate keyboard/mouse input, manage processes, control VSCode, read clipboard, and capture screen info. Use when the user wants to interact with any running program, switch windows, type text, press shortcuts, open files in VSCode, manage running processes, or get system display information.
Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Use when users ask to "critically review" my code or a PR, "critique my code", "find issues in my code", or "what's wrong with this code". Identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required, Suggestions) and specific, actionable recommendations.
Pragmatic coding standards for writing clean, maintainable code — naming, functions, structure, anti-patterns, and pre-edit safety checks. Use when writing new code, refactoring existing code, reviewing code quality, or establishing coding standards.
Claude Code integration for OpenClaw. This skill provides interfaces to: - Query Claude Code documentation from https://code.claude.com/docs - Manage subagents and coding tasks - Execute AI-assisted coding workflows - Access best practices and common workflows Use this skill when users want to: - Get help with coding tasks - Query Claude Code documentation - Manage AI-assisted development workflows - Execute complex programming tasks
Plan, draft, version, and refine written content with enforced versioning and quality audits.
Use when writing tests, creating test strategies, or building automation frameworks. Invoke for unit tests, integration tests, E2E, coverage analysis, performance testing, security testing.