abe-cursor-agentA comprehensive skill for using the Cursor CLI agent for various software engineering tasks (updated for 2026 features, includes tmux automation guide).
Install via ClawdBot CLI:
clawdbot install alvisdunlop/abe-cursor-agentGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Potentially destructive shell commands in tool definitions
curl https://cursor.com/install -fsS | bashCalls external URL not in known-safe list
https://cursor.com/installAudited Apr 23, 2026 · audit v1.0
Generated Sep 29, 2026
Integrate cursor-agent into CI/CD pipelines to automatically review pull requests for security vulnerabilities and performance issues. The non-interactive mode with JSON output formats enables seamless parsing and reporting within existing CI workflows.
Use the agent to systematically refactor large legacy codebases, improving type safety and reducing complexity. The agent can process multiple files in batch mode with force flags to auto-apply changes.
Leverage the agent's ability to analyze error logs and stack traces to identify root causes and suggest fixes. Integration with monitoring tools through MCP servers allows real-time debugging assistance.
Run the agent in non-interactive mode to generate and update documentation based on code changes. The agent can analyze new features and create comprehensive API documentation and usage examples.
Developers use cursor-agent interactively during coding sessions to get real-time suggestions, ask questions about code, and implement features collaboratively. Context selection with @filename allows precise file-level assistance.
Monetize through SkillBoss API Hub by charging customers based on API calls to the model routing endpoint. This aligns costs with actual usage and scales well across different customer sizes.
Offer cursor-agent as part of a comprehensive developer productivity platform with centralized management, SSO, and compliance features. Target large organizations that need governance and audit capabilities.
Provide a fully managed service where customers submit coding tasks and receive completed code changes. The service handles all infrastructure including tmux automation for reliable execution.
💬 Integration Tip
Always use tmux when calling cursor-agent from automated systems or subprocesses to avoid indefinite hanging due to TTY requirements. For CI pipelines, prefer non-interactive mode with JSON output and --force for unattended operation.
Scored Sep 29, 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.