Testing skills

This skill performs pre-release checks for code quality, API health, deployment readiness, and versioning to ensure smooth launches.

This skill guides turning an approved design into actionable tasks with clear steps and verification to accelerate implementation.

This skill guides you through planning, designing, and implementing statistically rigorous A/B tests to drive measurable improvements.

This skill helps you diagnose and resolve root causes systematically, preventing patch chains and ensuring fixes address the underlying problem.

This skill automates mobile UI tasks by driving Android devices via AutoGLM Phone Agent, enabling tapping, typing, swiping, and screenshots.

This skill helps you set up, audit, and debug analytics tracking (GA4, GTM) to ensure accurate, actionable data.

This skill analyzes and safeguards ClawHub skills before installation, helping you avoid unsafe packages and ensure compliance.

This skill enables safe local evolution loops for OpenClaw by planning, validating, promoting, and rolling back candidate skills.

This skill lets you measure real API latency across major LLM providers and compare results quickly to identify fastest options.

This skill enforces evidence-first debugging for coding tasks, guiding the agent through bounded escalation and dignified communication to resolve issues

This skill scaffolds a minimal MCP server from a tool list, generating a contract summary and starter layout to accelerate setup.

This skill helps you manage Ethereum Cannon workflows safely by guiding dry-runs, deployments, and inspections with clear prompts.

This skill helps plan, design, and implement rigorous A/B tests that generate statistically valid insights and actionable improvements.

This skill coordinates three specialized coding agents to collaboratively review, refactor, and validate code within a shared project, ensuring consensus.

This skill analyzes JUnit retry artifacts to identify flaky tests and produce a prioritized triage report.

This skill helps you generate Python tests to achieve coverage targets by analyzing code and creating pytest files.

This skill helps you design and test agents integrating the eSIMPal API to buy, create orders, and deliver activation securely with approvals.

This skill ensures AI tasks are executed faithfully to initial rules, propagating guidelines to subagents and validating consistency across concurrent work.

This skill verifies model identity by testing knowledge cutoff, safety style, multimodal capability, and thinking language patterns to determine authenticity.

This skill analyzes Sui Move test coverage, identifies untested paths, and guides automated test generation and security-focused improvements.

This skill runs a 29-point GEO site readiness audit to assess AI accessibility, structured data, content citability, and technical setup for your website.