Testing skills

This skill ensures deployment reliability by probing gateway health, validating doc sync, auditing channels, and generating MADR ADRs.

This skill quickly generates a professional CLI scaffold supporting Commander.js, yargs, oclif, and Ink, with templates, docs, tests, and npm publishing.

This skill helps you evaluate emergent cognition in AI agents by guiding structured self-assessment, creative reasoning, and meta cognitive probing across

This skill guides and automates the two-step CUCHD staff portal login process, handling username entry, password reveal, and error reporting.

This skill helps you install and wire a structured OpenClaw deep-research sub-agent for reproducible, end-to-end research workflows.

This skill performs zero-regression bug fixes: reproduce, analyze root cause, scope, predict impact, fix, verify, review, and reflect for improvement.

This skill helps you generate, modify, and review code using Claude CLI, accelerating project setup and debugging across languages.

This skill controls an Android device via CLI tools, auto retrying non-root commands with a root fallback for reliable automation.

This skill guides high-quality software development following SOLID principles, disciplined branching and commits, and session persistence for reliable Python

This skill provides a stable native macOS browser for OpenClaw agents, enabling tabbed browsing, login helpers, and interactive web access.

This skill provides a read-only MCP interface to the Lawmatics API, enabling secure, streamlined access for automation and testing.

This skill helps you test REST APIs with customizable headers, authentication, and bodies, speeding debugging and automated checks.

This skill orchestrates local Codex MCP tasks to implement, fix, or test features within a project using the local Codex installation.

This skill helps you safely switch OpenClaw's default LLM model by validating availability before updating config and optionally restarting gateway.

This skill performs dual-model embedded code reviews comparing Claude Code and Codex findings to detect memory, ISR, and interface hazards.

This skill helps you recover stuck or failed workflows by recommending targeted skills and concrete recovery steps.

This skill enables text-to-speech synthesis using espeak-ng to generate spoken output from input text efficiently.

This skill performs security-first vetting of external skills before installation, delivering risk scores, red flags, and practical safety recommendations.

This skill orchestrates a multi-agent development team to plan, design, implement, test, and deliver complex projects across roles.

This skill opens a browser window using a normalized URL to enable deterministic, quick-launch automation in local workflows.

This skill provides production-ready FastAPI patterns with Pydantic v2, async endpoints, OAuth2/JWT, and Kubernetes deployment guidance.