Testing skills

This skill scans codebases and infrastructure for traditional and agentic security issues, detects secrets, and guides remediation for secure deployments.

This skill automatically converts legacy Python 2 code to Python 3 with compatibility checks and generated unit tests.

This skill enables cross-model verification by spawning a judge subagent to review plans or code before execution, reducing blind spots and errors.

This skill runs PinchBench benchmarks to evaluate OpenClaw agent performance across calendar, email, coding, and multi-step workflows.

This skill guides planning, implementation, verification, and testing for clean Python coding workflows, storing user preferences locally.

This skill enables you to manage live agent takeover over a voice gateway, orchestrating dial, turn handling, and handback for seamless calls.

This skill helps you design and run adaptive tests with AI-generated questions and personalized recommendations using IRT-based CAT.

This skill synchronizes source Google calendars into private holds on target calendars to prevent double-booking idempotently.

This skill helps you describe trading ideas in natural language, generates a Python backtest strategy, and presents backtest results.

This skill helps you continuously improve OpenClaw agents by analyzing conversations, logging insights, and generating weekly improvement reports.

This skill designs and generates complete OpenClaw agent workspaces with safety rails, tests, and guardrails to accelerate secure agent deployment.

This skill automatically scrapes free proxy nodes from public sources, tests performance, and delivers usable configurations in multiple formats.

This skill helps you apply modern web best practices for security, quality, and maintainability across TypeScript, React, and code reviews.

This skill validates emails via the apipick Email Validator API, checking syntax, MX records, and disposable domain status to confirm deliverability.

This skill runs a VirusTotal style security review on OpenClaw/Cursor skills before install, highlighting RCE risks and malicious code indicators.

This skill generates mock API servers from OpenAPI specs or examples, enabling realistic data, delays, and error simulation for testing.

This skill generates final audio from a Composition Plan using a validated AI music model, ensuring duration, style, and fidelity with retries.

This skill helps you orchestrate interactive terminal sessions with tmux for TUI apps, long-running workflows, and real-time output capture.

This skill automatically generates pytest-compatible unit test templates from Python signatures and docstrings to speed up test scaffolding.

This skill helps you develop, review, and fix code using Claude Code CLI for multi-file edits, tests, and linting.

This skill ensures instruction compliance by tracing root causes, validating fixes with automated validators, and preventing repeated failures across future