Testing skills

This skill resets the OSWorld environment in soft or hard mode, preserving state or restoring from snapshot to support reflective testing.

This skill performs expert code reviews for quality, security, performance, and maintainability across languages, guiding improvements with a standardized

This skill advances forward up to a specified number of blocks, handling alignment and safety to maintain nav invariants.

This skill generates and runs ExUnit tests for Elixir projects, supporting describe blocks, setup callbacks, and async testing to verify behavior.

This skill helps you implement scalable Terraform infrastructure by applying module design, state management, security, and testing best practices across

This skill helps you design and implement scalable event-driven systems using patterns like event sourcing, CQRS, and message-driven communication.

This skill helps you advance toward a solid wall using nav conventions and motion tools to achieve stable adjacency.

This skill automatically detects test frameworks in a project by analyzing manifests, configs, and directories to guide test generation and execution.

This skill validates TSPEC documents against Layer 10 standards, ensuring structure, tagging, naming, and traceability meet compliance.

This skill tests and explains SQL sort by implementing descending order on a papers collection and validating output.

This skill checks if text is null, empty, or whitespace, enabling conditional logic and data validation.

This skill performs comprehensive SPEC content review, validating REQ coverage, interface completeness, and drift detection to ensure readiness for TASKS and

This skill tests and validates a calculate tool across arithmetic, trig, and variable substitution to ensure correct results.

This skill helps you build production-grade data tables with MRT V3 and MUI, covering server-side ops, CRUD, virtualization, and advanced filtering.

This skill automatically generates and validates TSPEC from SPEC documents for UTEST, ITEST, STEST, and FTEST with TASKS-Ready scoring.

This skill helps you inspect an agent-relative voxel grid for debugging by returning a formatted grid and structured coordinates.

This skill analyzes internal test data, applies a where citations > 100 filter, and returns the high-cited items.

This skill designs scalable test strategies for Python and TypeScript apps, covering unit to E2E testing, contract, mutation, and CI/CD integration.

This skill routes to the synthesize tool with format="comparison" to preserve behavior for legacy workflows.

This skill helps you systematically evaluate AI implementations with capability and regression tests, delivering actionable feedback and measurable quality.

This skill performs in-depth TSPEC content review, verifying test coverage, SPEC alignment, and identifies issues requiring manual follow-up.