Testing skills

This skill helps you validate AI outputs by coordinating multiple critics that cite evidence against rubrics to deliver a structured verdict.

This skill orchestrates a full pre-production validation sweep for GCP apps, generating test plans, executing checks, and producing go/no-go reports.

This skill validates PDFs against PDF/UA-1 deterministically via ua1.dev, producing compact verdicts for CI gates and remediation loops.

This skill helps you manage Nostr posting and engagement via nak, enabling note creation, threaded replies, and reliable relay monitoring.

This skill provides bulletproof AI code verification by running parallel slop scan, type check, mutation testing, and cross-verification to ship safe code.

This skill helps you manage bot email accounts programmatically, enabling creation, inbox checks, and optional heartbeat alerts for testing workflows.

This skill enforces test-driven loops for non-deterministic agents, ensuring tests run before production code and blocking warnings as errors.

This skill helps determine semantic version bumps (major, minor, patch) and aligns releases with SemVer 2.0.0 guidelines.

This skill performs a deep security audit with 1,000 iterations to uncover critical risks and strengthen pre-release compliance.

This skill enforces mandatory pre-deployment quality assurance by validating builds, testing browsers, ensuring mobile responsiveness, and verifying links and

This skill automatically validates construction data against ISO 19650, IFC, COBie, and UniFormat, ensuring compliance and reducing manual review time.

This skill helps AI agents stay honest and grounded by applying practical drift checks, ego awareness, and uncertainty practices in every session.

This skill conducts a minimal test matrix for Model Studio skills by running a single request per skill and recording results.

This skill aggressively stress-tests LLM throughput by iterative prompt-tool-LMM cycles to maximize token consumption while monitoring usage.

This skill helps you implement Jest best practices across mocks, async tests, timers, and snapshots to improve test reliability.

This skill performs multi-agent adversarial security reviews by enlisting three LLMs to debate findings and expose real vulnerabilities.

This skill helps you set up and verify Polymarket trading automation by configuring wallet, API credentials, and connectivity.

This skill generates reproducible fine-tuning run plans for transformer models, including hyperparameters, seeds, and model-card outputs for Hugging Face or

This skill automates production-grade vLLM deployment on AMD ROCm GPUs, with env checks, model detection, health tests, and comprehensive logging.

This skill enforces rigorous MLOps validation with typing, linting, testing, and security checks to improve code quality and reliability.

This skill writes, runs, and fixes tests across unit, integration, and E2E, while linting code and auto-fixing failures.