This skill helps you craft reliable Prowler SDK tests by enforcing AWS moto mocking and Azure MagicMock patterns for provider checks.

This skill helps you write robust API tests for JSON:API, RBAC, and cross-tenant isolation in Python projects, with Celery task validation.

This skill automates creating pull requests for prowler following the project template and conventions to streamline collaboration.

This skill guides Prowler documentation writing with brand voice, structure, and SEO best practices for features, tutorials, and guides.

This skill helps write reliable Playwright end-to-end tests for the Prowler UI using base patterns, MCP workflow, and page objects.

This skill helps enforce Prowler API patterns with tenant isolation, RLS, RBAC, and provider lifecycle across models, serializers, and tasks.

This skill helps diagnose and fix PR CI failures in prowler-ci by analyzing workflows, filters, and gating rules across .github/workflows.

This skill keeps AGENTS.md Auto-invoke sections in sync with skill metadata to ensure accurate invocation prompts.

This skill helps you apply prowler ui conventions using shadcn/ui and Tailwind to organize components, hooks, and styles for consistent UI.

This skill helps you style Tailwind 4 patterns with cn() safely, avoiding var() in className and hex colors.

This skill creates new justification files in .agents/justifications with a unique three-word ID, frontmatter, and a formatted title.

This skill creates new scratch files in .agents/scratches with a unique three-word ID, frontmatter, and formatted title to organize ideas.

This skill helps you design and run multi-dimensional evaluation for agent systems, enabling robust benchmarking, continuous improvement, and quality gates.

This skill helps you design and implement multi-agent systems with context isolation, coordination patterns, and scalable architectures.

This skill models agent beliefs, desires, and intentions from RDF context, enabling explainable BDI reasoning and coherent multi-agent coordination.

This skill helps you understand and design efficient context windows for AI agents, optimizing loading and budgeting across systems.

This skill helps manage and compress long agent conversations by optimizing tokens-per-task through anchored summaries and structured artifact tracking.

This skill enables building and validating author-style fine-tuning pipelines from ePub to LoRA-trainable models for book voices.

This skill helps you design and evaluate LLM-backed projects, selecting architecture, tasks, and cost estimates for efficient agent development.

This skill helps design and optimize agent tools, improving tool descriptions, consolidation, and interfaces for reliable multi-agent systems.

This skill enables automated LLM-based evaluation pipelines, compares model outputs, and mitigates biases to deliver consistent, objective quality assessments.