Skill UI

This skill audits a live web page against WCAG standards. It precisely locates accessibility violations, providing a detailed, selector-grounded worklist of necessary fixes without making any changes to the code. Ideal for QA engineers and developers needing a comprehensive, non-destructive report of broken accessibility elements.

This skill manages the acc deliberation queue by draining open or waiting brain_frames checkpointed during headless runs. It allows listing frames, reading context, deliberating, and submitting proposals via acc_act with runtime continue. It ensures safe resubmission and calibrates the Work Model using PREDICT lines.

This skill routes goals through the acc's scored-memory loop using acc_act with runtime="solve". It enables deliberation on returned brain_frames and submission via continue. Users must reason over frames and end proposals with a prediction score. It ensures honest commitment closure and prevents solo-derivation outside the loop.

Comprehensive offensive techniques for Microsoft Active Directory environments including reconnaissance, credential harvesting, Kerberos attacks, lateral movement, privilege escalation, and domain dominance for authorized red team operations and penetration testing.

This comprehensive toolkit allows users to automate core marketing and CRM operations within ActiveCampaign. Key functionalities include managing contacts (creation, lookup), updating contact tags, subscribing/unsubscribing from lists, enrolling contacts in automation workflows, and creating associated follow-up tasks. It streamlines communication and customer lifecycle management.

Add an iOS App Clip target to an Expo project, including setup for associated domains, AASA file hosting, and Smart App Banner. Use when the user mentions App Clip, AASA, appclips, or wants a lightweight iOS Clip invoked from a URL.

A comprehensive guide to building production-grade evaluation systems for Large Language Models (LLMs). This skill covers advanced methodologies, including Direct Scoring and Pairwise Comparison, alongside critical techniques for mitigating systematic biases (e.g., Position Bias, Length Bias). Learn how to select appropriate metrics and structure prompts to ensure reliable, consistent, and objective quality assessment across various AI applications.

This skill provides expert legal assistance across all areas of Brazilian law, including family, criminal, labor, tax, and corporate law. It utilizes AI tools to analyze legal documents and provide guidance on judicial processes. Suitable for users seeking specialized legal knowledge in Portuguese.

A professional-grade 'Living Pipeline' that integrates advanced AI reasoning into the SDLC. It provides autonomous guardrails for system security, cloud cost management (FinOps), and Kubernetes compliance. It audits Linux Kernel patches for memory vulnerabilities, detects cost drifts in Terraform plans, and generates hardened K8s manifests from natural language policies.

Build automated evaluation suites for AI agents using golden datasets, rubrics, and regression gates. Covers prompt-level unit evals, tool-calling checks, end-to-end tasks, safety/adversarial tests, and LLM-as-judge scoring to gate deployments on quality.

Evaluate AI agent behavior using versioned cases and explicit verifiers. This skill helps compare agent or prompt changes, reproduce failures, and run regression tests. It ensures reliability on declared task distributions without inferring product readiness from generic scores. Includes methods for uncertainty reporting and safety verification.

Generate decision-ready reports from AI agent evaluation runs. This skill ensures autonomous, assisted, failed, and timed-out outcomes remain distinct and comparable. It defines metrics with correct denominators, handles latency and cost populations honestly, and maps evidence to decision gates. Ideal for benchmarking, regression testing, and production readiness validation of AI agents.