Skill UI

This skill provides comprehensive techniques for security-testing Retrieval-Augmented Generation (RAG) pipelines. It probes for indirect prompt injection, which occurs when malicious instructions are embedded in retrieved documents, and tests for embedding-space manipulation. Using advanced tools like NVIDIA garak, Promptfoo, and PyRIT against vector stores (FAISS, Chroma, etc.), users can validate retrieval guardrails and secure CI/CD gates against adversarial inputs and data leakage.

Analyze Ahrefs data for SEO metrics including domain rating, backlinks, organic keywords, and content explorer results. Provides live data with confidence weighting and cost guardrails for batch operations.

Design and schedule recurring, self-running marketing workflows with defined triggers, cadences, guardrails, and stop conditions. Orchestrate SEO, ads, content, outbound, and retention loops as always-on systems.

Pattern for controlling LLM API costs while preserving quality. Combines complexity-based model routing, immutable budget tracking, retry logic limited to transient failures, and prompt caching. Use when building LLM API apps, processing batches with varying difficulty, or enforcing budget guardrails in production.

This skill provides comprehensive guardrails for handling Protected Health Information (PHI) in US healthcare software. It guides development teams on data classification, security best practices, access control, and audit logging to ensure strict adherence to HIPAA regulations. Use it when dealing with patient data storage, transmission, or processing to prevent breaches and maintain compliance.

Generates a comprehensive and structured brief for influencer marketing campaigns. This tool guides users through setting campaign objectives, defining creator criteria, establishing creative guardrails, managing compensation structures, and ensuring global compliance (e.g., FTC, EU deepfake rules) for paid partnerships. Ideal for brand marketing teams and agencies.

A comprehensive guide for drafting professional and strategic rebuttals for major academic conferences, such as ACM Multimedia. Learn how to triage reviewer comments, structure arguments for the Area Chair, address factual errors, and incorporate small, confirmatory results while maintaining anonymity and adhering to strict policy guardrails.

This guide helps authors sharply frame their econometric research contributions, specifically tailored for high-impact academic journals like The Econometrics Journal (EctJ). It enforces a strict four-part structure: identifying failure modes of incumbent methods, stating the smallest sharp advance, detailing the applied payoff, and establishing scope guardrails. This ensures the core novelty and practical value are immediately obvious to reviewers.

This module provides a lazy adapter registry to seamlessly integrate OpenMed's clinical PII detection with major NLP frameworks like Microsoft Presidio, spaCy, and LangChain. It allows users to use OpenMed for enhanced PII recall, merge spans, or implement on-device PHI redaction guardrails without rewriting entire pipelines.

Autonomous DevSecOps & FinOps guardrails that review Linux kernel patches for memory safety, analyze Terraform cost drifts to prevent bill spikes, and translate natural language security intent into hardened Kubernetes policies. Integrates advanced AI reasoning into the SDLC for high-stakes audits and CI/CD quality gating.

Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration. Ensures graceful degradation and clear failure modes. Capable of agent architecture design, tool calling, memory management, and complex task decomposition. Includes knowledge of ReAct loops, Plan-and-Execute patterns, and safety guardrails.

Secure AI coding agents such as Claude Code, Cursor, Codex and Copilot with permission boundaries, secret scanning, sandbox isolation, command allowlists and code review gates for team environments.