Skill UI

Detects goal hijacking vulnerabilities where malicious instructions are hidden within external content sources processed by the agent, such as retrieved documents (RAG), uploaded files, or web page content. This skill simulates these attack vectors to ensure the agent only uses the provided context for the stated task and does not execute embedded hidden commands.

A comprehensive technical guide for developers managing integrations with Lucidchart. It details strategies for handling API version changes, including version detection, schema migration (e.g., flat shapes to page-grouped hierarchies), rollback mechanisms, and common error troubleshooting (e.g., permission model updates, coordinate system shifts). Essential for maintaining compatibility when using Lucidchart's evolving diagramming platform.

This skill helps test the robustness of an AI agent's authorization mechanisms. Use it when the agent handles user roles, permissions, or sensitive data (e.g., admin functions, cross-tenant data). It simulates attempts to bypass authentication, escalate privileges, or access data belonging to other users or tenants.

This skill establishes a comprehensive CI/CD pipeline specifically for Abridge clinical AI integrations using GitHub Actions. It enforces critical healthcare compliance steps, including FHIR R4 resource validation, robust detection of Protected Health Information (PHI) leaks (like SSN), and end-to-end sandbox integration testing. Ideal for deploying secure, compliant AI applications in the healthcare sector.

This skill helps healthcare organizations optimize their Abridge AI spending. It provides structured analysis across provider utilization, session waste detection, and ROI calculation. Use it when reviewing complex billing statements, optimizing contract tiers, or ensuring maximum return on investment for AI adoption.

This workflow automates the design handoff process by creating a continuous pipeline from Figma designs to functional React code. It scans Figma components, generates code batches (supporting TypeScript, Tailwind CSS, etc.), and includes change detection to automatically update the codebase when the design source changes. Ideal for building complex design systems and implementing CI/CD design-to-code workflows.

This comprehensive skill provides multi-layered guardrails for integrating with LLMs like Claude. It enforces security and compliance by implementing input validation (PII detection, length checks), system prompt restriction (scope control, safety rules), output filtering (preventing sensitive data leakage), cost governance, and model access policies. Ideal for building secure, robust, and governed AI applications.

A comprehensive guide to using AssemblyAI for rich audio processing. This guide covers basic speech-to-text transcription from URLs or local files, along with advanced AI features. Capabilities include speaker diarization, sentiment analysis, key phrase extraction, entity detection, and powerful LLM-powered analysis (LeMUR) for summarization and Q&A. Ideal for integrating deep, multi-faceted audio insights into applications.

This reference architecture provides a comprehensive blueprint for building a robust revenue intelligence data platform integrated with Clari. It covers the entire data lifecycle, including API data extraction (ETL pipeline), data warehousing design (Snowflake/BQ), change detection logic, and advanced analytics/alerting layers. Use this guide when designing a scalable forecast tracking system, planning complex data integrations, or establishing best practices for enterprise revenue analytics.

This skill provides comprehensive handling for sensitive data extracted from the ClickUp API. It includes automated PII detection (emails, phone numbers, SSN), data redaction for secure logging, and mechanisms to ensure GDPR/CCPA compliance through structured data exports. Furthermore, it enforces data retention policies, managing data lifecycle from collection to secure deletion.

This skill provides robust mechanisms to ensure data privacy when interacting with Cohere APIs (Chat, Embed, etc.). It implements advanced PII detection (emails, SSNs, IP addresses, etc.), performs pre-call redaction to mask sensitive information, and includes post-call scrubbing and detailed audit logging. Essential for achieving GDPR/CCPA compliance and safely handling sensitive user data.

A comprehensive tool for creating high-quality training datasets for custom object detection and segmentation models. It supports multiple advanced annotation methods including BBox drawing, SAM2 pixel-perfect segmentation, and DINOv3 visual grounding. Features include AI auto-detection, object tracking, and standardized COCO format export, streamlining the entire data pipeline from capture to training.