Skill UI

A comprehensive, production-ready patterns library for interacting with the ClickUp API v2. It provides typed wrappers, robust error handling, rate limit management, and implements singleton/multi-tenant support, making complex ClickUp integrations reliable and scalable in TypeScript projects.

This guide provides a comprehensive architectural pattern (Adapter Pattern) for migrating code between different versions of the ClickUp API (v2 to v3). It addresses breaking changes, endpoint structural shifts, and terminology changes (e.g., 'Team' vs 'Workspace'), ensuring smooth and robust integration during large-scale platform upgrades.

Implements a robust, multi-tenant authorization layer for Cohere API v2. This solution enforces Role-Based Access Control (RBAC), manages individual API keys per team, and implements per-team usage limits and daily budget tracking. It is essential for large-scale applications requiring strict resource isolation and cost governance across multiple internal services.

A comprehensive guide and set of tools for establishing a local development workflow tailored for CoreWeave GPU deployments. This includes steps for building Docker containers, validating Kubernetes YAML manifests using dry-run, and managing the full deployment lifecycle for AI inference services before pushing to the cloud.

A comprehensive security auditing framework designed to systematically detect sensitive information disclosure from Large Language Models (LLMs). It uses multi-phase, escalating dialogue probes to test for leaks such as system prompts, API keys, PII, and internal configurations. Essential for red teaming and rigorous model security assessment.

This skill provides comprehensive tools and best practices for interacting with Amazon Aurora DSQL, a PostgreSQL-compatible distributed SQL database. It covers schema management, secure query execution, multi-tenant architecture implementation, and safe data migration using MCP tools and CLI scripts. Ideal for building scalable, distributed applications.

This guide provides comprehensive techniques for optimizing ElevenLabs Text-to-Speech (TTS) performance. Learn how to reduce latency and maximize throughput by strategically selecting models (e.g., Flash vs. v3), implementing streaming endpoints (HTTP or WebSocket), and choosing optimal audio formats. It is essential for real-time conversational AI, IVR systems, and high-volume content generation.

A robust utility for managing API calls to ElevenLabs, handling complex rate limiting, concurrency queuing, and quota monitoring. It implements plan-aware concurrency controls (managing 'too_many_concurrent_requests') and exponential backoff strategies for system overloads ('system_busy'). This is essential for building reliable, high-throughput Text-to-Speech applications.

A robust SSH job scheduler designed for orchestrating large-scale, complex machine learning experiments across multiple GPU nodes. It manages multi-seed sweeps, wave transitions, handles OOM retries, and prevents stale screen issues, ensuring reliable execution of deep learning pipelines.

This setup provides a local development loop for integrating and testing Fathom API functionalities. It utilizes mock meeting and transcript data, making it ideal for building meeting analytics tools, simulating webhook handlers, or iterating on complex transcript processing pipelines without requiring live API calls. It ensures a robust environment for isolated development testing.

A comprehensive tool for updating Feishu cloud documents. It supports seven distinct update modes including appending, full overwrite, targeted range replacement, and multi-instance replacement. The system allows highly precise positioning using content ranges (ellipsis) or chapter titles, ensuring content updates are localized and safe, thus preserving images, comments, and formatting.

A comprehensive guide to the three primary architecture patterns for integrating with Figma: CLI scripts, Webhook services, and dedicated plugins. This resource helps developers select the optimal pattern (REST vs. Plugin API) based on whether the use case requires real-time event handling, local automation, or in-editor component interaction. Ideal for planning robust Figma-connected applications like design token synchronization or linting.