Skill UI

Provides production-ready coding patterns for integrating Deepgram using TypeScript and Python. This guide covers essential best practices, including implementing singleton client management, performing text-to-speech synthesis with Aura, and setting up advanced audio intelligence pipelines (e.g., summarization, topic detection, sentiment analysis). Use this when establishing robust Deepgram integration standards, refactoring existing SDK usage, or migrating to newer SDK versions.

Guides users through a three-stage workflow for collaborative documentation, helping teams gather context, iteratively refine structure, and test readability before sharing specs, proposals, or decision docs.

This workflow guides the complete process of generating legal documents using the Documenso API. It covers creating document shells, uploading PDFs, defining multiple recipient roles (Signer, Approver, Viewer), setting specific signing orders, and strategically placing various interactive fields (Signature, Date, Text) across multiple pages. It is ideal for building complex, multi-party agreement workflows and managing the entire document lifecycle.

Provides a structured approach for creating, editing, and analyzing .docx files with tooling and best practices for tracked changes, comments, formatting, and text extraction, covering JavaScript document generation and Python OOXML editing plus markdown-based redlining.

Analyzes a codebase to surface subdomains (Core, Supporting, Generic) and recommend bounded contexts using DDD strategic design, helping teams clarify domain boundaries, cohesion, and service split decisions.

This skill guides the planning and execution of complex business domains using Domain-Driven Design (DDD) principles. It helps developers move from strategic modeling (defining subdomains and bounded contexts) to tactical implementation patterns like CQRS, Event Sourcing, and Saga orchestration. Use it when dealing with complex, high-variability business rules and needing explicit architectural boundaries.

A sophisticated AI system that coordinates multiple specialized agents (e.g., Security Auditors, Performance Analysts, Architecture Specialists) to perform comprehensive, multi-perspective code assessments. It analyzes code context, manages state, and synthesizes conflicting insights to provide deep, holistic reviews for complex software projects.

Provides comprehensive guidance on building robust evaluation frameworks for complex agent systems. It addresses the inherent challenges of non-determinism and multiple valid paths, enabling systematic performance testing, validating context engineering choices, and measuring continuous improvements across multiple quality dimensions (e.g., factual accuracy, tool efficiency).

Automate Everhour time-tracking tasks through Composio’s toolkit and Rube MCP, always discovering current tool schemas before executing workflows and reusing session context.

This comprehensive workflow manages the entire lifecycle of notes within Evernote. It provides structured methods for creating new notes (supporting plain text, checklists, and ENML formatting), retrieving existing content, updating notes, and organizing both notes and notebooks/stacks. Essential for building full-featured note-taking applications and content management systems.

A comprehensive workflow for executing advanced, semantic web searches using Exa. This tool moves beyond simple keyword matching, enabling deep context retrieval by understanding the intent behind the query. Key features include RAG context retrieval, content extraction (summaries, highlights, full text), and robust filtering by date range, specific domains, and content categories. Ideal for building knowledge base search features and complex research pipelines.

This skill manages and refines search results obtained from Exa's neural search API. It provides comprehensive control over content extraction scope, allowing users to selectively retrieve metadata, highlights, full text, or structured summaries. Key features include implementing result caching with TTL, deduplicating citations, and crucial token budget management, ensuring the retrieved context fits within LLM context window limits for robust RAG pipelines.