Skill UI

This comprehensive checklist guides the secure and robust deployment of AssemblyAI transcription services to a live production environment. It covers critical pre-deployment checks, health monitoring implementations, webhook-based processing setup, and gradual rollout strategies, ensuring high availability and reliability for mission-critical speech-to-text functions.

This skill provides comprehensive solutions for managing rate limits and throttling when interacting with the AssemblyAI Speech-to-Text API. It implements advanced patterns like exponential backoff with jitter, queue-based concurrency control, and resilient streaming retry logic. Use it when building high-throughput, reliable applications that process large volumes of audio data.

This guide provides production-ready architectural patterns for integrating the AssemblyAI SDK in TypeScript and Python. It details best practices including implementing Singleton clients, robust service wrappers, advanced error handling (like exponential backoff retries), and multi-tenant client management. Use this when building highly scalable and reliable speech-to-text applications.

Provides techniques and indicators for researching music bands from non-Western cultures (e.g., African, Asian, Middle Eastern). This guide helps users move beyond mainstream Western databases, offering search strategies for bands whose information is often found on regional sites or through unique contextual clues like recording conditions or historical milestones.

This skill converts dense text, articles, or complex notes into clean, highly structured, and hierarchical bullet points. It is ideal for summarization, academic studying, or creating organized notes where strict readability and clear parent-child relationships are required. It eliminates prose and paragraphs, enforcing a pure bullet format for maximum structural clarity and memorization.

This comprehensive workflow manages the entire Canva creative pipeline. Users can upload, read, and modify design assets (images, files) via API. Key features include autofilling brand templates using dynamic data (text, images, charts) and programmatically organizing generated designs into specific folders, significantly streamlining the content creation process.

A comprehensive guide covering Chinese technical documentation formatting rules. It addresses common issues like mixing full/half-width punctuation, spacing conventions (e.g., space between English/Chinese text, numbers/units), and best practices for handling technical terminology translation and structure.

Zero-context verification that every bibliographic entry in a paper is real, correctly attributed, and used in a context the cited paper actually supports. Catches hallucinated authors, wrong years, fabricated venues, title drift, phantom DOIs, and wrong-context citations. Run before submission after the LaTeX draft and bib file are finalized.

A comprehensive guide for building applications with Claude, ensuring responsible data handling. This skill covers critical patterns such as PII redaction (stripping sensitive data like emails, phone numbers, and card numbers), optimizing the 200K token context window through conversation trimming, and implementing best practices for data retention and privacy compliance when interacting with the Anthropic API.

A persistent memory kit designed for Claude AI agents. It maintains deep context across multiple sessions and projects using a two-layer architecture (hot cache and knowledge wiki). Features include safety hooks, multi-project context isolation, and a /close-day command for daily synthesis, ensuring agents remember complex information and continuously learn.

This comprehensive workflow guides the implementation of a complete Retrieval-Augmented Generation (RAG) pipeline using Cohere's core services. It demonstrates the full process: embedding documents, searching for relevant context, reranking results for precision, and finally generating a grounded answer with precise citations using the Chat API. Ideal for building knowledge-intensive, enterprise-grade Q&A systems.

This advanced engine creates deeply personalized, relationship-aware daily gifts using a sophisticated five-stage creative pipeline. It first performs an 'Editorial Judgment' to determine if a gift is warranted, and then generates the content concept. Output can be rendered as interactive H5 web pages, AI-generated images, or videos, ensuring that every artifact is highly unique, contextually relevant, and avoids repetition. Ideal for automated journaling, marking milestones, or maintaining thoughtful daily engagement.