Skill UI

Instructor lets you shape LLM responses into validated Pydantic models, automatically retrying failed extractions, parsing complex JSON with type safety, and streaming partial outputs across Anthropic, OpenAI, and other providers.

A comprehensive checklist designed for ensuring that Kling AI video generation integrations are robust, secure, and reliable before going live or during a deployment review. It covers critical areas including authentication protocols, detailed error handling (retry logic, timeouts), cost control mechanisms, content safety policies, and necessary monitoring setup for a stable production environment.

This resource provides production-ready, structured patterns for building robust voice agent applications using the Retell AI SDK. It covers best practices such as implementing singleton client management, defining typed agent configurations with integrated LLMs, adding automatic retry logic for call failures, and managing large-scale outbound campaigns. Use this when building stable, scalable, and reliable voice automation systems.

SSH job queue for multi-seed/multi-config ML experiments with OOM-aware retry, stale-screen cleanup, and wave-transition race prevention. Use for batch experiments, grid runs, multi-seed sweeps, or auto-chain experiments when /run-experiment cannot handle 10+ jobs that need orchestration.

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 code patterns for integrating with the Cohere AI API v2 using TypeScript and Python. It covers essential best practices, including singleton client management, robust retry mechanisms, type-safe chat wrappers, streaming, embedding, reranking, and structured JSON output. Use this when establishing team coding standards or refactoring existing Cohere integrations.

A comprehensive guide to implementing production-ready patterns for interacting with the Together AI API. This includes a singleton client for seamless OpenAI-compatible integration, robust error wrappers with retry logic, and a fluent request builder. It covers best practices for LLM inference, model setup, and handling diverse response types (chat, embedding, fine-tuning).

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.

A PreToolUse hook that forces Claude to investigate before editing files. It denies the first edit, demands concrete facts like importers and data schemas, then allows retry—raising design depth by an average of 2.25 points in A/B tests.

Design or review an AI agent tool registry or MCP router: document parameter schemas, caller authorization, runtime limits, effect-aware retry contracts and verification evidence before connecting tools to an agent runtime.