Skill UI

This skill provides comprehensive observability for ClickUp API integrations. It instruments API calls to capture key metrics like request rate, latency percentiles, error counts, and rate limit usage. It integrates with Prometheus for metrics, OpenTelemetry for distributed tracing, and structured logging for detailed event tracking. Use it to build robust dashboards and set up critical alerts for API performance issues.

A comprehensive guide to securing ClickUp API usage. Learn best practices for managing API tokens, implementing least-privilege access, and auditing usage patterns. This includes secure token rotation procedures, using environment variables, setting up pre-commit hooks to prevent leaks, and structuring calls for robust audit logging.

This skill provides a comprehensive framework for conducting high-quality code reviews. It guides developers through checking code across four critical dimensions: Correctness (functional accuracy and edge cases), Maintainability (readability and documentation), Performance (efficiency and resource usage), and Security (input validation and vulnerability management). It also emphasizes providing actionable, constructive, and empathetic feedback.

Provides strategies to optimize costs when utilizing the Cohere API. This guide covers model tier selection (economy, standard, premium), implementing token budgets, reducing embedding storage costs (e.g., using int8), and establishing comprehensive usage trackers. It is essential for maintaining cost predictability in production AI deployments.

This comprehensive guide details the process of installing and configuring the Cohere SDK (v2) in both Node.js and Python environments. It covers initial setup, setting API keys via environment variables, and provides full code examples for verifying connectivity across various Cohere endpoints, including Chat, Embed, and Rerank, enabling immediate integration into your AI projects.

A comprehensive solution for setting up production-grade observability for Cohere API v2. It integrates Prometheus metrics, OpenTelemetry tracing, and robust alerting mechanisms. This skill tracks critical operational data including per-endpoint latency, token consumption (input/output), error rates, and usage costs, ensuring reliable monitoring for AI-powered applications.

This skill provides comprehensive observability for CoreWeave's GPU-intensive workloads running on Kubernetes. It monitors critical operational metrics, including GPU utilization, memory usage, inference latency (p99), and job completion rates. Use it for setting up DCGM metrics dashboards, configuring proactive alerts for underutilization or Out-Of-Memory (OOM) conditions, and ensuring high reliability for AI/ML deployments.

This skill provides methods to optimize ElevenLabs usage costs for Text-to-Speech (TTS) workloads. It covers model selection (e.g., using Flash/Turbo for savings), implementing character-efficient text pre-processing to reduce character count, and setting up real-time quota monitoring with budget alerts. Ideal for developers managing high-volume, cost-sensitive voice applications.

This bundle collects comprehensive diagnostic evidence for ElevenLabs services. It automatically gathers SDK versions, API connectivity status, quota usage, voice inventories, and available model metadata. Use this tool when encountering persistent bugs or preparing comprehensive support tickets for technical support.

This guide provides best practices for optimizing Fathom API usage and managing associated cloud costs. It covers strategies like implementing caching for transcripts, switching from API polling to webhooks, batching CRM writes, and establishing data retention policies (e.g., archiving after 90 days) to minimize unnecessary spending on storage and API calls.

This skill provides comprehensive guidance on optimizing complex integrations with the Figma API to minimize operational costs and prevent hitting rate limits. It covers architectural best practices, such as transitioning from inefficient polling to webhook-driven systems, batching multiple requests, and using parameters like `depth=1`. Essential for building scalable, cost-effective SaaS solutions.

This guide provides strategies for optimizing Finta's operational costs during fundraising. It focuses on reducing API call volume, managing seat licenses, and streamlining data synchronization. Learn techniques such as implementing incremental syncing, archiving completed deal rooms, and batching updates to ensure you only pay for active usage.