Skill UI

A comprehensive guide for developers planning Deepgram SDK version upgrades (v3/v4 to v5) and model migrations (Nova-2 to Nova-3). This resource details breaking changes, provides side-by-side API comparisons, and includes automated validation scripts to ensure smooth integration of new features and improved speech recognition capabilities.

A comprehensive guide for selecting and optimizing embedding models for advanced vector search and retrieval-augmented generation (RAG) applications. This guide covers model comparison, chunking strategies, dimension reduction techniques, and provides runnable Python templates for both OpenAI and local Sentence Transformer implementations.

OpenRouter provides a unified API gateway to access leading AI models (OpenAI, Anthropic, Google, Meta, etc.) from a single endpoint. This skill is essential for developers who need to compare model performance (latency, tokens) across different providers, build resilient cross-provider fallback workflows, or manage complex AI pipelines without writing provider-specific code. It supports feature normalization and BYOK (Bring Your Own Key) for high-volume production use.

This skill provides a comprehensive guide to understanding OpenRouter's API billing structure. It teaches users how to accurately calculate costs based on prompt (input) and completion (output) tokens. Users can utilize provided scripts to estimate costs, check credit balances, and implement cost-saving strategies like using `:floor` or `:free` model variants. Ideal for budgeting, performance comparison, and production cost tracking.

A comprehensive guide to building production-grade evaluation systems for Large Language Models (LLMs). This skill covers advanced methodologies, including Direct Scoring and Pairwise Comparison, alongside critical techniques for mitigating systematic biases (e.g., Position Bias, Length Bias). Learn how to select appropriate metrics and structure prompts to ensure reliable, consistent, and objective quality assessment across various AI applications.

This tool analyzes ML experiment results from various paths (JSON/CSV). It computes comprehensive statistics, builds detailed comparison tables based on model types and hyperparameters, and generates actionable insights. Use it when you need to interpret raw experimental data, compare different model runs, or determine the next steps for research.

This skill automatically generates an interactive SQL Notebook designed to validate changes in dbt models or snapshots. It processes changes identified from a GitHub PR or local repository, generating comparison queries that compare 'before' (production) and 'after' (development) data states. It is essential for embedding data observability and quality checks into CI/CD pipelines.

Build, fit, and validate Bayesian models with PyMC 6, covering hierarchical models, MCMC/NUTS sampling, variational inference, prior and posterior predictive checks, diagnostics, and LOO/WAIC model comparison.

A comprehensive guide for developers on upgrading the Anthropic SDK versions and migrating between different Claude model generations. It covers best practices for version checking, reviewing breaking changes, updating model IDs across the codebase, running output comparison tests, and implementing gradual rollouts using environment variables to ensure stable deployment.

A comprehensive framework for conducting deep competitive analysis, providing structured insights for product decision-making and business strategy. It guides the creation of detailed reports, including feature comparison matrices, pricing models, market positioning maps, and win/loss analyses. Ideal for product managers, strategists, and sales teams developing battlecards.

This professional tool helps developers and researchers identify the optimal AI model for a specific task, such as coding, reasoning, or image recognition. It queries official HuggingFace leaderboards, filters models based on hardware constraints (e.g., available VRAM or RAM), and provides a detailed comparison table including benchmark scores, parameter size, and licensing information.

This skill executes the DeepSWE benchmark, a comprehensive coding-agent evaluation suite. It uses OpenRouter and mini-swe-agent to score various Large Language Models (LLMs) on 113 tasks, providing reproducible results for model comparison, development assessment, and research benchmarking. Use this when a standardized, deep evaluation of LLM coding capabilities is required.