Skill UI

Automates adapting pretrained models via transfer learning by analyzing requirements, generating PyTorch or TensorFlow fine-tuning code, validating data, tracking KPIs, and saving artifacts so you can quickly reuse existing models for new datasets and tasks.

This tool provides comprehensive cost management for Apollo.io API usage. It optimizes credit expenditure by implementing a daily budget tracker, preventing double-enrichment through deduplication, and using a lead scoring mechanism to ensure credits are only spent on high-potential leads. Ideal for large-scale data enrichment tasks to minimize API costs.

An advanced guide for optimizing API interaction with Apollo.io. This skill covers critical performance enhancements including implementing connection pooling, setting per-endpoint time-to-live (TTL) caching, utilizing bulk enrichment endpoints for efficiency, and controlling concurrency during parallel searches. It also demonstrates how to slim down large API response payloads to reduce memory and bandwidth usage.

This comprehensive skill guides the systematic optimization of end-to-end application performance across the entire stack. It covers establishing performance baselines through deep profiling (CPU, Memory, I/O), assessing observability gaps, optimizing databases, tuning backend services and APIs, and enhancing frontend rendering. Ideal for complex, scalable applications that require measurable performance improvements, reliability enhancements, and adherence to modern user experience standards.

This comprehensive skill guides the systematic optimization of end-to-end application performance across the entire stack. It covers establishing performance baselines through deep profiling (CPU, Memory, I/O), assessing observability gaps, optimizing databases, tuning backend services and APIs, and enhancing frontend rendering. Ideal for complex, scalable applications that require measurable performance improvements, reliability enhancements, and adherence to modern user experience standards.

Expert guidance for fine-tuning LLMs with Axolotl, covering YAML configs, LoRA/QLoRA/DPO variants, multimodal support, and practical troubleshooting patterns for development and training workflows.

Expert guidance for fine-tuning LLMs with Axolotl, covering YAML configs, LoRA/QLoRA/DPO variants, multimodal support, and practical troubleshooting patterns for development and training workflows.

Bridges frozen vision encoders and LLMs for high-quality image captioning, VQA, retrieval, and multimodal chat, enabling zero-shot reasoning without fine-tuning and offering efficient Q-Former training.

Automates building and evaluating classification models by analyzing datasets, selecting features, tuning hyperparameters, and reporting metrics via the classification-model-builder plugin for supervised learning requests.

Enables Claude to configure neural network architectures through the neural-network-builder plugin, creating or modifying models and defining layers, activation functions, and training parameters whenever network design or tuning is requested.

This guide details advanced strategies for optimizing and reducing data enrichment spending on platforms like Clay. Techniques include connecting private API keys (for significant savings), optimizing multi-step data pipelines (waterfalls), pre-filtering raw input data to prevent wasted credits, and implementing comprehensive budget monitoring. Ideal for professionals managing high-volume, cost-sensitive data pipelines.

A comprehensive guide to optimizing data enrichment workflows within Clay. Learn techniques to improve throughput, reduce API costs, and maximize data hit rates by correctly ordering enrichment columns, implementing conditional run rules, pre-cleaning raw leads, and managing auto-update settings. Use this when processing large datasets slowly or encountering high costs.