Download

Skill UI

Browse and discover 7039+ curated skills

All Development Artificial Intelligence Design & Creative Product & Business Data Science Marketing Soft Skills Productivity Engineering Languages

Search performance , found 28 results

Default Newest Most Downloaded

OpenRLHF Training Suite

openrlhf-training

Orchestra-Research/AI-Research-SKILLs

High-performance RLHF framework that combines Ray, vLLM, and ZeRO-3 to accelerate PPO/GRPO/RLOO/DPO training for 7B-70B+ models on distributed GPU clusters, providing a single-stack workflow for reward models and policy optimization.

OpenRouter Fallback

openrouter-fallback-config

jeremylongshore/claude-code-plugins-plus-skills

Configures model fallback chains for OpenRouter so LLM applications automatically switch to backup models when primary ones fail, ensuring high availability and monitored performance.

OpenRouter Model Routing

openrouter-model-routing

jeremylongshore/claude-code-plugins-plus-skills

Implements advanced OpenRouter model routing with A/B testing, gradual rollouts, and performance-aware selection to optimize multi-model deployments and experiments across environments.

Perplexity Performance Tuning

perplexity-performance-tuning

jeremylongshore/claude-code-plugins-plus-skills

Optimize Perplexity Sonar API calls by selecting appropriate models, caching query hashes, streaming long research, and batching deduplicated requests for faster, cost-effective research or fact-checking workflows.

Prompt Engineering Patterns

prompt-engineering-patterns

sickn33/antigravity-awesome-skills

Guides engineers through advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability across few-shot learning, reasoning patterns, templates, and system prompt design.

High-Performance Vector Similarity Search Engine

qdrant-vector-search

Orchestra-Research/AI-Research-SKILLs

Qdrant is a high-performance, Rust-powered vector database designed for production-grade RAG (Retrieval-Augmented Generation) and semantic search applications. It provides fast nearest neighbor search, supports complex hybrid search using metadata filtering, and offers horizontal scalability through sharding and replication. Ideal for building real-time recommendation systems and enterprise-level knowledge retrieval.

Retell AI Performance Tuning

retellai-performance-tuning

jeremylongshore/claude-code-plugins-plus-skills

Guide for optimizing Retell AI voice agents by tuning LLM prompts, agent settings, WebSocket pooling, and caching/analytics so API integrations stay responsive under load.

SGLang Structured Inference Service

Orchestra-Research/AI-Research-SKILLs

SGLang is a high-performance serving framework for LLMs and VLMs that uses RadixAttention prefix caching to deliver structured outputs (JSON/regex/grammar) and agentic workflows with function calls, providing up to 5× faster inference than vLLM across multi-GPU production deployments.

Implementing Similarity Search Patterns

similarity-search-patterns

sickn33/antigravity-awesome-skills

This skill provides comprehensive patterns and best practices for implementing efficient similarity search mechanisms using vector databases. It is essential for building advanced AI systems such as semantic search engines, implementing Retrieval-Augmented Generation (RAG), and developing recommendation systems. Use this when optimizing retrieval performance or scaling to massive volumes of vectors.

TensorBoard Visualization Toolkit

Orchestra-Research/AI-Research-SKILLs

TensorBoard delivers a unified interface to track training metrics, debug network behavior, compare experiments, inspect model graphs, and profile performance for PyTorch or TensorFlow workflows.

Model Version Tracker

tracking-model-versions

jeremylongshore/claude-code-plugins-plus-skills

Enables Claude to manage AI/ML model versions through the model-versioning-tracker plugin, automating logging, lineage tracking, performance summaries, and version retrieval whenever users request registry or deployment support.

Hyperparameter Optimization Assistant

tuning-hyperparameters

jeremylongshore/claude-code-plugins-plus-skills

Guides Claude to automatically tune machine learning model hyperparameters via grid, random, or Bayesian search, generating runnable Python code, executing validations, and reporting best configurations plus performance metrics for accuracy or other goals.

Language