Total 50,676 skills, AI & Machine Learning has 8495 skills
Showing 12 of 8495 skills
Search and analyze X/Twitter posts using xAI's Grok API with real-time social media data. Use when the user needs to (1) search X/Twitter for specific topics, keywords, or trends, (2) analyze sentiment or discussions on X, (3) find posts from specific users or time periods, (4) research what people are saying about companies/products/events on X, or (5) gather social media insights from Twitter/X platform.
Build and run evaluators for AI/LLM applications using Phoenix.
Build autonomous AI agents with Claude Agent SDK. Structured outputs guarantee JSON schema validation, with plugins system and hooks for event-driven workflows. Prevents 14 documented errors. Use when: building coding agents, SRE systems, security auditors, or troubleshooting CLI not found, structured output validation, session forking errors, MCP config issues, subagent cleanup.
Build RAG systems and semantic search with Gemini embeddings (gemini-embedding-001). 768-3072 dimension vectors, 8 task types, Cloudflare Vectorize integration. Prevents 13 documented errors. Use when: vector search, RAG systems, semantic search, document clustering. Troubleshoot: dimension mismatch, normalization required, batch ordering bug, memory limits, wrong task type, rate limits (100 RPM).
Development skill from everything-claude-code
Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabling faster inference on hardware accelerators. Covers unstructured pruning, structured pruning, N:M sparsity, magnitude pruning, and one-shot methods.
Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing, expert parallelism, and inference optimization.
Help users build software using AI coding tools. Use when someone is using AI to generate code, building prototypes without deep technical skills, or exploring how non-engineers can create functional software through natural language.
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.
Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML visualization toolkit
Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file implementations, no abstraction layers.
GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.