Loading...
Loading...
Found 1,335 Skills
State-of-the-art Machine Learning for PyTorch, TensorFlow, and JAX. Provides thousands of pretrained models to perform tasks on different modalities such as text, vision, and audio. The industry standard for Large Language Models (LLMs) and foundation models in science.
List all Langfuse models with their pricing. Use when checking model costs, verifying pricing configuration, or getting an overview of model definitions.
HyDE (Hypothetical Document Embeddings) for improved semantic retrieval. Use when queries don't match document vocabulary, retrieval quality is poor, or implementing advanced RAG patterns.
MCP (Model Context Protocol) 服务器构建指南
Provides guidance for writing and benchmarking optimized CUDA kernels for NVIDIA GPUs (H100, A100, T4) targeting HuggingFace diffusers and transformers libraries. Supports models like LTX-Video, Stable Diffusion, LLaMA, Mistral, and Qwen. Includes integration with HuggingFace Kernels Hub (get_kernel) for loading pre-compiled kernels. Includes benchmarking scripts to compare kernel performance against baseline implementations.
Build Retrieval-Augmented Generation (RAG) Q&A systems with Claude or OpenAI. Use for creating AI assistants that answer questions from document collections, technical libraries, or knowledge bases.
Instruments Python and TypeScript code with MLflow Tracing for observability. Triggers on questions about adding tracing, instrumenting agents/LLM apps, getting started with MLflow tracing, or tracing specific frameworks (LangGraph, LangChain, OpenAI, DSPy, CrewAI, AutoGen). Examples - "How do I add tracing?", "How to instrument my agent?", "How to trace my LangChain app?", "Getting started with MLflow tracing", "Trace my TypeScript app"
Adapter boundary rules for plugin integrations. Trigger: Changes in plugin scripts/hooks for Claude, OpenCode, Gemini, or Codex.
Complete guide for building MCP servers with FastMCP 3.0 - tools, resources, authentication, providers, middleware, and deployment. Use when creating Python MCP servers or integrating AI models with external tools and data.
Build, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. Also handles migrating existing Claude API code between Claude model versions (4.5 → 4.6, 4.6 → 4.7, retired-model replacements). TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`; user asks for the Claude API, Anthropic SDK, or Managed Agents; user adds/modifies/tunes a Claude feature (caching, thinking, compaction, tool use, batch, files, citations, memory) or model (Opus/Sonnet/Haiku) in a file; questions about prompt caching / cache hit rate in an Anthropic SDK project. SKIP: file imports `openai`/other-provider SDK, filename like `*-openai.py`/`*-generic.py`, provider-neutral code, general programming/ML.
Technical Document Knowledge Base (LLM Wiki) for Alibaba Cloud Tongyi Qianfan Platform. Activated when users inquire about Qianfan-related issues such as model lists, API parameters, error codes, application development (Agent/RAG/Knowledge Base/Memory/Plugins), model comparison and pricing, SDK/OpenAI compatible interfaces, multimodal capabilities (speech/image/video), Token billing, etc. It includes structured model market data in models (including contextWindow/QPM/pricing/sample code), wiki synthesis layer (topic pages/concept pages/comparison pages), and raw original document layer; for model specification issues, check models/index.md first, and for document-related issues, check wiki/index.md first.
Integrate Gemini API with @google/genai SDK (NOT deprecated @google/generative-ai). Text generation, multimodal (images/video/audio/PDFs), function calling, thinking mode, streaming. 1M input tokens. Prevents 14 documented errors. Use when: Gemini integration, multimodal AI, reasoning with thinking mode. Troubleshoot: SDK deprecation, model not found, context window, function calling errors, streaming corruption, safety settings, rate limits.