Claude Skills 列表

Expert in building voice AI applications - from real-time voice agents to voice-enabled apps. Covers OpenAI Realtime API, Vapi for voice agents, Deepgram for transcription,...

Build real-time conversational AI voice engines using async worker pipelines, streaming transcription, LLM agents, and TTS synthesis with interrupt handling and multi-provider...

Operate and evaluate Unified AI System through fifteen governed MCP tools, including provider-free prompt enhancement, while preserving fake-provider, authorization, and evidence...

Fine-tune and post-train LLMs with Unsloth Core on a single consumer GPU: VRAM sizing, LoRA/QLoRA, GRPO/DPO, chat-template correctness, and GGUF export.

Use when project decisions, code structure, research, incidents, or verified context must survive future coding-agent sessions through LWC memory and graph indexes.

Expert in vector databases, embedding strategies, and semantic search implementation. Masters Pinecone, Weaviate, Qdrant, Milvus, and pgvector for RAG applications, recommendation...

Optimize vector index performance for latency, recall, and memory. Use when tuning HNSW parameters, selecting quantization strategies, or scaling vector search infrastructure.

Expert in the Vercel AI SDK. Covers Core API (generateText, streamText), UI hooks (useChat, useCompletion), tool calling, and streaming UI components with React and Next.js.

Build tools that agents can use effectively, including architectural reduction patterns. Use when creating new tools for agent systems, debugging tool-related failures or misuse,...

Train or fine-tune SentenceTransformer, CrossEncoder, and SparseEncoder models for retrieval, similarity, clustering, classification, reranking, and related embedding tasks.

Use Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript.

Use Tree Ring Memory for local-first AI-agent memory lifecycle work: recall, evidence, audit, forgetting, and consolidation without transcript dumping.

Train and fine-tune transformer language models using TRL (Transformers Reinforcement Learning). Supports SFT, DPO, GRPO, KTO, RLOO and Reward Model training via CLI commands.

Coordinate quota-aware parallel subagents for large, multi-file Antigravity tasks.

Geracao de imagens via Stability AI (SD3.5, Ultra, Core). Text-to-image, img2img, inpainting, upscale, remove-bg, search-replace. 15 estilos artisticos.

Guide for creating effective skills for AI coding agents working with Azure SDKs and Microsoft Foundry services. Use when creating new skills or updating existing skills.

Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.

Seek and analyze video content using Memories.ai Large Visual Memory Model for persistent video intelligence

Machine learning in Python with scikit-learn. Use for classification, regression, clustering, model evaluation, and ML pipelines.

Integrate RouterBase as an OpenAI-compatible model gateway for routing GPT, Claude, Gemini, media, audio, and embedding requests.