236 skills · sorted by relevance
Especialista em construção de sistemas de Retrieval-Augmented Generation. Domina modelos de embedding, bancos de dados vetoriais, estratégias de chunking e otimização de recuperação para aplicações LLM. Use quando: construir RAG, busca vetorial, embeddings, busca semântica, recuperação de documentos.
The English summary is being prepared. Showing the original description.
The Ollama REST API as it is on this machine - /api/generate and /api/chat with streaming NDJSON, /api/embed vs the older /api/embeddings, /api/tags, /api/ps, /api/show, pull progress, create/copy/delete, the OpenAI-compatible /v1 endpoints, the options map, keep_alive, the error shapes, and the environment variables that change what the daemon does.
The English summary is being prepared. Showing the original description.
The `ollama` Python package used properly - chat and generate with streaming, embeddings, tool calling, structured outputs with a JSON Schema, the async client, keep_alive, timeouts and cancellation - and a project shape whose benchmark arithmetic is unit-tested against a fake transport while the live half skips loudly when no daemon answers.
The English summary is being prepared. Showing the original description.
Semantic search over project source files using vector embeddings. Use to find files related to a feature, bug, or concept.
The English summary is being prepared. Showing the original description.
Ask the second brain in plain words: semantic search over the curated vault with embeddings plus a reranker, returning the smallest relevant slice instead of a corpus dump. Token-cheap. Triggers: "/ask <question>", "what do I have on <topic>", "what did I write about X".
The English summary is being prepared. Showing the original description.
Spectral vector search using graph Laplacian eigenstructure. Use when cosine/L2 similarity misses latent structure in your embeddings.
The English summary is being prepared. Showing the original description.
Azure OpenAI SDK for .NET. Client library for Azure OpenAI and OpenAI services. Use for chat completions, embeddings, image generation, audio transcription, and assistants.
The English summary is being prepared. Showing the original description.
Write Estuary derivations in Python — async-generator transforms, Pydantic-typed source/output, optional persistent state, and dependency installation via uv. Use for ML/embeddings, async API calls, or any transform where SQL and TypeScript are awkward. Derivations add complexity and cost (and Python derivations require a private/BYOC data plane) — confirm the user wants a Python derivation before reaching for this. Use when user says "python derivation", "write a derivation in python", "embed with a python derivation", "ML derivation", "call an API from a derivation", or anything mentioning model2vec / huggingface / pydantic in a derivation context.
The English summary is being prepared. Showing the original description.
Azure OpenAI SDK for .NET. Client library for Azure OpenAI and OpenAI services. Use for chat completions, embeddings, image generation, audio transcription, and assistants.
The English summary is being prepared. Showing the original description.
Use when working with Cohere — cohere AI platform management covering models, embeddings, reranking, datasets, fine-tuning, and connectors. Use when monitoring API usage, analyzing model performance, reviewing fine-tuning jobs, managing datasets and connectors, or troubleshooting Cohere API issues.
The English summary is being prepared. Showing the original description.
Annotated matrices for single-cell genomics. Stores X with obs/var metadata, layers, embeddings (obsm/varm), graphs (obsp/varp), uns. Use for .h5ad/.zarr I/O, concatenation, scverse integration. For analysis use scanpy; for probabilistic models use scvi-tools.
The English summary is being prepared. Showing the original description.
Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder, dense or static embedding model for retrieval, similarity, clustering, classification, paraphrase mining, dedup, multimodal), `CrossEncoder` (reranker, pair scoring for two-stage retrieval / pair classification), `SparseEncoder` (SPLADE, sparse embedding model for learned-sparse retrieval), and `MultiVectorEncoder` (ColBERT / late-interaction, per-token embeddings scored with MaxSim). Covers loss selection, hard-negative mining, evaluators, distillation, LoRA, Matryoshka, and Hugging Face Hub publishing. Use for any sentence-transformers training task.
The English summary is being prepared. Showing the original description.
Guides MongoDB users through implementing and optimizing Atlas Search (full-text), Vector Search (semantic), and Hybrid Search solutions. Use this skill when users need to build search functionality for text-based queries (autocomplete, fuzzy matching, faceted search), semantic similarity (embeddings, RAG applications), or combined approaches. Also use when users need text containment, substring matching ('contains', 'includes', 'appears in'), case-insensitive or multi-field text search, or filtering across many fields with variable combinations. Provides workflows for selecting the right search type, creating indexes, constructing queries, and optimizing performance using the MongoDB MCP server.
The English summary is being prepared. Showing the original description.
Pick the right serving container for a SageMaker model deployment and find its current image URI. Use this skill whenever about to deploy a model to a SageMaker endpoint and an image URI needs to be chosen — including when the user says "deploy this LLM", "host this HuggingFace model", "serve this fine-tuned model", "deploy this embedding model", "host a reranker", "serve a sentence-transformers model", or when about to hardcode any container URI in deployment code. HuggingFace-curated Deep Learning Containers are ALWAYS preferred: HuggingFace vLLM (LLMs and generative rerankers), HuggingFace vLLM-Omni (multimodal), TEI (embeddings/cross-encoder rerankers), HF Inference Toolkit (other transformers). Generic images (AWS vLLM, DJL-LMI, SGLang) are used only when no HuggingFace image is compatible — never merely because they carry a newer version. Never hardcode a container URI from memory and never default to TGI. Prevents stale-image failures and wrong-region URIs.
The English summary is being prepared. Showing the original description.
Tokenize, tag, and analyze natural language text using Apple's NaturalLanguage framework and translate between languages with the Translation framework. Use when adding language identification, sentiment analysis, named entity recognition, part-of-speech tagging, text embeddings, or in-app translation to iOS/macOS/visionOS apps.
The English summary is being prepared. Showing the original description.
Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications. Use when: building RAG, vector search, embeddings, semantic search, document retrieval.
The English summary is being prepared. Showing the original description.
Azure OpenAI SDK for .NET. Client library for Azure OpenAI and OpenAI services. Use for chat completions, embeddings, image generation, audio transcription, and assistants.
The English summary is being prepared. Showing the original description.
Vercel AI SDK expert guidance. Use when building AI-powered features — chat interfaces, text generation, structured output, tool calling, agents, MCP integration, streaming, embeddings, reranking, image generation, or working with any LLM provider.
The English summary is being prepared. Showing the original description.
How to query the document_embeddings table for raw signal data using HogQL. Use when you need to perform semantic search over signals, fetch every signal that contributed to a specific report, or list signal types. For browsing the curated report layer (the Inbox) — listing reports, filtering by status/source, drilling into a single report by ID — use the `inbox-exploration` skill first; drop into this skill afterwards if the user wants the underlying observations.
The English summary is being prepared. Showing the original description.
Debug the signals pipeline locally end-to-end. Covers emitting test signals from fixtures, monitoring Temporal workflows via the REST API, reading sandbox agent logs from object storage, inspecting Docker sandbox containers, and diagnosing common failures (stale ClickHouse embeddings, agentsh network denials, inactivity timeouts). Use when a signal isn't reaching the inbox, a signal-report-summary workflow fails, or a sandbox task run times out.
The English summary is being prepared. Showing the original description.
This skill should be used when working with genomic interval data (BED files) for machine learning tasks. Use for training region embeddings (Region2Vec, BEDspace), single-cell ATAC-seq analysis (scEmbed), building consensus peaks (universes), or any ML-based analysis of genomic regions. Applies to BED file collections, scATAC-seq data, chromatin accessibility datasets, and region-based genomic feature learning.
The English summary is being prepared. Showing the original description.
High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.
The English summary is being prepared. Showing the original description.
Supabase (オープンソース Firebase 代替・BaaS) リファレンス。 PostgreSQL ベース、Auth (Email / OAuth / Magic Link / Phone / SSO)、Storage、 Edge Functions (Deno)、Realtime (subscriptions / presence / broadcast)、Vector embeddings、 supabase-js、@supabase/server (withSupabase)、supabase CLI (supabase stack)、 Supabase MCP サーバー、RLS (Row Level Security)、migrations。 SQL Server / node-mssql は別スキル mssql。
The English summary is being prepared. Showing the original description.
OpenAI API (developers.openai.com) の Responses API リファレンス。 text generation, embeddings, gpt-6-astra / gpt-6.1-sol / gpt-6-luna, structured outputs, streaming, function calling, programmatic / async tool calling, conversation state, prompt caching, prompt cache diagnostics, reasoning (configuration_update), background mode, compaction, multi-agent, WebSocket mode (mid-turn steering, stream_id), webhooks, error codes, rate limits, Realtime server controls, 公式 SDK (Python / JS / .NET / Java / Go / Ruby), openai CLI, Chat Completions / Assistants 移行, deprecations。
The English summary is being prepared. Showing the original description.