67 skills · sorted by relevance
Find relevant passages in an Obsidian vault using a local word-based search index. Optionally reorder results by meaning with a multilingual Nomic model, returning note paths and snippets while leaving the original notes unchanged.
Choose a serving container for models deployed on SageMaker. Match the model type to a compatible image, retrieve its address from the AWS catalog, and check regional availability, CPU or GPU variants, and required host settings.
Adds and tunes a reranker stage for RAG using the retrieve-wide, rerank-narrow pattern. Use when relevant documents appear in the initial top-N but are buried by noise, top-1 precision or MRR is low despite adequate recall, or too many marginal chunks consume context. Covers cross-encoder, API, and local rerankers; N-to-k selection; and latency/cost tradeoffs. Do not use when retrieval recall itself is failing.
The English summary is being prepared. Showing the original description.
Cohere API for enterprise NLP — embeddings, reranking, RAG, and text generation. Use when building RAG pipelines, semantic search, document reranking, or enterprise NLP applications. Command R+ excels at tool use and retrieval-augmented generation; Embed v3 and Rerank 3 are best-in-class for search quality.
The English summary is being prepared. Showing the original description.
Design recommendation and ranking workflows that select the best items for a user or situation. Organize candidate retrieval, enrichment, filtering, scoring, selection, and background recording into six stages, then generate a runnable code scaffold.
Train sentence-transformers models for search, similarity, and reranking, which reorders search results by relevance. Choose a model type, prepare data, configure training, compare results against a baseline, and publish the trained model to Hugging Face Hub.
Design and implement RAG systems, which retrieve documents to inform AI answers. Get document preparation strategies, vector database comparisons, combined keyword and meaning-based search, result reranking, and an evaluation plan for retrieval quality.
Plan how to serve a model on Amazon SageMaker AI. The skill uses model type, traffic, response time, and cost constraints to recommend a deployment route, check instance quotas, and coordinate specialized setup and deployment skills.
Train sentence-transformers models for search, similarity, and reranking, which reorders search results by relevance. Choose a model type, prepare data, configure training, compare results against a baseline, and publish the trained model to Hugging Face Hub.
Build and query a vault-local contextual BM25 retrieval index with optional multilingual Nomic cosine reranking; use for retrieve, hybrid retrieval, BM25, rerank, contextual retrieval, chunk search, vault search, semantic search, find relevant passages, or retrieval diagnostics. Derived caches stay under .vault-meta, remote egress requires explicit consent, and unavailable reranking falls back deterministically.
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.
Design recommendation and ranking systems that select the best items for a user or situation. Organize retrieval, enrichment, filtering, scoring, selection, and background actions into six stages, then generate a runnable scaffold for your chosen stack.
Combine vector search, which finds similar meanings, with keyword search for exact terms. Design retrieval for search engines and RAG systems that supply reference material to AI, using methods to merge and rerank results.
Design hybrid search on AlloyDB by combining meaning-based search, keywords, and SQL filters. Turn requirements into architecture diagrams, database setup scripts, deployment guidance, and validation plans for search applications on Google Cloud.
Use when planning, debugging, tuning, evaluating, exporting, or deploying public Nemotron `embed`/`rerank` retrieval recipes.
The English summary is being prepared. Showing the original description.
Use this skill to implement hybrid search combining BM25 keyword search with semantic vector search using Reciprocal Rank Fusion (RRF). **Trigger when user asks to:** - Combine keyword and semantic search - Implement hybrid search or multi-modal retrieval - Use BM25/pg_textsearch with pgvector together - Implement RRF (Reciprocal Rank Fusion) for search - Build search that handles both exact terms and meaning **Keywords:** hybrid search, BM25, pg_textsearch, RRF, reciprocal rank fusion, keyword search, full-text search, reranking, cross-encoder Covers: pg_textsearch BM25 index setup, parallel query patterns, client-side RRF fusion (Python/TypeScript), weighting strategies, and optional ML reranking.
The English summary is being prepared. Showing the original description.
Cross-encoder reranking and MMR diversity filtering for improved retrieval quality
The English summary is being prepared. Showing the original description.
Work with the @upstash/search TypeScript/JavaScript SDK, a serverless full-text and semantic search database with built-in reranking. Use when adding search to an app or site, creating a search index, upserting documents with searchable content and filterable metadata, running keyword, semantic, or hybrid search queries, reranking results, filtering with SQL-like or structured filter syntax, paginating with range, fetching or deleting documents, resetting an index, or checking index info. Also use when the user asks for site search, product, document, or knowledge-base search, or a managed search service that needs no cluster to run.
The English summary is being prepared. Showing the original description.
Plan and coordinate the deployment of a model to Amazon SageMaker AI. Use this skill whenever the user wants to deploy, host, serve, or expose a model on SageMaker or AWS — including phrases like "deploy a model", "host this LLM on AWS", "serve this embedding model", "deploy a reranker", "deploy a text-to-image / diffusion model", "host this for async inference", "create an endpoint", "serve my fine-tuned model", or any request that involves making a model available for inference on AWS. Use this even when the user is vague (e.g. "I just want to get this running on AWS, you figure it out"). Works for text-generation LLMs, embedding models, rerankers, classifiers, text-to-image / diffusion models — picks the right serving stack and chooses between real-time and async inference. This is the entry-point skill for SageMaker deployment work — it asks clarifying questions, picks a deployment pathway, and coordinates the other deployment skills.
The English summary is being prepared. Showing the original description.
Rust 製ローカルファースト vector 特化クエリ DB fandhe-db (PostgreSQL wire protocol v3 互換) の fandhe-db-engine / fandhe-db-wire-server リファレンス。 USING PLAN / USING OPERATION_ID 構文、DDL / JOIN / CTE / window 関数、 拡張クエリ・COPY・トランザクション、TLS 1.3 / SCRAM-SHA-256、 NoSQL HTTP 表層、precision・recall モード、HNSW / BM25 / RRF hybrid / rerank、 redb 永続化、tenant・RLS、SIMD / wgpu、wire_code エラー契約。
The English summary is being prepared. Showing the original description.
Upstash サーバーレスデータプラットフォーム (マネージド SaaS の JS SDK)。 @upstash/redis (REST, pipelining, transactions, JSON, Redis Search, VECTOR/Array/Functions コマンド)、 @upstash/ratelimit (Fixed/Sliding Window, Token Bucket, blockUntilReady)、 QStash (publishJSON, schedules, queues, URL Groups, flow-control, DLQ)、 @upstash/vector (upsert, query, ANN, namespace, hybrid/sparse index, embedding models, reranking)、 @upstash/workflow (serve, durable execution, context.run/sleep/call/invoke, waitForEvent, parallel steps, agents)、 Upstash Search (@upstash/search, search, upsert, fetch, range, filtering, reranking, algorithm)、 @upstash/box (サンドボックス, filesystem, git, CDP, browser, network policy, snapshots, custom harness)、 upstash CLI。Rust 製 fandhe-db とは別。
The English summary is being prepared. Showing the original description.
Connect AI agents to OmniRoute for text and image generation, speech synthesis, transcription, and web search. Use OpenAI-compatible APIs and create embeddings, numerical representations of text, through documented requests.
Find stored Ruflo memories by meaning, keywords, or an optional ranking method. Search across storage groups, retrieve past solutions and task context, and see which search method actually ran, including any fallback.
Find biological pathways and functions enriched in gene lists or ranked gene data. Choose an appropriate statistical method, align gene identifiers, define comparison backgrounds, and turn results into interpretable tables and plots with multiple-testing corrections.