Loading...
Loading...
Found 14 Skills
Search personal markdown knowledge bases, notes, meeting transcripts, and documentation using QMD - a local hybrid search engine. Combines BM25 keyword search, vector semantic search, and LLM re-ranking. Use when users ask to search notes, find documents, look up information in their knowledge base, retrieve meeting notes, or search documentation. Triggers on "search markdown files", "search my notes", "find in docs", "look up", "what did I write about", "meeting notes about".
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.
Implement BM25 ranking function for e-commerce product search relevance scoring. Use this skill when the user needs to build a text-based product search engine, improve search result relevance, or replace basic TF-IDF with a more robust ranking function — even if they say 'product search ranking', 'search relevance', or 'BM25 implementation'.
Implement hybrid search combining dense vectors and sparse retrieval for optimal RAG results. Use this skill when vector search alone isn't providing accurate results. Activate when: hybrid search, BM25, keyword search, sparse retrieval, dense retrieval, reranking, ensemble retrieval.
Production hybrid search combining PGVector HNSW with BM25 using Reciprocal Rank Fusion. Use when implementing hybrid search, semantic + keyword retrieval, vector search optimization, metadata filtering, or choosing between HNSW and IVFFlat indexes.
Senior-level UI/UX design skill with data-driven architecture for building premium, production-grade interfaces. Includes: BM25 search engine over 1,875+ data rows across 27 CSV databases, 8 Python scripts (search, contrast checker, palette/token/typography generators, design system generator, UI auditor), 16 tech stack guides, 11 reference documents, and 331 lines of intent-first design methodology. Covers: design token architecture, oklch color systems, typography hierarchies, spacing grids, depth strategies, component patterns, animation timing, WCAG 2.2 accessibility, cognitive science principles, and industry-specific reasoning for 30+ industries.
PostgreSQL-based semantic and hybrid search with pgvector and ParadeDB. Use when implementing vector search, semantic search, hybrid search, or full-text search in PostgreSQL. Covers pgvector setup, indexing (HNSW, IVFFlat), hybrid search (FTS + BM25 + RRF), ParadeDB as Elasticsearch alternative, and re-ranking with Cohere/cross-encoders. Supports vector(1536) and halfvec(3072) types for OpenAI embeddings. Triggers: pgvector, vector search, semantic search, hybrid search, embedding search, PostgreSQL RAG, BM25, RRF, HNSW index, similarity search, ParadeDB, pg_search, reranking, Cohere rerank, pg_trgm, trigram, fuzzy search, LIKE, ILIKE, autocomplete, typo tolerance, fuzzystrmatch
Anthropic's Contextual Retrieval technique for improved RAG. Use when chunks lose context during retrieval, implementing hybrid BM25+vector search, or reducing retrieval failures.
Build search applications and query log analytics data with OpenSearch. Use this skill when the user mentions OpenSearch, search app, index setup, search architecture, semantic search, vector search, hybrid search, BM25, dense vector, sparse vector, agentic search, RAG, embeddings, KNN, PDF ingestion, document processing, or any related search topic. Also use for log analytics and observability — when the user wants to set up log ingestion, query logs with PPL, analyze error patterns, set up index lifecycle policies, investigate traces, or check stack health. Activate even if the user says log analysis, Fluent Bit, Fluentd, Logstash, syslog, traceId, OpenTelemetry, or log analytics without mentioning OpenSearch.
Full-stack hybrid memory system with vector + keyword search. Stores embeddings in SQLite with FTS5 for BM25 keyword search and cosine similarity. Enables semantic memory recall for agents.
Build search applications and query log analytics data with OpenSearch. Use this skill when the user mentions OpenSearch, search app, index setup, search architecture, semantic search, vector search, hybrid search, BM25, dense vector, sparse vector, agentic search, RAG, embeddings, KNN, PDF ingestion, document processing, or any related search topic. Also use for log analytics and observability — when the user wants to set up log ingestion, query logs with PPL, analyze error patterns, set up index lifecycle policies, investigate traces, or check stack health. Activate even if the user says log analysis, Fluent Bit, Fluentd, Logstash, syslog, traceId, OpenTelemetry, or log analytics without mentioning OpenSearch.
KWCode (天工开物) — a CLI coding agent optimized for local open-source models (8B-30B), featuring deterministic expert pipelines, BM25+AST code location, runtime debugging, and a self-improving flywheel — all running fully offline.