Search code and documents by semantic similarity using embeddings.
npx skills add https://github.com/massgen/MassGen --skill semtools-massgen
Please help me install this Agent Skill. Skill: semtools Source: https://github.com/massgen/MassGen/tree/main/massgen/skills/semtools Command: npx skills add https://github.com/massgen/MassGen --skill semtools-massgen
Semtools enables meaning-based search across large codebases and documents by using embedding-based similarity, enabling users to find relevant items even when exact keywords are missing.
Use the semtools skill to perform a basic semantic search on a local codebase.
High-intent search queries and answers about installing and using this skill.
Semantic search locates files and text by meaning using embedding-based similarity, finding relevant code and documents even when exact keywords are missing. It indexes workspaces to enable fast, repeated concept-based searches.
Semantic search works by generating embeddings for code and documents, then comparing embedding similarity to locate conceptually related content. This approach matches meaning rather than exact text strings.
Document parsing converts PDFs, DOCX, and PPTX files to searchable text for semantic search. This feature requires providing an API key to process and extract text from these document formats.
Workspace management indexes large codebases to enable fast repeated semantic searches. By creating a searchable index of your codebase, subsequent queries return results quickly without reprocessing files.
A Rust-based CLI semantic search tool provides commands for search, workspace, and parse operations. Users interact with the tool through command-line instructions to manage and query their indexed documents.
Meaning-based search relies on embeddings, so it requires initial indexing of workspaces and may need API keys for document parsing. It is designed for software engineering workflows and knowledge discovery scenarios.
Snowflake-LabsA concise summary of your roleplay character: name,</name> personality, and/or behavior, formatted as a single string sentence. Typically不超过50字，此处省略
Aktoh-CyberPerform semantic vector search and retrieval with AgentDB for RAG workflows.
ionmidoriBuild RAG systems with vector databases and semantic search.
Mercurium-AnalyticsFuse BM25 lexical relevance with vector semantic similarity in pgsv.hybrid_search.
