Search documents, code, and PDFs semantically using embeddings.
npx skills add https://github.com/ryantking/agentctl --skill semtools-ryantking
Please help me install this Agent Skill. Skill: semtools Source: https://github.com/ryantking/agentctl/tree/main/internal/templates/templates/skills/semtools Command: npx skills add https://github.com/ryantking/agentctl --skill semtools-ryantking
Semtools enables fast semantic search and document parsing to help teams surface conceptually related information across large doc sets, codebases, and configuration files.
Use semtools to search for "authentication patterns" in docs/ and to parse a set of PDFs for semantic indexing.
High-intent search queries and answers about installing and using this skill.
Semantic search across large codebases and PDFs uses embeddings-based search to surface conceptually related content when exact keywords fail. It parses unsupported document formats into Markdown and indexes them within a workspace cache for fast retrieval.
Parsing PDFs for semantic indexing involves converting unsupported formats into searchable Markdown, then using embeddings to locate conceptually related information across the workspace cache.
Yes, semantic search can explore YAML manifests and documentation by applying embeddings to surface conceptually related content, enabling faster code understanding and documentation exploration at scale.
Semantic search works with LLM embeddings for code repository exploration by indexing parsed documents and configurations, allowing teams to quickly discover related concepts when exact keyword matching is insufficient.
Managing parsing and indexing for large document sets relies on a workspace cache to store parsed Markdown from unsupported formats, streamlining the embeddings-based search process across extensive codebases and documentation.
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
jmagarSearch documents and web sources semantically using Exa MCP tools.
wesichainBuild RAG pipelines for document Q&A and semantic search.
BEKO2210Search knowledge bases semantically with vector embeddings and keyword fallback.
