Search GTM knowledge bases using semantic, keyword, and hybrid queries.
npx skills add https://github.com/hathbanger/fridas-choppers-gtm --skill search-hathbanger
Please help me install this Agent Skill. Skill: search Source: https://github.com/hathbanger/fridas-choppers-gtm/tree/main/.claude/skills/search Command: npx skills add https://github.com/hathbanger/fridas-choppers-gtm --skill search-hathbanger
This skill enables semantic search across a GTM knowledge base to locate decisions and context by meaning rather than keywords.
Run a search command against your GTM workspace, for example: /search "what did we decide about pricing"
High-intent search queries and answers about installing and using this skill.
Semantic search across a GTM knowledge base locates decisions and context by meaning rather than keywords. It uses local hybrid search combining BM25 keywords, vector embeddings, and LLM reranking to retrieve relevant information.
Running a semantic search query like "what did we decide about pricing" locates decision rationale across multiple documents and teams. It enables knowledge exploration and decision tracking across vision, narrative, and content within the workspace.
Yes, semantic search requires a local search engine (qmd) and a GTM workspace index. The setup includes instructions for collection management and optional embeddings to enable local hybrid search.
Hybrid search combines BM25 keywords, vector embeddings, and LLM reranking to retrieve information. This contextual search approach improves workspace discovery by matching meaning rather than relying solely on exact keywords.
Yes, contextual search supports decision tracking across vision, narrative, and content. By applying semantic queries to the GTM workspace index, you can locate specific decisions and explore the knowledge base by meaning.
onebrain-aiConfigure qmd search indexes and manage embeddings for vault searching.
farzanmrzRetrieve SERP results and intent-ranked discovery results for keyword queries.
latestaiagentsCombine dense vector embeddings with sparse BM25 retrieval for RAG systems.
aryankumarraiSearches Replit documentation for platform features, pricing, and deployment information.
