Search vector-indexed passages and retrieve source context via the Glynk API.
npx skills add https://github.com/Talegorithm/Glynk --skill glk-search
Please help me install this Agent Skill. Skill: glk-search Source: https://github.com/Talegorithm/Glynk/tree/main/skills/glk-search Command: npx skills add https://github.com/Talegorithm/Glynk --skill glk-search
This Skill solves the challenge of finding specific insights, annotations, or relevant passages across vast libraries of books, papers, and personal notes that traditional keyword search often misses.
Use the glk-search skill to find all highlights and notes related to the topic of decision making under uncertainty.
High-intent search queries and answers about installing and using this skill.
Semantic search across annotations and highlights uses vector-indexed passages to match natural language meaning rather than exact keywords. You query your structured content library to find specific insights that traditional keyword search misses.
Semantic search retrieves original source context by querying vector-indexed passages and returning the exact paragraph or source text for any identified result. This allows you to verify information directly from the original document.
Yes, executing programmatic search and feedback operations requires a valid GLYNK_TOKEN and access to the Glynk API. This environment setup allows the semantic discovery process to query your indexed passages securely.
The best way to find relevant highlights and notes across your library is using semantic discovery to search by natural language meaning. This approach matches the conceptual intent of your query against all indexed content and annotations.
Traditional keyword search misses specific insights because it relies on exact text matching rather than understanding natural language meaning. Semantic search solves this by querying vector-indexed passages to find conceptually relevant information across vast libraries.
TalegorithmRead and annotate long-form documents via the Glynk API.
patronus-aiBuild RAG systems using vector databases and semantic search.
AbilityaiRetrieve relevant knowledge from an Obsidian vault via multi-layer semantic search.
BEKO2210Search knowledge bases semantically with vector embeddings and keyword fallback.
