Search a knowledge base with natural language and return ranked results with provenance.
npx skills add https://github.com/norrietaylor/distillery --skill recall-norrietaylor
Please help me install this Agent Skill. Skill: recall Source: https://github.com/norrietaylor/distillery/tree/main/skills/recall Command: npx skills add https://github.com/norrietaylor/distillery --skill recall-norrietaylor
When teams need to retrieve exact past decisions, discussions, or notes from a growing knowledge base, this skill makes it easy to ask in natural language and get ranked results with provenance.
Ask a question using natural language like: "What do we know about distributed caching?" and review the ranked results with provenance.
High-intent search queries and answers about installing and using this skill.
Semantic search lets you query a knowledge base using natural language and returns ranked results with provenance. Each entry includes author, project, and created_at metadata to trace the source of the information.
Knowledge base search results support optional filters including entry type, author, and project. These filters narrow the search scope to return only relevant entries matching specific workflow parameters.
Natural language queries retrieve exact past decisions, discussions, or notes from a knowledge base. Ask questions like "What do we know about distributed caching?" and review ranked results with provenance to find relevant entries fast.
Semantic search returns full, untruncated results including entry IDs and provenance. This ensures complete information retrieval without losing context or cutting off important details from the original knowledge base entries.
Search results can be limited to a configurable number to fit workflows. This constraint prevents information overload by capping the returned entries while maintaining relevance ranking and provenance metadata.
Provenance provides author, project, and created_at metadata for each knowledge base entry. This contextual information helps verify the credibility, timeline, and source of retrieved decisions, discussions, or notes during semantic search.
indranilbanerjeeSearch brand knowledge across vector, graph, and local memories with filters.
orbrunoConvert unstructured PDFs, DOCX, and HTML documents into structured Markdown or JSON.
fortunto2Index YouTube transcripts into a searchable local knowledge store with metadata and topic extraction.
tense-iRetrieve and rank knowledge-base entries by relevance and quality.
