Ingest URLs, documents, and transcripts into a searchable knowledge base.
npx skills add https://github.com/JKHeadley/instar --skill knowledge-base-jkheadley
Please help me install this Agent Skill. Skill: knowledge-base Source: https://github.com/JKHeadley/instar/tree/main/skills/knowledge-base Command: npx skills add https://github.com/JKHeadley/instar --skill knowledge-base-jkheadley
This Skill turns scattered URLs, documents, and transcripts into a searchable knowledge base so you can retrieve prior research instead of re-reading the same material.
Ask the agent to ingest the provided source into the knowledge base, sync the memory index, and make the new information searchable.
High-intent search queries and answers about installing and using this skill.
Ingesting documents into a searchable knowledge base involves adding web articles, transcripts, and notes into a local catalog. The system stores content as markdown files with YAML frontmatter and syncs a full-text index for instant retrieval.
The best way to search past research is querying a knowledge base with full-text search. This retrieves relevant facts, quotes, and reference material across previously ingested URLs and transcripts, eliminating the need to re-read source documents.
Yes, you can ingest meeting transcripts and media notes into a knowledge base. The system accepts URLs, documents, and transcripts, storing them with frontmatter metadata so you can review and search across media or meeting content later.
You manage and remove ingested sources from a knowledge catalog using CLI or API commands. These commands allow you to list, browse, and delete saved URLs and documents while keeping the memory index synchronized.
Yes, full-text search works with markdown files using YAML frontmatter. The knowledge base uses MemoryIndex FTS5 indexing to parse the frontmatter metadata and search across the ingested content catalog.
zjykzkIngest raw text data into an Obsidian wiki as searchable knowledge.
alanharrryy-wqSearch Notion pages and generate citation-rich briefs with inline citations.
joonlabConvert web page DOM content into Markdown files with YAML frontmatter.
eddmannStore and retrieve atomic notes with semantic connections in SQLite.
