Stats
Actions
Tags
From mem-oracle
Searches indexed documentation for library, framework, API usage, best practices, and code examples. Retrieves relevant snippets with titles, headings, content, URLs, and scores via local API.
How this skill is triggered — by the user, by Claude, or both
Slash command
/mem-oracle:docs-searchThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Search indexed documentation for relevant information.
Search indexed documentation for relevant information.
Use this skill when the user asks about:
Base URL: http://127.0.0.1:7432
curl -X POST http://127.0.0.1:7432/retrieve \
-H "Content-Type: application/json" \
-d '{"query": "your search query", "topK": 5}'
curl -X POST http://127.0.0.1:7432/index \
-H "Content-Type: application/json" \
-d '{"baseUrl": "https://docs.example.com", "seedSlug": "/getting-started"}'
curl http://127.0.0.1:7432/status
Results include:
title: Page titleheading: Section heading (if available)content: Relevant text snippeturl: Source documentation URLscore: Relevance score (0-1)npx claudepluginhub jagjeevanak/mem-oracle --plugin mem-oracleUses docpull tools to fetch, index, and search live docs for fast-moving libraries like Next.js, FastAPI, LangChain, React when answering 'how to X' or API questions.
Crawls web documentation into context for up-to-date coding assistance. Quick mode fetches 1-15 pages; deep mode indexes 20-100 pages for search and selective retrieval.
Fetches up-to-date GitHub documentation for libraries, frameworks, and APIs via search and chunk/TOC retrieval for usage, references, configs.