jina-ai
CommunityFast web reading, search, and PDF extraction
Authorarchibate
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Provide reliable extraction and retrieval of web pages, academic papers, images, and PDF figures so users can quickly gather and analyze source content without manual copy-paste or visual inspection.
Core Features & Use Cases
- Web Reading: Cleanly extract article content, links, and images from single or multiple URLs for summarization or ingestion.
- Search & Research: Perform web, arXiv, SSRN, and blog searches with parallel queries and time/location filters for up-to-date or domain-specific research.
- PDF & Visual Extraction: Extract figures, tables, and equations from PDFs and capture full-page or viewport screenshots as base64 or URLs.
- NLP & Embeddings: Classify text with embeddings, rerank documents by relevance, deduplicate strings/images, and expand queries for deeper coverage.
- Use Case: Collect and extract figures from recent arXiv papers, gather web sources and screenshots, then deduplicate and rerank results for literature review.
Quick Start
Call the jina-ai skill to read a URL, extract the main content and all links, and return cleaned markdown.
Dependency Matrix
Required Modules
mcpanyiohttpxhttpx-sse
Components
scripts
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: jina-ai Download link: https://github.com/archibate/archibate-skills/archive/main.zip#jina-ai Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.