// Use Jina AI APIs for converting URLs to LLM-friendly Markdown (Reader) and searching the web (Search).
| name | jina-ai |
| description | Use Jina AI APIs for converting URLs to LLM-friendly Markdown (Reader) and searching the web (Search). |
This skill integrates Jina AI's Reader (r.jina.ai) and Search (s.jina.ai) APIs to convert URLs and web search results into clean, LLM-friendly Markdown.
Dependencies: Requires requests.
pip install requests python-dotenv
API Key Configuration (Recommended): Jina APIs offer higher limits with an API key (JINA_API_KEY).
read -p "Enter your Jina API key (optional, press Enter to skip): " JINA_KEY
if [ ! -z "$JINA_KEY" ]; then
echo "JINA_API_KEY=$JINA_KEY" >> .env
if [ -f .gitignore ] && ! grep -q ".env" .gitignore; then echo ".env" >> .gitignore; fi
echo "API key saved to .env."
fi
The script scripts/jina_tools.py supports read and search operations.
Convert a URL into clean Markdown.
python3 scripts/jina_tools.py read "<url>"
Example:
python3 scripts/jina_tools.py read "https://en.wikipedia.org/wiki/Large_language_model"
Search the web and return the top results converted to Markdown.
python3 scripts/jina_tools.py search "<query>"
Example:
python3 scripts/jina_tools.py search "What is Jina AI?"
The script outputs results in JSON format, containing title, URL, and content_markdown.
Browser automation CLI for AI agents. Use when needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. TRIGGER when user requests to "open a website", "fill out a form", "click a button", "take a screenshot", "debug this in browser", "scrape data from a page", "test this web app", "login to a site", "frontend UI/UX aesthetics", "automate browser actions", or any task requiring programmatic web interaction.
Design and implement distinctive, production-ready frontend interfaces with strong aesthetic direction. Use when asked to create or restyle web pages, components, or applications (HTML/CSS/JS, React, Vue, etc.).
This skill should be used when the user sends an image and asks to "analyze this image", "describe this picture", "what's in this image", or any request requiring visual understanding of images. Provides image analysis using Zhipu GLM-4.6V multimodal model.
This skill should be used for web search and content scraping via DuckDuckGo MCP Server.
Create and render OpenSCAD 3D models. Generate preview images from multiple angles, extract customizable parameters, validate syntax, and export STL files for 3D printing.
This skill should be used before running non-interactive long-running tasks, computation intensive tasks, background tasks, or needs guidance on the pueue CLI tool usage. TRIGGER when user says "use pueue", "run in background", "queue this task", or when about to run any long-running (>2 min) task.