tinyfish
Use TinyFish web agent to extract/scrape websites, extract data, and automate browser actions using natural language. Use when you need to extract/scrape data from websites, handle bot-protected sites, or automate web tasks.
Why use this skill?
Automate web browsing and data extraction with the TinyFish skill. Easily scrape protected websites, handle complex forms, and get structured JSON data fast.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/simantak-dabhade/tinyfish-web-agentWhat This Skill Does
The tinyfish skill is an advanced web automation agent designed to streamline data extraction, web scraping, and browser interactions. By leveraging the TinyFish web agent infrastructure, it enables natural language commands to drive browser-based actions, making it ideal for tasks that require navigating complex, dynamic, or bot-protected websites. It bridges the gap between raw web data and structured JSON, allowing users to turn entire websites into usable data formats without manual parsing.
Installation
To integrate this skill into your environment, use the OpenClaw skill manager:
clawhub install openclaw/skills/skills/simantak-dabhade/tinyfish-web-agent
Before execution, ensure your TINYFISH_API_KEY is exported in your environment. You can verify this by running the pre-flight check script provided in the documentation. Failure to set this key will halt operations immediately.
Use Cases
- E-commerce Monitoring: Automatically track product prices, inventory status, and availability across multiple vendors.
- Bot-Protected Scraping: Access data from sites that use aggressive anti-bot protections by utilizing the built-in 'stealth' browser profile.
- Market Research: Extract lists of articles, research papers, or business listings into structured JSON for analysis.
- Geo-Targeting: Use the proxy configuration to access region-locked content or compare pricing variations across different countries.
Example Prompts
- "Use tinyfish to go to https://example.com/shop and extract all products into a JSON array with name, price, and stock status."
- "Can you extract the latest tech news headlines from https://techcrunch.com? Please format the output as a list of objects with the title and URL."
- "Scrape the pricing information from this protected site https://protected-retailer.com using the stealth browser profile and proxy it through the US."
Tips & Limitations
- Be Specific with JSON: Always define the expected output schema (e.g., 'JSON array: [{name: str}]') to ensure the agent returns data that is ready for programmatic use.
- Parallelize Work: If scraping many sites, invoke separate calls to minimize downtime and prevent one long-running task from blocking others.
- Stealth Mode: Only use the 'stealth' profile when necessary, as it may increase latency compared to standard requests.
- API Dependency: This skill is strictly dependent on the TinyFish API; local network access is required to communicate with their infrastructure.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-simantak-dabhade-tinyfish-web-agent": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access, external-api