browse-sh

Query websites via API-first or browser automation playbooks.

4|1|Updated May 15, 2026

Search Tags:#api integration #web automation #browserbase #catalog skills #scraping avoidance #domain playbooks

Ready to run

npx skills add https://github.com/Yasuui/hermes-community-skills --skill browse-sh

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: browse-sh
Source: https://github.com/Yasuui/hermes-community-skills/tree/main/skills/community/browse-sh
Command: npx skills add https://github.com/Yasuui/hermes-community-skills --skill browse-sh

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

It reduces unreliable web scraping and LLM guessing by providing precise, website-specific instructions for interacting with sites.

Core Features & Use Cases

API-first site playbooks: Leverages documented endpoints for token-efficient workflows like weather forecasts, GitHub metadata, and Hacker News stories.
Browser-required workflows when needed: Guides agent behavior for JS-rendered or anti-bot sites that require Browserbase-driven browsing.
Operational requirements clarity: Specifies when Browserbase API keys and a real browser session are required versus clean API calls.

Quick Start

Use the browse-sh skill to plan a weather workflow for a given location by asking an AI agent to resolve a point via api.weather.gov and then fetch the associated forecast.

Frequently Asked Questions about browse-sh

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I turn websites into APIs reliably without web scraping?▼

To turn websites into APIs, you use predefined domain playbooks that provide specific instructions for querying sites via documented endpoints first, avoiding unreliable scraping and LLM guessing for structured data extraction.

What is the best way to extract structured data from JS-rendered or anti-bot websites?▼

For JS-rendered or anti-bot websites, domain playbooks specify a browser-required workflow that drives a controlled Browserbase session to execute interactions and extract information reliably.

Do I need a Browserbase API key to use browse-sh for web automation?▼

You need a Browserbase API key only when a playbook specifies a browser-required workflow for JS-rendered or anti-bot sites. API-first workflows for domains like weather or GitHub metadata do not require Browserbase.

How do I get weather forecasts and GitHub metadata using API integration?▼

You get weather forecasts and GitHub metadata through API-first site playbooks that leverage documented endpoints, such as resolving a point via api.weather.gov and fetching the associated forecast for token-efficient workflows.

When should I choose an API-first approach over browser automation for scraping avoidance?▼

You should choose an API-first approach over browser automation when interacting with domains that have documented endpoints. This ensures token-efficient workflows and scraping avoidance for tasks like fetching Hacker News stories.