web-research-ingest

Coordinates web research by generating plans and extracting content via Playwright for draft documents.

1|Updated Apr 12, 2026

Search Tags:#playwright #drafting #web-research #ingest #crawl #content-cleaning

Ready to run

npx skills add https://github.com/mengsi16/brain-base --skill web-research-ingest

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: web-research-ingest
Source: https://github.com/mengsi16/brain-base/tree/main/skills/web-research-ingest
Command: npx skills add https://github.com/mengsi16/brain-base --skill web-research-ingest

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill orchestrates external web research when get-info-agent requires supplementary, up-to-date information. It selects search strategies based on a query plan and produces structured drafts suitable for persistence.

Core Features & Use Cases

Generate search plans with multiple variants and prioritize candidate sources.
Invoke Playwright-based tooling to fetch, filter, and extract content from web pages.
Clean, structure, and annotate retrieved content for downstream persistence and QA.

Quick Start

Generate a retrieval plan and produce a structured draft from the selected web sources.

Frequently Asked Questions about web-research-ingest

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

FAQPage Schema

How do I automate web research and draft documents from crawled content?▼

Automated web research generates multi-variant search plans, uses Playwright to fetch and extract web content, then cleans and structures the data into a draft document for persistence.

What is the best way to extract and clean content from web pages for a knowledge base?▼

Content extraction and cleaning uses Playwright-driven retrieval to filter candidate pages, extract relevant text, and annotate the structured content for downstream persistence and QA.

How does Playwright work for fetching and filtering web pages during research?▼

Playwright fetches web pages by executing retrieval plans, filtering candidate sources against query variants, and extracting structured content suitable for draft generation.

Can I generate a retrieval plan to prioritize candidate sources before crawling?▼

Yes, retrieval plan generation creates multiple search variants and prioritizes candidate web sources before invoking Playwright to fetch, filter, and extract the actual content.

Do I need to install Playwright to use this web research and ingest workflow?▼

Playwright is required as the underlying tool for fetching, filtering, and extracting content from web sources during the retrieval and draft document generation process.

What are the limitations of using Playwright for web content extraction?▼

Playwright content extraction depends on candidate source filtering and retrieval plan variants, limiting results to accessible web pages that can be cleaned and structured for persistence.