skills.rest
cutec-chris
cutec-chrisCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

researcher

Index and query topic-specific knowledge bases within separate research projects.

1|Updated Mar 19, 2026
Search Tags:#research#python#rag#web-scraping#knowledge-base#query-engine#document-indexing
One-click install
npx skills add https://github.com/cutec-chris/PawLia --skill researcher-cutec-chris
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: researcher
Source: https://github.com/cutec-chris/PawLia/tree/main/skills/researcher
Command: npx skills add https://github.com/cutec-chris/PawLia --skill researcher-cutec-chris

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, beautifulsoup4, html2text, trafilatura, pdfminer.six, youtube-transcript-api, lightrag-hku, pyyaml, and includes scripts (resource) components.

What problem does it solve?

Organize research topics into separate projects, each with an isolated knowledge base and indexing pipeline, so you can independently store, search, and manage information for different topics.

Core Features & Use Cases

  • Create multiple research projects with per-project memory and a dedicated RAG backend for indexing and querying documents.
  • Add URLs or documents to a project to build and query its knowledge base; support for URL scraping with depth control.
  • Query across a project’s indexed content to retrieve precise, context-aware answers and maintain separate workflows per topic.

Quick Start

Create a project with a name and description, then add a URL to start building its knowledge base.

Frequently Asked Questions about researcher

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

FAQPage Schema
How do I build a separate knowledge base for different research topics?▼

To build separate knowledge bases for different research topics, create multiple research projects with per-project RAG backends. This isolates indexing and querying workflows, allowing independent storage and retrieval for each topic.

Can I scrape web pages and add URLs to a RAG query engine?▼

Yes, you can add URLs to a project to build its knowledge base using automated web scraping scripts with depth control. The RAG backend then indexes the extracted content for context-aware querying.

Do I need to configure embedding providers before using a RAG-backed research project?▼

Yes, you need to configure embedding providers and models before using the RAG-backed research project. This setup is required to enable document indexing and precise context-aware retrieval.

What file formats and sources can I index for document retrieval in a research project?▼

You can index web pages and PDFs using dependencies like pdfminer.six, beautifulsoup4, and trafilatura. YouTube transcripts can also be extracted and added to the project's knowledge base.

What's the best way to organize multiple research workflows without mixing indexed documents?▼

Organize research workflows by creating separate projects with isolated knowledge bases. Each project maintains its own dedicated RAG backend, preventing indexed documents from mixing across different topics.

Why does my RAG query return incomplete information after adding a URL?▼

Incomplete RAG queries may occur if URL scraping depth is too shallow or content extraction fails. Ensure the scraping depth setting captures linked pages and that automated extraction scripts properly parse the document.

Related Skills

Explore More Education & Research Skills→
juanrejuanre
6

basic-usage

Store, index, and search documents with LLMemory in Python.

Community
Advanced
legoutlegout
3

exa-search

Perform semantic web searches and structured research via the Exa API.

Community
Intermediate
simoneschiavosimoneschiavo

youtube

Extract plain or timestamped transcripts and insights from YouTube videos.

Community
Intermediate
justStevejustSteve
19

AgentDB Vector Search

Perform semantic vector search and retrieval with AgentDB using HNSW indexing.

Community
Advanced