skills.rest
AMGrobelnik
AMGrobelnikCOMMUNITY
Explore all skills by this author →
GitHub

aii_web_research_tools

Search the web, retrieve page content, and extract text from HTML and PDF documents.

1|Updated Feb 27, 2026
Search Tags:#data extraction#information retrieval#web search#web scraping#content fetching#pdf parsing
One-click install
npx skills add https://github.com/AMGrobelnik/ai-inventor-old3 --skill aii-web-research-tools
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: aii_web_research_tools
Source: https://github.com/AMGrobelnik/ai-inventor-old3/tree/main/.claude/skills/aii_web_research_tools
Command: npx skills add https://github.com/AMGrobelnik/ai-inventor-old3 --skill aii-web-research-tools

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill streamlines web-based information gathering by providing tools to search the web, retrieve page content, and extract specific text or data from HTML and PDF documents.

Core Features & Use Cases

  • WebSearch: Perform broad web searches to discover relevant information, returning titles, URLs, and snippets.
  • WebFetch: Retrieve and summarize the content of a specific web page (HTML only).
  • aii_web_fetch_grep: Extract precise text or data from HTML or PDF files using pattern matching and context windows.
  • Use Case: When researching a new technology, start with WebSearch to get an overview, use WebFetch to read key articles, and then use aii_web_fetch_grep to extract specific technical specifications or code examples.

Quick Start

Use the aii_web_fetch_grep tool to find all occurrences of the pattern "machine learning models" within the provided URL, returning up to 10 matches with 150 characters of context on each side.

Frequently Asked Questions about aii_web_research_tools

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

FAQPage Schema
How do I extract specific text from a PDF document using pattern matching?▼

To extract specific text from a PDF, use the aii_web_fetch_grep tool to find pattern matches and return the exact occurrences with configurable character context windows. This enables precise data pinpointing from PDF documents without manual reading.

What is the best way to research a new technology by scanning and analyzing web pages?▼

The best way to research a new technology is to use a web search workflow: perform broad discovery searches, retrieve and summarize key article content, and extract specific technical specifications. This streamlines web-based information gathering into a single scanning and extraction process.

Can I retrieve and summarize the content of an HTML web page?▼

Yes, you can retrieve and summarize HTML web page content using the WebFetch tool. It fetches the specified URL and provides a summarized version of the page content, though it does not support PDF summarization.

How do I perform a broad web search to discover relevant information and links?▼

You can perform a broad web search using the WebSearch tool to discover relevant information across the internet. It returns search results containing page titles, URLs, and snippets to help you identify relevant sources for further research.

Does the web scraping workflow support extracting data from both HTML and PDF files?▼

Yes, the web scraping workflow supports data extraction from both HTML and PDF files. The aii_web_fetch_grep tool handles both formats, allowing you to extract precise text using pattern matching and context windows across different document types.

What are the limitations of using automated content fetching for web research?▼

Limitations of automated content fetching include the WebFetch tool being restricted to HTML only, meaning it cannot summarize PDF content. Additionally, broad web searches return snippets rather than full text, requiring a separate fetching step for detailed page analysis.

Related Skills

Explore More Education & Research Skills→
ouzayrouzayr

web-search

Searches the web for current information and fetches content from specified URLs.

Community
Intermediate
tatsuki-washimitatsuki-washimi

analyze_external

Analyze external code, documents, media, and web data to extract structured insights.

Community
Intermediate
claude-office-skillsclaude-office-skills
368

data-extractor

Extract structured text, tables, and metadata from PDF, DOCX, HTML, and email documents.

Official
Intermediate
platonaiplatonai
1.1k

web-scraping

Extract titles, text, and structured fields from web pages using browser automation.

Community
Intermediate