Automates web research, generates HTML reports with confidence scores, contradiction detection, and source attribution. Benefits operations teams by streamlining data gathering and analysis. Integrates with Claude Code for automated research tasks.
git clone https://github.com/vasilievyakov/researching-web-skill.gitResearching Web transforms any question into a comprehensive research report by combining semantic search with parallel content extraction. The skill synthesizes 5+ sources simultaneously, detects contradictions between conflicting information, and generates beautiful HTML reports with transparency. Each finding includes a confidence score broken down by consensus level, source authority, and content freshness. Unlike traditional AI responses, every claim is attributed to specific sources with scoring methodology visible. The skill auto-selects optimal search depth based on query classification and outputs publication-ready reports with dark/light theme support.
Clone the skill to ~/.claude/skills/researching-web and configure Exa and Tabstack MCP servers in Claude Code with your API keys. Ask any research question and the skill generates an HTML report automatically. No manual source selection or formatting required.
Market research and competitive analysis with multi-source synthesis
Fact-checking and contradiction detection across industry sources
Due diligence reports with transparent source scoring and attribution
Technical comparison analysis (frameworks, tools, platforms)
No install command available. Check the GitHub repository for manual installation instructions.
git clone https://github.com/vasilievyakov/researching-web-skillCopy the install command above and run it in your terminal.
Launch Claude Code, Cursor, or your preferred AI coding agent.
Use the prompt template or examples below to test the skill.
Adapt the skill to your specific use case and workflow.
I need you to research [TOPIC] for [COMPANY] in the [INDUSTRY] sector. Use the Researching Web skill to gather information, generate an HTML report with confidence scores, detect contradictions, and attribute sources. Focus on [SPECIFIC DATA POINTS] and provide insights relevant to [COMPANY]'s goals.
# Research Report on Sustainable Packaging Trends for GreenPack Solutions ## Key Findings - **Eco-friendly materials**: Biodegradable plastics and recycled materials are gaining traction. (Confidence: 85%) - **Consumer demand**: 72% of consumers prefer sustainable packaging. (Confidence: 90%) - **Regulatory trends**: New EU regulations on single-use plastics. (Confidence: 95%) ## Contradictions Detected - Source A claims biodegradable plastics take 5 years to decompose, while Source B claims 2 years. Further investigation needed. ## Sources 1. [Environmental Protection Agency](https://www.epa.gov) 2. [McKinsey & Company](https://www.mckinsey.com) 3. [EU Official Journal](https://eur-lex.europa.eu) ## Recommendations - GreenPack should consider investing in R&D for biodegradable materials. - Monitor EU regulations closely for compliance.
AI assistant built for thoughtful, nuanced conversation
IronCalc is a spreadsheet engine and ecosystem
ITIL-aligned IT service management platform
Customer feedback management made simple
Enterprise workflow automation and service management platform
Automate your spreadsheet tasks with AI power
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan