Research
This skill swiftly gathers relevant information from the web to support your queries and decision-making processes.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add scientiacapital-research npx -- -y @trustedskills/scientiacapital-research
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"scientiacapital-research": {
"command": "npx",
"args": [
"-y",
"@trustedskills/scientiacapital-research"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
This skill enables an AI agent to conduct research, combining market intelligence and technical evaluation to support decision-making. It gathers information from various online sources like websites, LinkedIn, Google News, GitHub, HuggingFace, and Context7 documentation. The output is a structured research report including questions, answers, confidence levels (high/medium/low), and cited sources.
When to use it
- Company Profiling: Before outreach or call preparation to understand a company's basics and operations.
- Competitive Intelligence: To analyze market position and pricing for deal strategy.
- Tech Stack Discovery: For lead qualification by identifying software and integrations used.
- Technical Evaluation: To compare frameworks, APIs, or LLMs (Large Language Models) when making technical decisions.
- MCP (Model Context Protocol) Discovery: To identify available servers and tools for expanding capabilities.
Key capabilities
- Market Research: Company profiling, competitive intelligence, tech stack discovery, pain signal detection.
- Technical Research: Framework evaluation, LLM comparison, API assessment, MCP discovery.
- Structured Output: Generates research reports with questions, answers, confidence levels, and sources.
- Source Documentation: Includes access dates for all cited sources.
- Decision Matrix Support: Facilitates multi-option comparisons using decision matrices.
Example prompts
- "Research [Company Name] and create a company profile."
- "What is the tech stack used by [Company Name], focusing on their CRM?"
- "Evaluate [Framework A] versus [Framework B] for [specific use case]."
- “Find pain signals associated with [Company Name].”
Tips & gotchas
- The skill requires a clearly defined question and documented constraints to be effective.
- For technical research, the agent respects an "NO OPENAI" constraint, meaning it will avoid using OpenAI models in its process.
- Multiple sources are consulted for each research task; relying on a single source is discouraged.
Tags
TrustedSkills Verification
Unlike other registries that point to live repositories, TrustedSkills pins every skill to a verified commit hash. This protects you from malicious updates — what you install today is exactly what was reviewed and verified.
Security Audits
| Gen Agent Trust Hub | Pass |
| Socket | Pass |
| Snyk | Pass |
🌐 Community
Passed automated security scans.