Deep Research AI Skill: Master Investigations & Fact-Checking

Deep Research AI Skill: Master Investigations & Fact-Checking

This AI skill supports users in conducting thorough research, comparing options, fact-checking claims, and investigating unfamiliar topics. It helps to prepare reports, build knowledge bases, and trace claims to their primary sources using a structured workflow.

What this skill does

• Defines the research scope by setting question, audience, depth, and query budget.
• Outlines key items, fields, and success criteria necessary for the investigation.
• Selects the appropriate retrieval tool to acquire information, prioritizing sources as needed.
• Conducts information retrieval in a tiered manner, never starting at the most detailed level.
• Verifies information according to established protocols and checks for staleness or outdated versions.
• Applies stop criteria to manage workflow effectively and compiles results into the desired output format.

Who it is for

This skill is suitable for developers and teams using AI coding agents such as Claude Code, Cursor, and Codex. It is particularly useful for those involved in research-intensive activities or requiring precise information verification.

Use cases

• Assisting teams in performing comprehensive market analyses by comparing vendors and options.
• Supporting fact-checking initiatives to ensure claims are verifiable and traceable to primary sources.
• Facilitating the creation of reference documentation or knowledge bases for technical subjects.
• Preparing detailed reports or briefings on novel or complex topics.

Technical details

• Utilizes a Docs-index tool for accessing library, API, and framework documentation in a version-scoped manner.
• Employs headless-browser fetches to gather client-rendered content when necessary.
• Uses a bulk-crawler for handling multiple sources simultaneously, optimizing query budget usage.
• Implements retry protocols for sites with known access, including browser-capable tools to navigate access challenges.
• Incorporates a capped query budget system shared across parallel subagents for efficient resource allocation.

Source & Licence

This package is built on open-source work published by slilbudget (slilbudget/knowledge-delta-skills) and distributed under MIT. The original licence text and copyright notice are included in your download.

Personal and commercial use, modification and redistribution are permitted, provided the original copyright and licence notice are retained.

Your purchase covers curation, licence verification, packaging, documentation and instant delivery. It does not grant exclusive rights to the underlying open-source code, which remains available under its original licence.

Delivery & Support

• Delivery: instant — a secure download link is emailed to you as soon as payment is confirmed.
• Format: ZIP archive containing the skill files, documentation and the original licence.
• Support: support@mcpcart.com — we aim to reply within 2 business days.
• Updates: updates are included only where stated on this page.

Refunds

This is a digital product delivered immediately after purchase. By completing your order you request immediate delivery and acknowledge that, once the download has been accessed, the statutory right to cancel no longer applies to the extent permitted by law. Refund requests are handled in accordance with our published Refund Policy.

Claude, Codex, Gemini and Cursor are trademarks of their respective owners. MCP Cart is an independent marketplace and is not affiliated with, endorsed by, or sponsored by any of them. Compatibility references describe interoperability only.