research-protocol

Classify external research findings by confidence levels and enforce source attribution.

Updated Mar 9, 2026
One-click install
npx skills add https://github.com/Yazo1968/market --skill research-protocol
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: research-protocol
Source: https://github.com/Yazo1968/market/tree/main/plugins/startup-assessment/skills/research-protocol
Command: npx skills add https://github.com/Yazo1968/market --skill research-protocol

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill ensures that all external research conducted by agents adheres to strict standards of honesty, humility, and hedging, preventing the use of unreliable or biased information in assessments.

Core Features & Use Cases

  • 3H Principle Enforcement: Guarantees research is Honest, Humble, and Hedged.
  • Confidence Classification: Assigns appropriate confidence levels (Verified, Corroborated, Conflicted, Unverified, Training-Derived) to research findings.
  • Research Category Guidance: Provides structured approaches for researching Market Validation, Competitive Intelligence, Regulatory Environment, Team Verification, and Comparable Transactions.
  • Conflict Resolution: Defines clear rules for handling conflicting research sources.
  • Source Attribution: Mandates detailed attribution for all research findings.
  • Use Case: When an agent needs to verify a company's market size claim, this Skill guides the agent to find authoritative sources, compare findings, and report with appropriate confidence and attribution, ensuring the assessment is based on sound data.

Quick Start

Use the research protocol skill to verify the market size for enterprise AI software.

Frequently Asked Questions about research-protocol

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

FAQPage Schema
How do I enforce research integrity when verifying external market validation data?

To enforce research integrity, apply the 3H Principle (Honest, Humble, Hedged) to external research, classifying findings by confidence levels like Verified or Unverified to prevent reliance on biased information. This ensures market validation data is rigorously evaluated.

What is the 3H Principle for maintaining research protocol in competitive intelligence?

The 3H Principle requires that research findings remain Honest, Humble, and Hedged. It mandates detailed source attribution and confidence classification to ensure competitive intelligence assessments are based on sound, verifiable data rather than unreliable claims.

How do I handle conflict resolution when research sources provide contradictory information?

Conflict resolution for contradictory sources involves applying predefined rules to evaluate findings and assigning a Conflicted confidence classification. This structured approach ensures conflicting research sources are managed transparently without compromising the final assessment.

How do I classify confidence levels for team verification and comparable transactions?

Classify confidence levels for team verification by categorizing findings as Verified, Corroborated, Conflicted, Unverified, or Training-Derived. This prevents training-derived knowledge from scoring assessments and ensures comparable transactions rely on attributed data.

When should I mandate source attribution for regulatory environment research?

Source attribution for regulatory environment research should always be mandated to prevent reliance on training-derived knowledge. Detailed attribution ensures all findings are traceable to authoritative sources, maintaining research integrity across all five research categories.

What are the limitations of using training-derived knowledge in research protocol assessments?

Training-derived knowledge lacks verifiable source attribution and cannot be relied upon for scoring assessments. The research protocol explicitly prevents its use by mandating external verification and classifying such findings with appropriate confidence levels to maintain integrity.