research

Automate structured research with evidence archives and self-audit outputs.

8|1|Updated Mar 30, 2026

Search Tags:#research #queries #audit #evidence #sources #claims

Ready to run

npx skills add https://github.com/wphillipmoore/ai-research-methodology --skill research-wphillipmoore

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: research
Source: https://github.com/wphillipmoore/ai-research-methodology/tree/main/skills/research
Command: npx skills add https://github.com/wphillipmoore/ai-research-methodology --skill research-wphillipmoore

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Open-source researchers and AI agents often struggle to organize evidence and produce auditable, reproducible results. This Skill automates end-to-end research pipelines to generate defensible conclusions with transparent provenance.

Core Features & Use Cases

Claims, Queries, and Axioms handling: parses inputs, generates competing hypotheses, and routes tasks through a structured research workflow.
Evidence archives & self-audits: produces comprehensive outputs including source scorecards, search logs, hypotheses, and self-audits for full traceability.
Reproducibility & isolation: supports reruns with input specifications and strict separation from prior outputs to ensure unbiased results.
Use Case: researchers can conduct a complete, literature-backed investigation with transparent provenance for each claim.

Quick Start

Provide your claims, queries, and/or axioms to start a structured research run.

Frequently Asked Questions about research

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

FAQPage Schema

How do I verify claims and fact-check documents with full evidence archives?▼

Structured research automates claim verification and document fact-checking by parsing inputs, generating competing hypotheses, running discriminating searches, scoring sources, and producing self-audits with full evidence archives for transparent provenance.

What is the best way to organize evidence for reproducible open-source research?▼

Organizing evidence for reproducible open-source research requires a workflow that separates prior outputs, supports reruns with input specifications, and generates comprehensive outputs including source scorecards, search logs, and self-audits to ensure unbiased, defensible conclusions.

How does a structured research workflow handle queries and axioms differently?▼

A structured research workflow handles queries and axioms by parsing each input type, generating competing hypotheses, and routing the tasks through discriminating searches, source scoring, and collection synthesis to produce defensible conclusions with formal self-audit outputs.

Can I rerun an investigation without prior outputs biasing the new results?▼

Yes, you can rerun an investigation without prior bias because this research workflow supports strict isolation from previous outputs and accepts input specifications to ensure reproducible, unbiased results across multiple research runs.

What outputs do I get from an automated fact-checking and research pipeline?▼

Outputs from an automated fact-checking pipeline include comprehensive evidence archives, source scorecards, search logs, competing hypotheses, collection synthesis, and formal self-audits that provide full traceability for each claim or query.

When should I use an automated research pipeline instead of manual source verification?▼

Use an automated research pipeline instead of manual source verification when you need to organize complex evidence, generate competing hypotheses, and produce auditable, reproducible results with transparent provenance across multiple claims, queries, or axioms.