home / skills / toilahuongg / shopify-agents-kit / research

research skill

safe

This skill guides thorough, multi-source research using verification, synthesis, and RAG patterns to deliver well-supported, actionable conclusions.

npx playbooks add skill toilahuongg/shopify-agents-kit --skill research

Review the files below or copy the command above to add this skill to your agents.

Files (1)

SKILL.md

2.7 KB

---
name: research
description: Guide for conducting thorough and synthesized research, focusing on verification, multi-source analysis, and RAG patterns.
---

# Research Skill

This skill outlines the process for conducting deep, accurate, and synthesized research. It transforms the agent from a simple search engine interface into a comprehensive research assistant.

## 🕵️ Core Philosophy
*   **Synthesis over Summarization:** Don't just list search results. Combine information to answer the "So What?".
*   **Triangulation:** Verify facts by finding them in multiple independent sources.
*   **Citation is Mandatory:** Every specific claim must be backed by a source.

## 🛠️ The Research Framework

### 1. Planning (The "Research Agent" Mode)
Before searching, define the scope.
*   **Clarify Objectives:** What is the exact question?
*   **Identify Domains:** Where does this information live? (Academic papers, technical docs, news, forums?)
*   **Keyword Strategy:** Generate diverse search queries to target different aspects (e.g., broad vs. specific, technical vs. layman).

### 2. Information Gathering (Source Quality)
*   **Primary Sources:** Official documentation, direct interviews, laws, scientific papers.
*   **Secondary Sources:** Reputable analysis, industry reports, expert articles.
*   **Tertiary Sources:** Wikipedia, generalized blog posts (use only for initial context).

> **Rule:** If a search result contradicts the user's premise, investigate the discrepancy explicitly.

### 3. Synthesis & Analysis (RAG Pattern)
When presenting findings:
1.  **The Executive Summary:** Answer the question directly in 1-2 paragraphs.
2.  **Key Findings:** Group facts by *theme*, not by source.
    *   *Bad:* "Source A says X. Source B says Y."
    *   *Good:* "The consensus on Topic X is [...], although some experts disagree regarding [...] (Source B)."
3.  **Evidence Table:** If comparing options, always use a table.

### 4. Verification & Fact-Checking
*   **Check Dates:** Is this info outdated? (Critical for tech/laws).
*   **Cross-Reference:** If one source makes a bold claim, find a second source to confirm.
*   **Identify Bias:** Note if a source has a conflict of interest (e.g., a vendor review).

## 🚀 Execution Patterns

**for "Deep Dive" Requests:**
1.  Search for the core concept.
2.  Read the top results to understand the vocabulary.
3.  Refine search with specific technical terms found in step 2.
4.  Synthesize findings into a structured report.

**for "Tech Stack Comparison":**
1.  Identify criteria (e.g., Performance, Cost, DX).
2.  Search for specific comparisons (e.g., "Mongoose vs Prisma performance").
3.  Create a comparison matrix.
4.  Provide a recommendation based on specific use cases.

Overview

This skill guides an agent to conduct thorough, verifiable, and synthesized research that goes beyond surface-level search results. It emphasizes planning, multi-source verification, and presenting clear, evidence-backed conclusions using RAG (retrieve-and-generate) patterns. The goal is actionable research outputs that answer the "So what?".

How this skill works

Start by defining the research question and the domains where relevant information lives (academic papers, official docs, news, forums). Gather primary, secondary, and tertiary sources with a bias toward primary evidence. Synthesize findings into an executive summary, thematically grouped key findings, and an evidence-backed comparison or table when applicable. Verify claims by triangulating multiple independent sources and checking dates and conflicts of interest.

When to use it

Preparing a decision-ready research brief or executive summary.
Comparing technical options, products, or vendor claims with evidence.
Fact-checking a claim or tracing the origin of a reported statistic.
Conducting literature reviews or background research for reports.
Creating RAG-enabled summaries that combine retrieved documents with generated analysis.

Best practices

Define a narrow research scope and concrete questions before searching.
Prioritize primary sources and corroborate bold claims with at least one independent source.
Use diverse query strategies (broad, specific, jargon, lay terms) to surface different perspectives.
Group findings by theme and highlight consensus versus disagreement with citations.
Always note dates and potential bias or conflicts of interest for each source.

Example use cases

Produce a 1–2 paragraph executive summary plus a themed evidence section for a market-entry decision.
Compare two database ORMs with a criteria matrix (performance, cost, DX) and cite benchmark sources.
Verify a viral technical claim by locating original tests, follow-up analyses, and vendor statements.
Assemble a literature review on a narrow scientific question with prioritized primary papers.

FAQ

How many sources are enough to verify a claim?

Aim for at least two independent, credible sources for any specific factual claim; prefer primary sources when available.

When should I use tertiary sources like Wikipedia?

Use tertiary sources only for initial orientation or to find primary references, not as final evidence.