research

Synthesize academic and practical sources into evidence cards and research reports.

4|Updated Dec 14, 2025
One-click install
npx skills add https://github.com/LukasStrickler/ai-dev-atelier --skill research-lukasstrickler
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: research
Source: https://github.com/LukasStrickler/ai-dev-atelier/tree/main/content/skills/research
Command: npx skills add https://github.com/LukasStrickler/ai-dev-atelier --skill research-lukasstrickler

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires jq, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill enables teams to perform comprehensive academic research and evidence synthesis to inform architecture decisions, software design, and implementation plans. It organizes diverse sources, enforces write-first evidence-card workflows, and produces structured outputs that can be embedded into product decisions.

Core Features & Use Cases

  • Evidence synthesis: Gather and synthesize a broad set of academic and non-academic sources into cohesive evidence cards and references.json.
  • Conflict-seeking analysis: Explicitly surface opposing viewpoints to support robust decision making in uncertain domains.
  • Output artifacts: Generate evidence cards, references.json, and final research reports to guide architecture decisions and documentation.
  • Decision support: Reuse evidence cards for architecture experiments and risk assessments across teams.

Quick Start

  1. Start a session by defining topic and codebase context in a research-question.md and create the first evidence-card after reviewing 1-2 sources.
  2. Continue adding sources in batches of 1-2, updating references.json after each card, and saving progress.
  3. When ready, generate a comprehensive research report that synthesizes all evidence cards and presents a clear recommendation.

Frequently Asked Questions about research

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

FAQPage Schema
What is evidence-based research for architecture decisions?

Evidence-based research for architecture decisions involves collecting diverse sources, synthesizing claims into structured evidence cards, and producing final research reports with citations to guide technology evaluation and implementation planning.

How do I synthesize academic and non-academic sources into evidence cards?

You synthesize sources into evidence cards using a write-first workflow: after reviewing 1-2 sources, create an evidence card and update references.json, explicitly surfacing opposing viewpoints to support robust decision making in uncertain domains.

Does this research workflow require any specific dependencies or environment setup?

Yes, this research workflow requires jq as a dependency to process structured artifacts. You also need to initialize a research-question.md file to define your topic and codebase context before starting the evidence synthesis process.

Can I use OpenAlex for evidence synthesis and decision-making documentation?

Yes, you can use OpenAlex to gather academic sources for evidence synthesis. The workflow integrates both academic and non-academic sources, documenting metadata and producing structured outputs like references.json for decision-making documentation.

What is the best way to document conflicting viewpoints during technology evaluation?

The best way to document conflicting viewpoints during technology evaluation is through conflict-seeking analysis, which explicitly surfaces opposing viewpoints within evidence cards to support robust architecture decisions and risk assessments across teams.

When should I not use a write-first evidence card workflow?

You should avoid the write-first evidence card workflow for research that does not require rigorous architecture decisions or technology evaluations, as it enforces structured metadata documentation and citation generation designed for comprehensive evidence synthesis.