research-prompt

Convert implementation prompts into research prompts for codebase exploration.

3|Updated Apr 10, 2026
One-click install
npx skills add https://github.com/Visma-Tech-LT/ai-workshop-marketplace --skill research-prompt-visma-tech-lt
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: research-prompt
Source: https://github.com/Visma-Tech-LT/ai-workshop-marketplace/tree/main/plugins/sdw/skills/research-prompt
Command: npx skills add https://github.com/Visma-Tech-LT/ai-workshop-marketplace --skill research-prompt-visma-tech-lt

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

When you start with a “do X” request, you can end up coding against assumptions instead of the codebase’s real structure and conventions, leading to rework and drift.

Core Features & Use Cases

  • Transforms solution prompts into research prompts that explicitly seek current-state understanding instead of implementation.
  • Guides thorough exploration by asking for concrete file locations, patterns, dependencies, and real usage examples.
  • Reduces solution bias by removing presumptive implementation details and focusing on evidence from the repository.

Quick Start

Use the research-prompt skill to rewrite your original “add/fix/change” request into a research-focused instruction you can run after reviewing the existing codebase.

Frequently Asked Questions about research-prompt

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

FAQPage Schema
How do I convert a build request into a codebase research prompt?

To convert a build request into a codebase research prompt, you rewrite the implementation-oriented instructions into research-focused queries that seek current-state understanding, concrete file locations, and real usage examples.

Why should I explore codebase patterns before implementing a new feature?

Exploring codebase patterns before implementing a new feature prevents coding against assumptions, which leads to rework and drift. Research-focused prompts direct the agent toward existing dependencies and cross-component relationships for evidence-based changes.

What is solution bias in spec-driven development and how do I remove it?

Solution bias in spec-driven development occurs when presumptive implementation details override actual repository conventions. You remove it by transforming your request into a research prompt that focuses on discovering existing files, patterns, and dependencies instead of assuming a solution.

How do I map dependencies and cross-component relationships before coding?

To map dependencies and cross-component relationships before coding, generate a structured research prompt that explicitly asks for concrete file locations, current usage conventions, and dependency mappings to understand the codebase's real structure.

Does transforming prompts into research queries work for fixing existing code?

Transforming prompts into research queries works for fixing existing code by shifting the focus from immediate changes to discovering current patterns, file locations, and real usage examples, ensuring fixes align with the actual codebase structure.