research

Investigates questions against primary sources and records cited findings in Markdown files.

2|Updated Jul 6, 2026
One-click install
npx skills add https://github.com/NAMEWTA/learning-open-code --skill research-namewta
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: research
Source: https://github.com/NAMEWTA/learning-open-code/tree/main/translator/open-ai-skills/matt-pocock-skills/skills/engineering/research
Command: npx skills add https://github.com/NAMEWTA/learning-open-code --skill research-namewta

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Researching a topic often means reading large amounts of documentation, source code, and specifications, which blocks your main work. This Skill delegates that reading to a background agent so you can keep working while findings are gathered and documented. ## Core Features & Use Cases - Primary-source investigation: Traces every claim back to official documentation, source code, specifications, or first-party APIs rather than secondary summaries. - Cited Markdown reports: Writes findings into a single Markdown file where each claim is annotated with its owning source. - Convention-aware storage: Saves the report to the repository's existing notes location, or picks a sensible location and explains the choice. - Use Case: You need to understand how a third-party API's rate limiting works before integrating it. Launch the research agent, continue coding, and later read a Markdown report with every behavior cited to the official API docs. ## Quick Start Ask the agent to research how a specific library or API works using primary sources and save the cited findings as a Markdown note in this repository.

Frequently Asked Questions about research

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

FAQPage Schema
How do I delegate research to a background AI agent?▼

Launch the research skill with your question, and a background agent investigates it while you continue working. It reads primary sources and writes a cited Markdown report into your repository when finished.

What sources does an AI research agent use for technical questions?▼

It uses primary sources only: official documentation, source code, specifications, and first-party APIs. Each claim in the final report is traced back to the source that owns it, avoiding secondary summaries.

Where are research findings saved in a repository?▼

Findings are written to a single Markdown file saved wherever the repository already keeps notes, following existing conventions. If no convention exists, the agent picks a suitable location and states where the file was placed.

When should I not use a background research agent?▼

Avoid it for questions answerable from your own codebase context or when you need immediate interactive back-and-forth. It suits open-ended reading tasks, not quick lookups or decisions requiring your real-time judgment.