research

Investigate questions against primary sources and write cited findings to Markdown files.

Updated Jul 16, 2026
One-click install
npx skills add https://github.com/The-Focus-AI/walking-thoughts --skill research-the-focus-ai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: research
Source: https://github.com/The-Focus-AI/walking-thoughts/tree/main/.agents/skills/research
Command: npx skills add https://github.com/The-Focus-AI/walking-thoughts --skill research-the-focus-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Delegating research to a background agent lets you keep working while documentation, API facts, and technical questions are investigated against trustworthy sources instead of secondhand summaries. ## Core Features & Use Cases - Primary-source investigation: Traces every claim back to official docs, source code, specs, or first-party APIs rather than secondary write-ups. - Cited Markdown output: Writes findings to a single Markdown file with a source citation for each claim. - Convention-aware placement: Saves the file where the repo already keeps such notes, matching existing conventions. - Use Case: Ask how a third-party API handles rate limits; a background agent reads the official documentation and source, then delivers a cited Markdown summary in your repo while you continue coding. ## Quick Start Research how Clerk handles session token refresh and save the cited findings as a Markdown note in this repo.

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 agent?

Invoke the research skill with your question, and it spins up a background agent that investigates primary sources while you keep working. The agent writes cited findings to a Markdown file in your repository.

What sources does the research agent use?

The agent investigates primary sources only: official documentation, source code, specifications, and first-party APIs. It follows every claim back to the source that owns it rather than relying on secondary write-ups.

Where are research findings saved in the repo?

Findings are saved as a single Markdown file where the repository already keeps such notes, matching existing conventions. If no convention exists, the agent picks a sensible location and tells you where.

Does the research output include citations?

Yes, each claim in the Markdown findings file cites its source. This makes it possible to verify every statement against the original documentation or code.

When should I not use a background research agent?

Avoid it for questions answerable from code already in your local context or when you need an immediate inline answer. The background approach suits deeper investigations where parallel work matters more than instant results.