research

Investigates questions against primary sources and writes cited findings to a Markdown file.

Updated Jun 26, 2026
One-click install
npx skills add https://github.com/dulltackle/kangkang-skills --skill research-dulltackle
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: research
Source: https://github.com/dulltackle/kangkang-skills/tree/main/research
Command: npx skills add https://github.com/dulltackle/kangkang-skills --skill research-dulltackle

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Getting accurate answers about a topic, API, or library usually means reading official documentation and source code yourself, which interrupts your current work. This Skill delegates that reading to a background agent that consults primary sources and records the findings in the repository. ## 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 reports: Writes findings to a single Markdown file with a source citation for each claim. - Convention-aware storage: Saves the report where the repo already keeps such notes, matching existing conventions or choosing a sensible location. - Use Case: While implementing a feature, ask how a third-party API handles rate limits; the background agent reads the official API docs and source, then saves a cited summary you can reference later. ## Quick Start Ask the agent to research how a specific library or API feature works using official documentation and save the findings as a Markdown note in the repo.

Frequently Asked Questions about research

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

FAQPage Schema
How do I research a topic using primary sources with an AI agent?

Invoke the research skill with your question, and it spins up a background agent that reads official docs, source code, specs, and first-party APIs. The agent writes findings to a Markdown file with a citation for each claim.

How to delegate documentation reading to a background agent?

State the question you want answered and let the skill launch a background agent to do the reading. You keep working while it investigates, and the results appear as a Markdown note in the repository.

Where does the research skill save its findings?

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

Does the research agent cite its sources?

Yes, every claim in the output report includes a citation to the primary source that owns it. The agent follows each claim back to official documentation, source code, or specifications rather than secondary write-ups.

When should I not use a background research agent?

Avoid it for questions answerable from your current context or requiring real-time interaction, since the agent works asynchronously. It is best suited for open-ended investigation of docs, APIs, and specs rather than quick lookups.