research

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

Updated Aug 11, 2026
One-click install
npx skills add https://github.com/Kunj-Sharma03/agent-contextify --skill research-kunj-sharma03
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: research
Source: https://github.com/Kunj-Sharma03/agent-contextify/tree/main/skills-main/skills/engineering/research
Command: npx skills add https://github.com/Kunj-Sharma03/agent-contextify --skill research-kunj-sharma03

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? It removes the manual legwork of digging through documentation, source code, and specs to answer technical questions, delegating the reading to a background agent while you keep working. ## 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 Output: Saves the report where the repo already keeps such notes, matching existing conventions. - Use Case: Ask how a specific API endpoint behaves; a background agent reads the official docs and source, then drops a cited Markdown summary into your repo's notes folder. ## Quick Start Ask the agent to research how a specific library or API works and save the cited 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 delegate research to a background agent?▼

Describe the question you want answered and the agent investigates it against primary sources in the background. It writes the findings to a cited Markdown file in your repo while you continue working on other tasks.

What sources does the research agent use?▼

It relies on primary sources: official documentation, source code, specifications, and first-party APIs. Every claim is followed back to the source that owns it rather than trusting secondary write-ups or blog posts.

Where are the research findings saved?▼

Findings are written to a single Markdown file saved where the repository already keeps such notes. If no convention exists, the agent picks a sensible location and tells you where it placed the file.

Does the research output include citations?▼

Yes, each claim in the Markdown report cites its source. This lets you verify statements directly against the official docs, code, or spec they came from.

When should I not use a background research agent?▼

Avoid it for questions answerable from your own codebase context or requiring real-time interaction, since it is designed for reading-heavy investigation of external primary sources rather than local code edits.