research

Dispatch parallel sub-agents to synthesize community and official source findings.

2|1|Updated Feb 9, 2026
One-click install
npx skills add https://github.com/costa-marcello/skillkit --skill research-costa-marcello
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: research
Source: https://github.com/costa-marcello/skillkit/tree/main/skills/research
Command: npx skills add https://github.com/costa-marcello/skillkit --skill research-costa-marcello

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

Researching topics often requires consulting many sources across communities and official docs, compiling findings, and reconciling conflicting perspectives. This Skill orchestrates a disciplined, multi-agent research workflow to deliver a ready-to-use, two-sided synthesis.

Core Features & Use Cases

  • Dispatches 6-10 parallel sub-agents across community discussions and official sources to cover community sentiment and official documentation.
  • Produces a two-sided report that contrasts community findings with official findings, including cross-reference analysis and an optional web-coverage workflow.
  • Use cases include deep topic research, feature/tool comparisons, sentiment analysis, and staying updated on official changes.

Quick Start

Provide a topic to start the deep research workflow and the skill will dispatch 6-10 sub-agents across community and official sources to return a two-sided report.

Frequently Asked Questions about research

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

FAQPage Schema
How do I conduct in-depth topic research across both community discussions and official documentation?

In-depth topic research across community discussions and official documentation is conducted by dispatching 6-10 parallel sub-agents to assess sources. This mechanism contrasts community sentiment with official findings to deliver a structured two-sided report.

What is the best way to generate a two-sided report comparing community sentiment with official sources?

Generating a two-sided report comparing community sentiment with official sources is achieved by running parallel sub-agents that cross-reference findings. This approach contrasts community discussions against official documentation and returns a structured synthesis with supporting metrics.

Can I use parallel agents for feature comparisons and sentiment analysis without manual source compilation?

Parallel agents support feature comparisons and sentiment analysis without manual source compilation by automatically dispatching across community and official sources. They reconcile conflicting perspectives and return a structured synthesis ready for immediate use.

How do I start a deep research workflow and get a follow-on prompt for further investigation?

Starting a deep research workflow requires providing a topic to trigger parallel sub-agents. The workflow assesses community and official sources, delivering a two-sided report that includes a follow-on prompt ready for continued investigation.

Does this multi-agent research workflow require any external dependencies or specific environment setup?

This multi-agent research workflow requires no external dependencies or specific environment setup. It operates independently by dispatching sub-agents to evaluate community discussions and official documentation, returning a structured synthesis.

What are the limitations of using automated sub-agents for reconciling conflicting perspectives in research?

Limitations of using automated sub-agents for reconciling conflicting perspectives include relying entirely on accessible community discussions and official documentation. The resulting two-sided synthesis is constrained by the coverage and accuracy of those assessed sources.