research

Conducts multi-source technical research and produces a verified report with confidence-tiered findings.

Updated Mar 24, 2026
One-click install
npx skills add https://github.com/hanh-nd/agent-kit --skill research-hanh-nd
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: research
Source: https://github.com/hanh-nd/agent-kit/tree/main/plugins/agent-kit/.gemini/skills/research
Command: npx skills add https://github.com/hanh-nd/agent-kit --skill research-hanh-nd

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Engineers and architects making production decisions need research grounded in fetched sources rather than speculation or stale training knowledge. This Skill enforces source-backed claims, version specificity, and transparent handling of gaps between official documentation and practitioner reality. ## Core Features & Use Cases - Verified Multi-Source Research: Searches official docs, issue trackers, Q&A sites, and engineering blogs, then classifies every claim as Verified, Community-Reported, or Inferred. - Structured Research Report: Produces a report with executive summary, friction points, ecosystem audit, risk table, negative findings, and cited references. - Theory/Practice Gap Detection: Flags conflicts where official docs claim stability but practitioners report failures, presenting both sides. - Use Case: Before migrating a service to a new framework version, run this Skill to get a version-pinned report covering breaking changes, known friction points, ecosystem compatibility, and an execution roadmap. ## Quick Start Ask the agent to research whether a specific technology version is production-ready for your use case and save the findings as a research handoff.

Frequently Asked Questions about research

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

FAQPage Schema
How do I research whether a technology is production-ready?▼

Provide the exact technology and version, and the Skill searches official docs, issue trackers, and practitioner sources. It returns a report with confidence-tiered claims, friction points, risks, and a final recommendation.

How does the research report handle conflicting information?▼

Conflicts between official documentation and practitioner reports are classified as Theory/Practice Gaps. Both sides are presented side by side with sources, and the operational risk is flagged rather than silently resolved.

What sources does technical research use for verification?▼

It fetches full pages from primary sources plus practitioner channels like GitHub issues, Q&A sites, engineering blogs, and postmortems. Real-world risk claims require corroboration across multiple independent sources with URL, platform, and date recorded.

Can research proceed without a specified version?▼

No. Version-specific questions without a stated version trigger a hard stop requesting the missing context. The Skill pins every claim to exact versions and resolves 'latest' references via search before researching.

What happens when no data is found for a research question?▼

Missing data is recorded in the Negative Findings section with the exact query attempted, the implication, and what source would resolve it. Gaps never become silent assumptions or unsupported claims.