From gr
Guides creation of precise, falsifiable research briefs via adversarial interviewing. Includes templates, anti-patterns, and evidence tiering for effective Deep Research agent use.
How this skill is triggered — by the user, by Claude, or both
Slash command
/gr:research-brief-builderThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Last updated: 2026-03-05 14:58 CET
Last updated: 2026-03-05 14:58 CET
Knowledge pack for constructing high-quality research briefs for the Gemini Deep Research Agent.
RESEARCH BRIEF
==============
Question: <precise, falsifiable research question>
Scope: <time period, domains, geography, depth>
Hypotheses to test: <H1, H2, ...>
Known context: <what we already know>
Output format: <structure, audience, tone>
Exclusions: <what to skip>
Cost: $2-5 | Time: 10-20 min
==============
When reviewing results, label claims:
npx claudepluginhub galbaz1/video-research-mcpGuides users through building structured research queries with topic, scope, and source quality selection before starting deep research.
Guides researchers through 5 Socratic segments—research question sharpening, expected mechanism, identifiability check, validation plan, risk register—outputting `.research/design_brief.md`. Domain-agnostic, for use after a topic is chosen.
Runs structured multi-step web research with source synthesis, citations, skeptical evaluation, and confidence/gap analysis. Supports native and dense/frontier modes.