skills.rest
smartmarbles
smartmarblesCOMMUNITY
Explore all skills by this author →
GitHub

conduct-research

Scope research requests and deliver structured, source-backed findings in four sections.

4|Updated Apr 2, 2026
Search Tags:#research#evaluation#handoff#scoop#source-corroboration#conversational-delivery
One-click install
npx skills add https://github.com/smartmarbles/helm --skill conduct-research
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: conduct-research
Source: https://github.com/smartmarbles/helm/tree/main/.github/skills/conduct-research
Command: npx skills add https://github.com/smartmarbles/helm --skill conduct-research

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

SCOOP provides a rigorous, in-conversation research framework that delivers structured, source-backed findings while avoiding on-disk deliverables unless explicitly handed off to QUILL.

Core Features & Use Cases

  • Scope requests before gathering to define the question, dimensions, and depth.
  • Prioritize primary sources and reputable secondary analysis; maintain explicit corroboration discipline.
  • Deliver findings in the four-section format: Executive Summary, Key Findings, ## What Most People Miss, Recommendations; flag confidence and mark unknowns where needed.
  • Hand off to QUILL for persisting results as a written file when required.

Quick Start

Scope the request, identify dimensions, plan sources, then gather and structure the in-conversation report.

Frequently Asked Questions about conduct-research

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

FAQPage Schema
How do I conduct in-conversation research with source-backed findings?▼

In-conversation research structures source-backed findings by scoping requests, prioritizing primary sources, and delivering a four-section report with explicit confidence flags and unknowns marked.

What is the structured format for delivering research findings in a chat?▼

Structured research delivery uses a four-section format: Executive Summary, Key Findings, What Most People Miss, and Recommendations, ensuring source corroboration and explicit confidence flags.

How do I evaluate technology or roles using a structured research framework?▼

Evaluating technology or roles requires scoping the question, defining dimensions, planning primary sources, and structuring the in-conversation report with independent corroboration and confidence flags.

How do I persist in-conversation research results into a written file?▼

Persisting in-conversation research results into a written file requires handing off the structured findings to QUILL, which manages on-disk deliverables when explicitly requested.

Can I use this structured research approach for scope-limited requests without on-disk files?▼

Structured research operates entirely in-conversation without on-disk deliverables, enforcing scope, sourcing discipline, and source corroboration unless explicitly handed off to QUILL.

When should I flag unknowns during source corroboration in research?▼

Flag unknowns during source corroboration when primary sources cannot independently verify findings, ensuring explicit confidence flags are maintained throughout the structured research delivery.

Related Skills

Explore More Education & Research Skills→
yu13130122297yu13130122297

scout

Identify uncertainties in research framing, datasets, metrics, and baselines.

Community
Intermediate
danalexilewisdanalexilewis
1

report

Generate structured reports from conversation findings and save them to a reports/ directory.

Community
Intermediate
myapihqmyapihq
83

my-storage-api

Upload files or ingest public URLs into a CDN-backed storage system.

Official
Intermediate
vasilievyakovvasilievyakov
17

triangulate

Cross-check claims against three or more independent sources and produce a structured verdict.

Community
Intermediate