One-click install
npx skills add https://github.com/christophevg/c3 --skill research-christophevg
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: research
Source: https://github.com/christophevg/c3/tree/main/skills/research
Command: npx skills add https://github.com/christophevg/c3 --skill research-christophevg

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It helps you gather accurate information on any subject while producing a fully traceable set of sources and citations, so you can write credible reports instead of relying on unverified notes.

Core Features & Use Cases

  • Comprehensive research with provenance: Organizes work into a dated topic folder with an indexed SOURCES.md, fetched content snapshots, and explicit citations.
  • WebSearch + WebFetch workflow: Enforces immediate recording of each search and each fetch, with a minimum of two sources and a strict fetch persistence rule to fetched/.
  • Evidence-driven reporting: Produces a structured README research report with executive summary, corroboration, resource comparison (when sources disagree), and key takeaways.
  • Avoids wrong scope: Steers Python package/library research to the dedicated find-package skill paths instead of duplicating effort.

Quick Start

Use the research skill to produce a cited literature- or web-style investigation for the topic “investigate best practices for X” with at least two distinct sources and a final report that links each claim to its provenance.

Frequently Asked Questions about research

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

FAQPage Schema
How do I conduct web research with source citations and provenance tracking?

A literature review with provenance tracks sources by immediately recording each search and fetch event into SOURCES.md, saving all fetched content snapshots into a dedicated folder, and enforcing a minimum of two corroborating sources for evidence-based reporting.

How do I generate an evidence-based report from web searches?

An evidence-based report is generated by structuring fetched web content into a final README featuring an executive summary, key takeaways, resource comparisons for disagreeing sources, and explicit citations linking claims to provenance.

What is provenance tracking for technology investigations?

Provenance tracking for technology investigations is the process of saving every WebFetch verbatim into a fetched folder and maintaining a SOURCES.md index, ensuring every conclusion in the final report is fully traceable to its original web source.

Can I use this approach to research Python packages and libraries?

Researching Python packages and libraries should be directed to dedicated find-package skill paths instead of this general research workflow, avoiding duplicated effort and ensuring the correct scope for technology investigations.

What are the minimum source requirements for traceable literature reviews?

Traceable literature reviews require a strict minimum of two distinct sources, with immediate recording of each search and fetch event into SOURCES.md, to guarantee corroboration and prevent reliance on unverified notes.