research-source-planner

Build a deduplicated source manifest with URL normalization and ownership assignment.

Updated Jul 3, 2026
One-click install
npx skills add https://github.com/Reidond/Banshee --skill research-source-planner
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: research-source-planner
Source: https://github.com/Reidond/Banshee/tree/main/.claude/skills/research-source-planner
Command: npx skills add https://github.com/Reidond/Banshee --skill research-source-planner

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill prevents duplicated research effort and unreliable source selection by creating a curated, verified, and uniquely assigned source manifest for parallel deep research workflows.

Core Features & Use Cases

  • Source Curation & Validation: Gather candidate sources, evaluate relevance and authority using structured SIFT-based checks, and preserve audit trails for rejected or uncertain sources.
  • Deduplication & Ownership Assignment: Canonicalize URLs, identify true duplicates conservatively, and assign every surviving source to exactly one research owner or agent bucket.
  • Use Case: When preparing a multi-agent research project, use this Skill to organize scattered references into a source-manifest.md file where each researcher receives a distinct set of trusted sources without overlap.

Quick Start

Use the research-source-planner skill to build a deduplicated source manifest for my upcoming multi-agent research question about AI coding assistants.

Frequently Asked Questions about research-source-planner

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

FAQPage Schema
How do I prevent duplicated research effort across multiple agents analyzing the same sources?

You can prevent duplicated research effort by generating a deduplicated source manifest that canonicalizes URLs and assigns every trusted source to exactly one research owner, ensuring parallel agents work without overlap.

What is source curation and deduplication for parallel deep research workflows?

Source curation for parallel deep research involves gathering candidate references, applying SIFT-based quality checks, and conservatively removing true duplicates to produce a verified, uniquely assigned source manifest.

How do I build a deduplicated source manifest for a multi-agent research project?

To build a deduplicated source manifest, provide your candidate sources to the planner, which will normalize URLs, apply SIFT-based relevance checks, filter duplicates conservatively, and output a structured manifest file for ownership assignment.

Does this source planning approach handle URL normalization and uncertain source rejection?

Yes, this source planning approach handles URL normalization to identify true duplicates conservatively and preserves audit trails for uncertain or rejected sources during the SIFT-based quality evaluation process.

When should I use a structured source manifest instead of ad-hoc reference lists?

You should use a structured source manifest when preparing parallel deep research workflows that require strict source ownership assignment, evidence tracking, and reliable prevention of overlapping analysis across multiple agents.