research-wiki

Organize papers, ideas, experiments, and claims into a graph-linked knowledge base.

2|Updated Aug 12, 2025
One-click install
npx skills add https://github.com/goupup-ai/miccai25 --skill research-wiki-goupup-ai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: research-wiki
Source: https://github.com/goupup-ai/miccai25/tree/main/ARIS/skills/research-wiki
Command: npx skills add https://github.com/goupup-ai/miccai25 --skill research-wiki-goupup-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill eliminates the loss of fragmented research knowledge that occurs after one-off literature reviews, removing the need to re-derive insights, paper details, and experimental outcomes every time you reference prior work.

Core Features & Use Cases

  • Structured Knowledge Accumulation: Automatically organizes papers, research ideas, experiments, and testable claims into a consistent, queryable format across the full research lifecycle.
  • Relationship Tracking: Maintains a graph of typed relationships between research entities (e.g., "extends", "contradicts", "tested_by") to map the evolution of ideas and evidence.
  • Anti-Repetition Guardrails: Tracks failed ideas and contradictions to prevent repeating past research mistakes, and includes capture filters to avoid storing transient operational noise as durable knowledge.
  • Use Case: For a vertebrae segmentation research project, you can ingest all related MICCAI papers, log tested ideas for frequency-enhanced feature refinement, track experiment results, and quickly query which prior work addresses gaps in low-frequency context aggregation.

Quick Start

Use the research-wiki skill to ingest the FMC-Net paper from arXiv ID 2506.23086 and link it to the existing research gap for low-frequency feature distortion in blurred medical images.

Frequently Asked Questions about research-wiki

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

FAQPage Schema
How do I build a persistent research knowledge base from literature reviews?

To build a persistent research knowledge base, you need a system that ingests papers and logs experiments into a graph-linked structure, preventing the loss of fragmented insights after one-off literature reviews. This ensures knowledge compounds continuously across the research lifecycle.

How does tracking relationships between papers prevent repeating failed research ideas?

Tracking typed relationships like 'extends' or 'contradicts' maps the evolution of ideas and evidence. This creates anti-repetition guardrails that log failed ideas and contradictions, preventing you from repeating past research mistakes during claim validation.

What is the best way to organize paper ingestion and experiment tracking for a segmentation project?

The best way to organize paper ingestion and experiment tracking is using a structured format that automatically links related work, logs tested ideas, and tracks experiment results. This allows you to query prior work addressing specific research gaps quickly.

Can I use a research wiki to validate testable claims from ingested papers?

Yes, you can use a research wiki to validate testable claims. It structures papers, ideas, and experiments into a queryable format across the full research lifecycle, applying capture filters to ensure only durable knowledge is stored rather than transient noise.

Does this research knowledge base work with existing literature review and ideation skills?

Yes, the research knowledge base provides integration hooks for existing literature review and ideation skills. This allows you to connect your persistent graph-linked data with your current academic or industry research workflows seamlessly.

Why do I need capture filters when logging research experiments into a knowledge base?

You need capture filters to implement anti-self-poisoning guardrails that prevent storing transient operational noise as durable knowledge. This ensures your experiment tracking maintains a high signal-to-noise ratio for accurate future claim validation.