brainstorm

Determine extraction types for converting unstructured documents into structured knowledge.

3.3k|386|Updated Jan 7, 2026

Search Tags:#requirements #data-modeling #graph #knowledge-extraction #schema-design #hypergraph #template-design

Ready to run

npx skills add https://github.com/yifanfeng97/Hyper-Extract --skill brainstorm-yifanfeng97

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: brainstorm
Source: https://github.com/yifanfeng97/Hyper-Extract/tree/main/hyperextract-skills/brainstorm
Command: npx skills add https://github.com/yifanfeng97/Hyper-Extract --skill brainstorm-yifanfeng97

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Helps teams and users quickly decide which extraction type to use when converting unstructured documents into structured knowledge, reducing trial-and-error and ambiguity in template design.

Core Features & Use Cases

Decision Tree Guidance: Walks through whether data is a record, list, set, graph, hypergraph, or spatio-temporal structure and suggests the appropriate extraction type.
Guided Requirement Questions: Prompts about input sources, key fields, entity granularity, relations, and temporal/spatial needs to surface design constraints.
Design Draft Output: Produces a concise design draft (fields, entities, relations, identifiers, and notes) that can be handed to a downstream designer.
Use Case: When preparing extraction templates for event logs or multi-entity reports, use this Skill to choose between graph, hypergraph, or temporal representations and get a starter spec.

Quick Start

Ask the skill to review your source document and recommend an extraction type and an initial design draft.

Frequently Asked Questions about brainstorm

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

FAQPage Schema

How do I choose the right extraction type for converting unstructured documents into structured knowledge?▼

To choose the right extraction type for unstructured documents, evaluate whether your data represents a record, list, set, graph, hypergraph, or spatio-temporal structure. A decision tree helps determine the correct model based on entity granularity and relations.

What is the difference between graph and hypergraph data modeling for knowledge extraction?▼

Graph data modeling connects entities through binary relations, while hypergraph data modeling allows relations that connect multiple entities simultaneously. Choosing between them depends on whether your template design requires grouping multi-entity event logs or complex relational sets.

How do I design an extraction template for multi-entity reports?▼

Designing an extraction template for multi-entity reports requires answering guided questions about input sources, key fields, and entity granularity. This produces a design draft capturing input/output definitions and type-specific fields for downstream schema design.

When do I need spatio-temporal extraction types for document parsing?▼

You need spatio-temporal extraction types for document parsing when your source data has inherent temporal and spatial constraints. Identifying these needs during requirement clarification ensures the resulting schema design accurately captures dynamic geographical or time-based events.

Can I get an initial schema design draft from my source documents?▼

You can generate an initial schema design draft by providing your source documents for review. The process identifies key fields, entities, relations, and identifiers, outputting a concise specification ready for downstream designers to implement.