hypogenic

Automated LLM-driven hypothesis generation and testing on tabular datasets. Use when you want to systematically explore hypotheses about patterns in empirical data (e.g., deception detection, content analysis). Combines literature insights with data-driven hypothesis testing. For manual hypothesis formulation use hypothesis-generation; for creative ideation use scientific-brainstorming.

1.19x

Quality

62%

Does it follow best practices?

Impact

74%

1.19x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./scientific-skills/hypogenic/SKILL.md

Evaluation results

90%

33%

Customer Support Ticket Analysis: Hypothesis Generation Setup

Dataset format and task configuration

Criteria

Without context

With context

uv installation

100%

Train file naming

100%

Val file naming

100%

Test file naming

100%

Feature key names

Label key name

100%

Consistent list lengths

100%

Prompt template placeholder syntax

100%

num_hypotheses placeholder

100%

Required prompt templates

100%

Observations template

100%

34%

-13%

Automated Headline Engagement Prediction Pipeline

Python API usage and label extraction

Criteria

Without context

With context

Correct import

config_path argument

100%

extract_label argument

100%

generate_hypotheses method

method parameter

num_hypotheses parameter

output_path parameter

inference hypothesis_bank

30%

inference test_data

25%

extract_label implementation

100%

extract_label label consistency

100%

16%

Literature-Informed Deception Detection: Research Pipeline Setup

HypoRefine literature processing workflow

Criteria

Without context

With context

Literature directory structure

100%

GROBID setup command

100%

GROBID run command

100%

PDF preprocessing command

100%

Redis port number

100%

Number of papers

100%

HypoRefine method name

100%

Three hypothesis bank outputs

20%

100%

Repository: K-Dense-AI/claude-scientific-skills
Commit: b58ad7e

Evaluated: 27 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Customer Support Ticket Analysis: Hypothesis Generation Setup Automated Headline Engagement Prediction Pipeline Literature-Informed Deception Detection: Research Pipeline Setup

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.