CtrlK
BlogDocsLog inGet started
Tessl Logo

hypothesis-generation

Structured hypothesis formulation from observations. Use when you have experimental observations or data and need to formulate testable hypotheses with predictions, propose mechanisms, and design experiments to test them. Follows scientific method framework. For open-ended ideation use scientific-brainstorming; for automated LLM-driven hypothesis testing on datasets use hypogenic.

78

1.67x
Quality

67%

Does it follow best practices?

Impact

99%

1.67x

Average score across 3 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./scientific-skills/hypothesis-generation/SKILL.md
SKILL.md
Quality
Evals
Security

Evaluation results

100%

76%

Post-Sepsis Cognitive Impairment Hypothesis Report

LaTeX report structure and box environments

Criteria
Without context
With context

Style package loaded

0%

100%

Hypothesis box environments used

0%

100%

newpage before hypothesis boxes

0%

100%

Prediction box used

0%

100%

Comparison box used

0%

100%

Summary box used

0%

100%

XeLaTeX compilation

0%

100%

bibtex step in compilation

100%

100%

Correct hypothesis count

100%

100%

All four appendices present

0%

100%

citep citation format

100%

100%

XeLaTeX directive or template reference

0%

100%

100%

33%

Coral Bleaching Timing Anomaly — Hypothesis Report

Hypothesis quality criteria evaluation

Criteria
Without context
With context

Testability assessed

100%

100%

Falsifiability assessed

75%

100%

Parsimony assessed

37%

100%

Explanatory power assessed

87%

100%

Scope assessed

62%

100%

Consistency assessed

100%

100%

Novelty assessed

12%

100%

Quality comparison table present

80%

100%

Mechanistic explanations

100%

100%

Quantitative predictions

50%

100%

Quality assessment in appendix

0%

100%

Strengths and weaknesses noted

100%

100%

97%

9%

Wildfire Smoke and Influenza Severity — Hypothesis Report

Literature search strategy and citation standards

Criteria
Without context
With context

PubMed search documented

100%

100%

Web search documented

100%

100%

Broad-to-specific search progression

100%

100%

50+ total references

100%

100%

Comprehensive appendix citations

0%

90%

citep format used

100%

100%

Multiple hypothesis types covered

100%

100%

Review articles cited

100%

100%

Search queries documented

100%

100%

Evidence synthesis noted

77%

77%

Repository
K-Dense-AI/claude-scientific-skills
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

Table of Contents

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.