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.
8.3
Rating
0
Installs
AI & LLM
Category
Exceptionally comprehensive skill for automated hypothesis generation and testing on tabular datasets. The description clearly articulates three distinct methods (HypoGeniC, HypoRefine, Union) and when to use each. The documentation provides extensive task knowledge including installation, dataset formatting, CLI/API usage, workflow examples, and troubleshooting. Structure is excellent with logical progression from quick start to advanced topics, though the single-file approach is lengthy (acceptable given complexity). The skill addresses a genuinely novel research need - systematic hypothesis generation from empirical data using LLMs - that would be extremely token-intensive and difficult for a CLI agent to replicate without this framework. Strong support for literature integration, caching, and iterative refinement demonstrates production-ready maturity. The skill is well-positioned between manual hypothesis formulation and creative brainstorming tools, with clear differentiation. Minor improvements could include more explicit decision trees for method selection and condensed quick-reference sections.
K-Dense-AI
Skill Author
Loading SKILL.md…
