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.
Install with Tessl CLI
npx tessl i github:K-Dense-AI/claude-scientific-skills --skill hypogenic72
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-crafted description that excels at completeness and distinctiveness, particularly with its explicit disambiguation from related skills. The trigger terms are natural and cover the domain well. The main weakness is that the specific capabilities could be more concrete - listing actual actions like 'generates hypotheses', 'validates against data', or 'produces statistical summaries' would strengthen it.
Suggestions
Add more concrete action verbs describing what the skill actually does (e.g., 'generates hypotheses from literature, tests them against data, produces statistical summaries')
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (LLM-driven hypothesis generation/testing on tabular datasets) and mentions some actions (explore hypotheses, combines literature insights with data-driven testing), but lacks specific concrete actions like 'generates hypotheses', 'runs statistical tests', or 'produces reports'. | 2 / 3 |
Completeness | Clearly answers both what (automated LLM-driven hypothesis generation and testing on tabular datasets, combines literature with data-driven testing) and when (explicit 'Use when you want to systematically explore hypotheses about patterns in empirical data'). Also includes helpful disambiguation for related skills. | 3 / 3 |
Trigger Term Quality | Includes good natural keywords users would say: 'hypothesis generation', 'hypothesis testing', 'tabular datasets', 'patterns', 'empirical data', 'deception detection', 'content analysis'. Also provides helpful disambiguation with related skills. | 3 / 3 |
Distinctiveness Conflict Risk | Excellent distinctiveness with explicit disambiguation from related skills ('For manual hypothesis formulation use hypothesis-generation; for creative ideation use scientific-brainstorming'). The 'automated LLM-driven' and 'tabular datasets' qualifiers create a clear niche. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides highly actionable, executable guidance with comprehensive code examples and clear CLI/API usage patterns. However, it is severely bloated with unnecessary explanations, marketing content, full academic citations, and repetitive information that wastes context window space. The workflow clarity suffers from missing validation checkpoints in multi-step processes.
Suggestions
Reduce content by 60-70% by removing: marketing language ('Proven Results', performance statistics), full BibTeX citations (link to papers instead), explanations of basic concepts, and the promotional K-Dense Web section
Move Repository Structure, Related Publications, and Additional Resources sections to separate reference files, keeping only essential quick-start content in SKILL.md
Add explicit validation steps to workflows, e.g., 'Verify GROBID is running: curl localhost:8070' before PDF processing, and 'Check output file exists and is valid JSON' after generation
Consolidate the three separate installation/dataset clone instructions into a single setup section to eliminate repetition
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at 500+ lines with extensive explanations Claude already knows (what PDFs are, how pip works, basic Python concepts). Includes marketing-style content ('Proven Results'), full BibTeX citations, and repetitive information across sections that could be dramatically condensed. | 1 / 3 |
Actionability | Provides fully executable code examples throughout - installation commands, Python API usage, CLI commands, and complete workflow examples. Code is copy-paste ready with specific parameters and file paths. | 3 / 3 |
Workflow Clarity | Multi-step workflows are listed (e.g., HypoRefine process, Example workflows) but lack explicit validation checkpoints. The GROBID setup and PDF processing workflow mentions steps but doesn't include verification that each step succeeded before proceeding. | 2 / 3 |
Progressive Disclosure | References external files (config_template.yaml, example datasets) but the main document is monolithic with extensive inline content that should be split. Repository structure and publications sections add bulk that could be separate reference files. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
87%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 14 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (655 lines); consider splitting into references/ and linking | Warning |
metadata_version | 'metadata.version' is missing | Warning |
Total | 14 / 16 Passed | |
- Reviewed
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.