hypogenic

Automated LLM-driven hypothesis generation and testing for tabular datasets; use when you need systematic exploration of empirical patterns (e.g., fraud detection, content analysis) and want to combine literature insights with data-driven hypothesis evaluation.

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Protocol Design/hypogenic/SKILL.md

Quality

Content

65%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Highly actionable content with copy-paste-ready CLI, Python, config, and data-schema examples, but weakened by missing validation checkpoints in the batch workflow and an orphaned, inlined config template that should be referenced from a bundle file.

Suggestions

Add explicit validation checkpoints to the workflow — e.g., verify hypotheses.json is well-formed and spot-check extract_label output against dataset labels before running full inference — since batch LLM operations currently lack verification steps.

Reference the bundled references/config_template.yaml from the Example Usage section instead of inlining a full config.yaml, so the existing bundle file is no longer orphaned and progressive disclosure improves.

Trim redundancy between the 'When to Use' and 'Key Features' sections and reduce the inlined config to essential fields to reclaim token budget.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with no heavy over-explanation of general concepts, but it inlines a full config.yaml that duplicates the bundled references/config_template.yaml and the 'When to Use' and 'Key Features' sections overlap, so it could be tightened; not lean enough for 4.	3 / 5
Actionability	Fully executable, copy-paste-ready guidance across common cases: complete CLI commands, a full Python API example, a full config.yaml, and a dataset JSON schema, matching the top anchor.	5 / 5
Workflow Clarity	The Example Usage is a clear 4-step sequence, but batch LLM operations (generating hypotheses, running inference on test splits) have no explicit validation checkpoints, so per the batch-operation cap workflow_clarity cannot exceed 3.	3 / 5
Progressive Disclosure	Section structure is reasonable, but the bundled references/config_template.yaml is never referenced from the body and its content is inlined instead, fitting the 'content that should be separate is inline / references not signaled' anchor rather than the well-split 4.	3 / 5
	Total	14 / 20 Passed

Description

83%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that explicitly states what the skill does and when to use it, with concrete example domains as natural triggers. It is specific and largely distinct, with only minor overlap risk and a few missing keyword synonyms.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('hypothesis generation and testing', 'combine literature insights with data-driven hypothesis evaluation') with only minor coverage gaps, fitting the 'several specific actions' anchor rather than the single-action anchor at 3.	4 / 5
Completeness	Explicitly answers both 'what' ('Automated LLM-driven hypothesis generation and testing for tabular datasets') and 'when' ('use when you need systematic exploration of empirical patterns...') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Good keyword coverage with natural domain phrases users would say ('fraud detection', 'content analysis', 'empirical patterns', 'tabular datasets'), though a few common synonyms/variants are missing, so it does not reach comprehensive 5.	4 / 5
Distinctiveness Conflict Risk	The LLM-driven hypothesis-generation/testing niche with literature integration is mostly distinct, but 'systematic exploration of empirical patterns on tabular datasets' has minor overlap risk with general data-analysis/EDA skills, keeping it below 5.	4 / 5
	Total	17 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Protocol Design/hypogenic/SKILL.md
Commit: 63c61d3

Reviewed: 10 hours ago

Table of Contents

Discovery Implementation Validation

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.