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.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./backend/cli/skills/chemistry/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.

The body is highly actionable with executable code and concrete examples, but it is verbose due to repeated commands and inlined reference material, and its batch workflows lack the validation checkpoints the rubric requires. Splitting reference material into bundle files and de-duplicating repeated commands would meaningfully raise the score.

Suggestions

De-duplicate repeated content: state the install command and dataset git-clone once in Installation and reference them elsewhere instead of repeating full command blocks in Quick Start, Python API Usage, and Workflow Examples; merge the duplicated Proven Results and Expected Outcomes metrics into a single section.

Add explicit validation checkpoints to the batch workflows, e.g. after hypothesis generation verify output/hypotheses.json is well-formed, and after inference confirm result/label formats match the dataset label field before reporting accuracy.

Move reference-heavy material out of SKILL.md into bundle files (e.g. references/publications.bib for BibTeX, references/repository_structure.md for the layout, references/python_api.md for the full API) and keep SKILL.md as a concise overview pointing to them; either create the advertised scripts/ and assets/ directories or remove those placeholder sections.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of basic-concept over-explanation, but noticeably padded by duplication: the install command recurs 3+ times, the dataset git-clone recurs 3+ times, the generation example repeats across Quick Start / Python API / Workflow Examples, and performance metrics appear twice (Proven Results and Expected Outcomes) alongside three full inlined BibTeX entries.	3 / 5
Actionability	Provides copy-paste-ready executable guidance throughout: CLI commands with flags, complete Python API snippets, a concrete config.yaml skeleton, a working extract_label regex implementation, and JSON dataset-format examples covering the common cases.	5 / 5
Workflow Clarity	Numbered sequences exist for literature processing and custom-task creation, but this batch-oriented skill (generating/testing many hypotheses) lacks explicit validation/verification checkpoints or feedback loops inside the workflows; per the rubric cap, batch skills without validation cannot exceed 3.	3 / 5
Progressive Disclosure	Section headers are well organized and the one in-body reference (references/config_template.yaml, a verified real file) is clearly signaled one level deep, but substantial reference material is inlined in SKILL.md (three BibTeX entries, full repository structure, complete Python API) that would be better split into separate files; the scripts/ and assets/ directories are described in the body but do not actually exist.	3 / 5
	Total	14 / 20 Passed

Description

87%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, third-person description that clearly states capabilities, provides explicit 'Use when' trigger guidance with concrete example domains, and proactively distinguishes itself from adjacent skills. Minor gains are possible by adding a few more synonyms or file-format triggers.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('hypothesis generation and testing', 'Combines literature insights with data-driven hypothesis testing', 'systematically explore hypotheses'), with only minor coverage gaps relative to the comprehensive 5-anchor.	4 / 5
Completeness	Explicitly answers both 'what' (automated generation, testing, literature+data combination) and 'when' ('Use when you want to systematically explore hypotheses about patterns in empirical data') with concrete trigger phrases and example domains.	5 / 5
Trigger Term Quality	Includes natural user-facing terms ('hypothesis generation', 'explore hypotheses', 'deception detection', 'content analysis', 'empirical data'), though a few synonyms/extensions are missing versus the comprehensive 5-anchor.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (LLM-driven hypothesis generation/testing on tabular data) and explicitly disambiguates from sibling skills ('For manual hypothesis formulation use hypothesis-generation; for creative ideation use scientific-brainstorming'), minimizing conflict risk.	5 / 5
	Total	18 / 20 Passed

Validation

81%

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 — 13 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/chemistry/hypogenic/SKILL.md
Commit: 3a6c3a9

Reviewed: 1 day 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.