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

82%

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

Quality

Content

65%

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

The skill body is highly actionable with concrete code and commands, but it reads like a project README: verbose prose, marketing-style sections, and a large inline footprint rather than a lean overview pointing to real bundle files.

Suggestions

Trim README-style sections ("Key Features", "Proven Results", "Expected Outcomes", the K-Dense Web promotion) and de-duplicate the installation and Python API content shown in both Quick Start and dedicated sections to recover token budget.

Add explicit validation/verification checkpoints to the generation and inference workflows (e.g., confirm hypotheses.json is non-empty and labels match the dataset format before running inference) to support error recovery.

Move the full config reference, repository structure, and publication/BibTeX material into reference files under references/, and actually create the referenced config_template.yaml plus scripts/ and assets/ directories so progressive disclosure points to real, one-level-deep resources.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete commands and code, but it is padded with README-style prose ("Key Features", "Proven Results", "Expected Outcomes"), repeated installation/API content, and a lengthy promotional K-Dense Web section that does not earn its tokens.	2 / 3
Actionability	Provides fully executable CLI commands, complete Python API snippets with imports, a concrete config.yaml example with real placeholders, and a working extract_label implementation — copy-paste ready.	3 / 3
Workflow Clarity	Multi-step workflows are sequenced (Literature Processing, Creating Custom Tasks, numbered Examples), but there are no explicit validation/verification checkpoints or error-recovery loops for the generation and inference batch operations, which caps the score at 2.	2 / 3
Progressive Disclosure	Sections are present and navigation is implied, but the body is a ~650-line monolith with inline content (full config reference, repository structure, BibTeX citations) that should be split out, and it references a config_template.yaml plus scripts/ and assets/ directories that do not exist on disk.	2 / 3
	Total	9 / 12 Passed

Description

100%

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

The description is specific, trigger-rich, complete, and explicitly distinct from neighboring skills. It is one of the stronger descriptions in the reference set.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "hypothesis generation and testing", "systematically explore hypotheses", and "Combines literature insights with data-driven hypothesis testing" — matching the top anchor for specific concrete actions.	3 / 3
Completeness	Explicitly answers both what (generation and testing on tabular datasets) and when ("Use when you want to systematically explore hypotheses about patterns in empirical data"), satisfying the explicit-trigger requirement for a top score.	3 / 3
Trigger Term Quality	Covers natural user-facing terms ("hypotheses", "empirical data", "deception detection", "content analysis") plus routing triggers ("manual hypothesis formulation", "creative ideation"), giving good coverage of phrases a user would actually say.	3 / 3
Distinctiveness Conflict Risk	Provides explicit disambiguation from siblings ("For manual hypothesis formulation use hypothesis-generation; for creative ideation use scientific-brainstorming"), giving a clear niche unlikely to trigger the wrong skill.	3 / 3
	Total	12 / 12 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
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	13 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/bio/hypogenic/SKILL.md
Commit: df37802

Reviewed: about 2 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.