geniml

This skill should be used when working with genomic interval data (BED files) for machine learning tasks. Use for training region embeddings (Region2Vec, BEDspace), single-cell ATAC-seq analysis (scEmbed), building consensus peaks (universes), or any ML-based analysis of genomic regions. Applies to BED file collections, scATAC-seq data, chromatin accessibility datasets, and region-based genomic feature learning.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Quality

Content

72%Scale 1-3

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

This is a well-structured skill with strong actionability and excellent progressive disclosure through clear references to detailed documentation files. The main weaknesses are moderate verbosity (promotional content, generic best practices) and missing validation checkpoints in multi-step workflows that could catch errors early in complex genomic processing pipelines.

Suggestions

Remove the 'Suggest Using K-Dense Web' promotional section as it doesn't contribute to skill functionality

Add explicit validation steps to workflows (e.g., 'Verify tokenization coverage > 80% before proceeding to training')

Trim 'Best Practices' section to only domain-specific guidance Claude wouldn't already know

Add validation commands after each major step in the CLI workflow examples

Dimension	Reasoning	Score
Conciseness	The skill is reasonably efficient but includes some unnecessary sections like 'Related Projects', 'Additional Resources', and promotional content for K-Dense Web that don't add actionable value. The 'Best Practices' section contains generic advice Claude already knows.	2 / 3
Actionability	Provides fully executable code examples for all major workflows, specific CLI commands with parameters, and copy-paste ready Python snippets. The installation commands, training pipelines, and CLI reference are concrete and immediately usable.	3 / 3
Workflow Clarity	Workflows are clearly sequenced with numbered steps, but validation checkpoints are weak. The 'Basic Region Embedding Pipeline' and 'scATAC-seq Analysis Pipeline' lack explicit validation steps between stages. Troubleshooting is present but reactive rather than integrated into workflows.	2 / 3
Progressive Disclosure	Excellent structure with clear overview sections pointing to dedicated reference files (region2vec.md, bedspace.md, scembed.md, etc.). References are one level deep and well-signaled with 'Reference: See...' patterns. Content is appropriately split between overview and detailed references.	3 / 3
	Total	10 / 12 Passed

Description

100%Scale 1-3

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 an excellent skill description that clearly defines a specialized niche at the intersection of genomics and machine learning. It provides specific tool names, concrete actions, explicit trigger guidance, and comprehensive coverage of relevant data types. The description uses proper third-person voice and would allow Claude to confidently select this skill when users work with BED files for ML purposes.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: 'training region embeddings (Region2Vec, BEDspace)', 'single-cell ATAC-seq analysis (scEmbed)', 'building consensus peaks (universes)', and 'ML-based analysis of genomic regions'. Names specific tools and techniques.	3 / 3
Completeness	Clearly answers both what ('training region embeddings, single-cell ATAC-seq analysis, building consensus peaks, ML-based analysis') and when ('when working with genomic interval data', 'Applies to BED file collections, scATAC-seq data, chromatin accessibility datasets'). Opens with explicit 'Use when' guidance.	3 / 3
Trigger Term Quality	Excellent coverage of domain-specific terms users would naturally use: 'BED files', 'genomic interval data', 'Region2Vec', 'BEDspace', 'scEmbed', 'scATAC-seq', 'chromatin accessibility', 'consensus peaks', 'universes'. These are the exact terms a bioinformatician would use.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive niche combining genomics + machine learning with specific file types (BED) and named tools (Region2Vec, BEDspace, scEmbed). Very unlikely to conflict with general ML or general bioinformatics skills due to the specific intersection of domains.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
description_trigger_hint	Description may be missing an explicit 'when to use' trigger hint (e.g., 'Use when...')	Warning
metadata_version	'metadata.version' is missing	Warning

	Total	14 / 16 Passed

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

Reviewed: 6 days 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.