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

Passed

No findings from the security scan

Quality

Content

72%

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

The body is well-structured with strong executable examples and clean progressive disclosure to real reference files. Its main weaknesses are conciseness (the 'When to Use Which Tool' and ancillary sections duplicate earlier material) and the absence of explicit validation/feedback checkpoints in multi-step workflows.

Suggestions

Remove or condense the 'When to Use Which Tool' section since each capability already has a 'Use for' block in Core Capabilities; this duplication inflates token cost.

Add explicit validation checkpoints to the universe-building and tokenization workflows (e.g. 'Verify tokenization coverage >80% before training; if below, rebuild universe'), turning implicit best-practice notes into fix-retry loops.

Trim 'Related Projects' and 'Performance Considerations' to only non-obvious, geniml-specific guidance that Claude would not infer.

Dimension	Reasoning	Score
Conciseness	Largely lean with executable code, but 'When to Use Which Tool' repeats the per-capability 'Use for' bullets already in Core Capabilities, and Best Practices/Performance/Related Projects add content Claude largely already knows.	2 / 3
Actionability	Provides fully executable Python and concrete CLI commands with real flags (e.g. 'geniml universe build cc --cutoff 5 --merge 100 --filter-size 50'), copy-paste ready.	3 / 3
Workflow Clarity	Workflows are numbered and sequenced (scATAC pipeline steps 1-5), but lack explicit validation checkpoints or fix-retry feedback loops for batch operations like universe building, which the rubric caps at 2.	2 / 3
Progressive Disclosure	Clear overview with well-signaled one-level-deep references to verified files (references/region2vec.md, bedspace.md, scembed.md, consensus_peaks.md, utilities.md), content appropriately split.	3 / 3
	Total	10 / 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 strong: it is written in third person, names concrete capabilities with specific tool names, and provides an explicit 'Use when...' trigger clause covering both what and when. It is a tight, low-conflict statement of the skill's purpose.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions ('training region embeddings (Region2Vec, BEDspace)', 'single-cell ATAC-seq analysis (scEmbed)', 'building consensus peaks (universes)') tied to named tools.	3 / 3
Completeness	Explicitly answers what (embeddings, scATAC analysis, consensus peaks) and when ('This skill should be used when working with genomic interval data...Use for...').	3 / 3
Trigger Term Quality	Good coverage of natural terms a user would say: 'BED files', 'single-cell ATAC-seq', 'scATAC-seq', 'chromatin accessibility datasets'.	3 / 3
Distinctiveness Conflict Risk	A clearly defined niche (genomic interval ML) with distinct triggers (BED files, scATAC-seq) unlikely to fire for unrelated skills.	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
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/ml-training/geniml/SKILL.md
Commit: 52845c3

Reviewed: about 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.