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.
58
67%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/geniml/SKILL.mdQuality
Discovery
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.
This is a strong, well-crafted skill description that clearly defines a specialized niche at the intersection of genomics and machine learning. It names specific tools, data types, and use cases, making it easy for Claude to select appropriately. The explicit 'Use when' and 'Applies to' clauses provide clear trigger guidance.
| 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. These are concrete, named tools and tasks. | 3 / 3 |
Completeness | Clearly answers both 'what' (training region embeddings, scATAC-seq analysis, building consensus peaks, ML-based genomic analysis) and 'when' with explicit triggers ('Use for...', 'Applies to BED file collections, scATAC-seq data, chromatin accessibility datasets'). Opens with an explicit 'should be used when' clause. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms a bioinformatics user would say: 'BED files', 'Region2Vec', 'BEDspace', 'scEmbed', 'scATAC-seq', 'chromatin accessibility', 'genomic regions', 'region embeddings', 'consensus peaks', 'universes'. These are the exact terms domain users would use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche combining genomic interval data (BED files) with machine learning. The specific tool names (Region2Vec, BEDspace, scEmbed) and domain-specific terms (chromatin accessibility, consensus peaks) make it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is comprehensive in scope but suffers from significant verbosity — it tries to be both an overview and a detailed reference simultaneously, defeating the purpose of its own progressive disclosure structure. The code examples provide reasonable actionability but may not reflect actual API signatures, and workflows lack the validation checkpoints needed for data-intensive ML pipelines. The content would benefit greatly from aggressive trimming, moving detailed content to the referenced files, and adding explicit validation steps.
Suggestions
Cut the SKILL.md body by at least 50% — move CLI reference, best practices, troubleshooting, 'When to Use Which Tool', and 'Related Projects' sections into the referenced files or a separate guide, keeping only a concise overview with one representative code example.
Add explicit validation checkpoints to workflows, e.g., 'Verify tokenization coverage > 80% before proceeding to training' with the actual command to check coverage.
Verify and correct the Python API examples against the actual geniml package — ensure import paths, function signatures, and parameter names match the real library.
Create the referenced bundle files (references/region2vec.md, etc.) so the progressive disclosure structure actually works, and remove the duplicated detail from SKILL.md.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~250+ lines. It includes extensive 'When to Use Which Tool' decision trees, 'Best Practices' sections with generic advice ('Document parameters and random seeds for reproducibility'), 'Related Projects' and 'Additional Resources' sections that Claude doesn't need, and a troubleshooting section with vague guidance. Much of this is padding that Claude could infer. | 1 / 3 |
Actionability | The skill provides code examples for common workflows and CLI commands, which is good. However, the code examples appear to be illustrative rather than verified executable code (e.g., the API signatures like `region2vec()` as a function call, `tokenize_cells()` may not match actual geniml APIs), and key details like exact import paths and parameter names may be inaccurate. | 2 / 3 |
Workflow Clarity | Multi-step workflows are listed with numbered steps, which is helpful. However, there are no explicit validation checkpoints or feedback loops — for example, the Region Embedding Pipeline doesn't validate tokenization coverage before training, and the universe building workflow doesn't verify output quality before using the universe downstream. The 'Best Practices' section mentions validation but doesn't integrate it into the workflows. | 2 / 3 |
Progressive Disclosure | The skill references five detailed reference files (references/region2vec.md, references/bedspace.md, etc.) which is good structure, but no bundle files are provided, so these references point to nothing. Additionally, the SKILL.md itself contains too much inline content (full code examples, CLI reference, best practices, troubleshooting) that should be in the reference files, undermining the progressive disclosure pattern. | 2 / 3 |
Total | 7 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
Total | 10 / 11 Passed | |
- Repository
- K-Dense-AI/claude-scientific-skills
- Commit
cbcae7b
- Reviewed
Table of Contents
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.