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.
74
71%
Does it follow best practices?
Impact
68%
1.74xAverage score across 3 eval scenarios
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 this skill when appropriate. The explicit 'Use for' 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'). | 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
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill has excellent progressive disclosure structure with clear references to detailed sub-files, but is significantly too verbose for its purpose. It repeats information across sections (capabilities vs. 'when to use' vs. best practices), includes generic advice Claude doesn't need, and has a typo in the installation commands. The code examples provide reasonable guidance but lack validation steps in workflows.
Suggestions
Remove the 'When to Use Which Tool' section entirely — the brief 'Use for:' lines under each capability already cover this, making it redundant.
Cut the 'Best Practices' and 'Related Projects' sections, which contain generic advice (parameter tuning, documentation, memory management) that Claude already knows or that belongs in reference files.
Fix the installation typo: `uv uv pip install` should be `uv pip install`.
Add explicit validation checkpoints in workflows, e.g., 'Verify tokenization coverage > 80% before training' as a numbered step with a concrete command or code snippet.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~250+ lines. It includes extensive explanatory text about when to use each tool, general best practices Claude already knows (parameter tuning, documentation, memory management), and a 'Related Projects' section that adds little actionable value. The 'When to Use Which Tool' section largely restates what was already described in the Core Capabilities section. | 1 / 3 |
Actionability | The skill provides concrete code examples and CLI commands, but the code appears to be illustrative rather than verified executable (e.g., `from geniml.region2vec import region2vec` and `from geniml.scembed import ScEmbed` may not reflect actual API). The installation commands contain a typo (`uv uv pip install`). Key details like actual function signatures and return types are missing. | 2 / 3 |
Workflow Clarity | Multi-step workflows are listed with numbered steps, which is good. However, validation checkpoints are mostly absent — there's no explicit 'verify tokenization output before proceeding' or 'check model convergence before generating embeddings' step. The troubleshooting section partially compensates but doesn't integrate validation into the workflows themselves. | 2 / 3 |
Progressive Disclosure | The skill effectively uses a hub-and-spoke model, providing concise overviews of each capability and pointing to dedicated reference files (references/region2vec.md, references/bedspace.md, etc.) with clear one-level-deep navigation. The structure is well-organized with clear section headers. | 3 / 3 |
Total | 8 / 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
b58ad7e
- 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.