gtars
High-performance toolkit for genomic interval analysis in Rust with Python bindings. Use when working with genomic regions, BED files, coverage tracks, overlap detection, tokenization for ML models, or fragment analysis in computational genomics and machine learning applications.
64
66%
Does it follow best practices?
Impact
32%
1.23xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/gtars/SKILL.mdQuality
Discovery
89%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 solid skill description with excellent trigger term coverage and completeness, clearly specifying both what the skill does and when to use it. The main weakness is that the capabilities are described more as topic areas than concrete actions—listing specific operations (e.g., 'parse BED files', 'compute interval overlaps', 'generate coverage histograms') would strengthen specificity. The highly specialized domain ensures strong distinctiveness.
Suggestions
Replace topic-area nouns with concrete action phrases, e.g., 'Parses BED files, computes interval overlaps, generates coverage tracks, tokenizes genomic regions for ML models' instead of listing domains.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (genomic interval analysis) and mentions several areas like BED files, coverage tracks, overlap detection, tokenization, and fragment analysis, but these read more as topic areas than concrete actions. It lacks specific verbs describing what the toolkit does (e.g., 'parse BED files', 'compute overlaps', 'generate coverage histograms'). | 2 / 3 |
Completeness | Clearly answers both 'what' (high-performance toolkit for genomic interval analysis in Rust with Python bindings) and 'when' (explicit 'Use when...' clause listing specific trigger scenarios like BED files, coverage tracks, overlap detection, tokenization for ML, and fragment analysis). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'genomic regions', 'BED files', 'coverage tracks', 'overlap detection', 'tokenization', 'ML models', 'fragment analysis', 'computational genomics', 'Rust', 'Python bindings'. These cover a wide range of terms a user in this domain would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche combining genomic intervals, BED files, Rust/Python bindings, and ML tokenization. Very unlikely to conflict with other skills given the specialized domain and specific trigger terms. | 3 / 3 |
Total | 11 / 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 with clear references to detailed documentation, but is significantly too verbose—explaining concepts Claude already knows (genomic formats, when to use various tools) and including marketing-style content (performance characteristics). Code examples provide a reasonable starting point but may not be fully executable, and workflows lack validation checkpoints for potentially error-prone genomic data operations.
Suggestions
Remove all 'When to use' bullet lists and 'Data Formats' / 'Performance Characteristics' sections—Claude can infer these; this would cut ~40% of token usage
Fix the installation typo ('uv uv pip install' → 'uv pip install') and verify all code examples against the actual API to ensure they are executable
Add validation/error-checking steps to workflows, e.g., verify BED file format before processing, check output file existence after generation
Consolidate the 'Python vs CLI Usage' section into a single sentence or remove it entirely—the distinction is obvious
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is very verbose with extensive 'When to use' lists that Claude can infer, explanations of what genomic formats are, performance characteristics that are marketing-style bullet points rather than actionable guidance, and a 'Python vs CLI Usage' section stating obvious heuristics. Many sections explain concepts Claude already knows (e.g., what BED files are, what coverage tracks are for). | 1 / 3 |
Actionability | The skill provides code examples for installation and basic usage, but many examples appear to be pseudocode or illustrative rather than verified executable code (e.g., `gtars.RegionSet.from_bed()`, `peaks.filter_overlapping()` may not reflect the actual API). The installation has a typo ('uv uv pip install'). Quick examples give a starting point but lack completeness for real execution. | 2 / 3 |
Workflow Clarity | Multi-step workflows are listed (Peak Overlap Analysis, Coverage Track Pipeline, ML Preprocessing) with sequential steps, but they lack validation checkpoints or error recovery steps. For operations on genomic data files that could fail (malformed BED files, missing chromosomes), there are no verification steps between pipeline stages. | 2 / 3 |
Progressive Disclosure | The skill has a clear overview structure with well-signaled one-level-deep references to specific documentation files (references/overlap.md, references/coverage.md, etc.). The reference documentation section at the end provides a clean navigation index. Content is appropriately split between the overview and detailed reference files. | 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.