scikit-bio
Biological data toolkit. Sequence analysis, alignments, phylogenetic trees, diversity metrics (alpha/beta, UniFrac), ordination (PCoA), PERMANOVA, FASTA/Newick I/O, for microbiome analysis.
72
66%
Does it follow best practices?
Impact
73%
2.21xAverage score across 6 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/scikit-bio/SKILL.mdQuality
Discovery
82%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 description excels at specificity and distinctiveness, listing numerous concrete bioinformatics capabilities with domain-specific terminology that clearly carves out a unique niche. Its main weakness is the absence of an explicit 'Use when...' clause, which means Claude must infer when to select this skill rather than being explicitly guided. Adding trigger guidance would elevate this from a good to excellent description.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about microbiome analysis, biological sequence data, phylogenetics, diversity metrics, or mentions FASTA/Newick files.'
Consider adding common user-facing synonyms like '16S rRNA', 'metagenomics', 'OTU tables', or 'amplicon sequencing' to broaden trigger term coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: sequence analysis, alignments, phylogenetic trees, diversity metrics (alpha/beta, UniFrac), ordination (PCoA), PERMANOVA, and specific file format I/O (FASTA/Newick). | 3 / 3 |
Completeness | Clearly answers 'what does this do' with specific capabilities, but lacks an explicit 'Use when...' clause or equivalent trigger guidance. The 'when' is only implied by the domain context ('for microbiome analysis'). | 2 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'microbiome analysis', 'sequence analysis', 'phylogenetic trees', 'FASTA', 'Newick', 'UniFrac', 'PCoA', 'PERMANOVA', 'alpha/beta diversity'. These are terms bioinformaticians naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche targeting microbiome/bioinformatics analysis with very specific technical terms (UniFrac, PCoA, PERMANOVA, FASTA/Newick) that are unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides excellent actionable code examples across a comprehensive range of scikit-bio capabilities, making it highly useful for execution. However, it is significantly over-verbose for a skill file—much of the content reads like library documentation rather than a concise skill targeting Claude's needs. The workflows lack validation checkpoints, and the content would benefit from being split across multiple files with a leaner overview.
Suggestions
Reduce content by at least 50%: remove 'When to Use This Skill' section entirely, trim 'Important notes' to only non-obvious gotchas (e.g., keep 'counts must be integers' but remove 'permutation tests provide non-parametric significance testing'), and eliminate redundant explanations of what each capability does.
Add explicit validation/verification steps to the Common Workflows section—e.g., after alignment check alignment scores, after tree construction verify tip counts, after diversity calculation sanity-check output dimensions.
Split the 10 capability sections into separate reference files (e.g., sequences.md, diversity.md, ordination.md) and keep SKILL.md as a concise overview with quick-start examples and navigation links.
Actually provide the referenced 'references/api_reference.md' bundle file, or remove the reference if it doesn't exist.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~350+ lines, with significant redundancy. Sections like 'When to Use This Skill' explain obvious use cases Claude can infer. 'Important notes' sections often state things Claude already knows (e.g., 'Permutation tests provide non-parametric significance testing'). Many sections could be condensed by 50%+ without losing actionable content. | 1 / 3 |
Actionability | The skill provides fully executable, copy-paste ready code examples for every capability area. Code snippets use real imports, real method calls, and demonstrate concrete patterns rather than pseudocode. Examples cover both basic and advanced usage patterns. | 3 / 3 |
Workflow Clarity | The 'Common Workflows' section lists four multi-step workflows but only as high-level arrow sequences without validation checkpoints or error recovery steps. For operations like sequence alignment pipelines or diversity analysis, there are no explicit verification steps (e.g., checking alignment quality, validating BIOM table integrity). Individual sections have clear patterns but lack feedback loops. | 2 / 3 |
Progressive Disclosure | The skill references 'references/api_reference.md' for detailed documentation, which is good structure, but no bundle files are provided so this reference is unverifiable. The main file itself is monolithic with 10 major sections that could benefit from being split into separate reference files, with the SKILL.md serving as a leaner overview pointing to them. | 2 / 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
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.