biopython
Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.
82
75%
Does it follow best practices?
Impact
96%
1.17xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/biopython/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 an excellent skill description that covers specific capabilities, includes abundant natural trigger terms from the bioinformatics domain, clearly states both what it does and when to use it, and proactively differentiates itself from related skills. The explicit cross-referencing to gget and bioservices is a particularly strong feature that helps Claude route requests correctly.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, programmatic NCBI/PubMed access, batch processing, custom bioinformatics pipelines, BLAST automation. | 3 / 3 |
Completeness | Clearly answers 'what' (sequence manipulation, file parsing, phylogenetics, NCBI/PubMed access) and 'when' ('Use for...', 'Best for batch processing, custom bioinformatics pipelines, BLAST automation'). Also provides differentiation guidance ('For quick lookups use gget; for multi-service integration use bioservices'). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: FASTA, GenBank, PDB, NCBI, PubMed, Bio.Entrez, BLAST, bioinformatics, molecular biology, sequence manipulation, phylogenetics. These are terms bioinformaticians naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche in molecular biology/bioinformatics. Explicitly differentiates itself from related skills (gget for quick lookups, bioservices for multi-service integration), which directly reduces conflict risk. | 3 / 3 |
Total | 12 / 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 is highly actionable with excellent executable code examples covering all major Biopython modules, but it is severely bloated with redundant sections, obvious information Claude already knows, and content that should live in the referenced sub-files rather than the main SKILL.md. The workflow guidance lacks explicit validation checkpoints for operations involving network calls and file I/O.
Suggestions
Remove the 'When to Use This Skill', 'Core Capabilities', 'Overview' explanation, and 'Summary' sections - these are redundant and explain things Claude already knows. The description field already covers when to use the skill.
Move 'Common Patterns', 'Troubleshooting', and 'Best Practices' into the reference files where they belong, keeping SKILL.md as a lean overview with one quick example per module and clear pointers to references.
Add explicit validation steps to multi-step workflows - e.g., verify Entrez responses before parsing, check file existence before parsing, validate BLAST results before fetching sequences.
Remove the 'Quick Reference' grep examples section - Claude knows how to search files without being told to use grep.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose. The 'When to Use This Skill' section lists 12 bullet points of obvious use cases Claude already knows. The 'Core Capabilities' section redundantly summarizes what's repeated in detail below. The 'Overview' explains what Biopython is (unnecessary for Claude). The 'Best Practices' and 'Summary' sections largely repeat earlier content. The 'General Workflow Guidelines' section tells Claude how to read documentation and use grep, which is basic knowledge. | 1 / 3 |
Actionability | The skill provides numerous executable, copy-paste-ready code examples across all major modules. Each section includes concrete Python code with proper imports, and the common patterns section shows complete multi-step pipelines. The troubleshooting section provides specific solutions to specific errors. | 3 / 3 |
Workflow Clarity | The 'General Workflow Guidelines' section provides a reasonable sequence for approaching tasks, and common patterns show multi-step processes. However, there are no explicit validation checkpoints - for example, the BLAST+fetch pattern doesn't validate responses, the file conversion pattern doesn't verify output, and network operations lack retry logic beyond a basic try/except. | 2 / 3 |
Progressive Disclosure | The skill correctly references 6 separate reference files for detailed documentation, which is good progressive disclosure. However, the main SKILL.md itself is excessively long with substantial inline content (quick examples for every module, common patterns, best practices, troubleshooting, additional resources, quick reference, summary) that bloats what should be an overview. Much of this content should be in the reference files. | 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
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.