string-database
Query STRING API for protein-protein interactions (59M proteins, 20B interactions). Network analysis, GO/KEGG enrichment, interaction discovery, 5000+ species, for systems biology.
83
83%
Does it follow best practices?
Impact
81%
2.02xAverage score across 6 eval scenarios
Passed
No known issues
Quality
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 is a strong, domain-specific description with excellent specificity and trigger terms for bioinformatics users. The main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill. The technical depth and concrete metrics (59M proteins, 20B interactions) are valuable for distinguishing this skill.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about protein interactions, STRING database queries, pathway enrichment analysis, or systems biology network visualization.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Query STRING API', 'Network analysis', 'GO/KEGG enrichment', 'interaction discovery'. Also provides concrete scope metrics (59M proteins, 20B interactions, 5000+ species). | 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 through domain context. | 2 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'protein-protein interactions', 'STRING API', 'GO/KEGG enrichment', 'network analysis', 'systems biology', 'interaction discovery'. These are domain-appropriate terms bioinformatics users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche: STRING API specifically, protein-protein interactions, GO/KEGG enrichment. Very unlikely to conflict with other skills due to specific bioinformatics domain and named API. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable skill with excellent workflow clarity and progressive disclosure. The main weakness is verbosity - explanations of what STRING is, detailed evidence channel descriptions, and some redundant parameter documentation could be trimmed. The executable code examples and clear workflows are strong points that make this immediately usable.
Suggestions
Remove the Overview paragraph explaining what STRING is - Claude already knows this; start directly with Quick Start or When to Use
Condense the 'Understanding Confidence Scores' section - the evidence channel explanations are verbose; a simple table would suffice
Remove redundant parameter descriptions that appear in multiple function examples (e.g., species and required_score are explained repeatedly)
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but includes some unnecessary verbosity, such as explaining what STRING is (Claude knows databases), detailed explanations of evidence channels that could be condensed, and repetitive parameter descriptions across functions. | 2 / 3 |
Actionability | Excellent actionability with fully executable Python code examples throughout, specific function calls with real parameters, copy-paste ready workflows, and concrete examples using actual protein names like TP53, BRCA1. | 3 / 3 |
Workflow Clarity | Clear numbered workflows with explicit steps, multiple complete analysis workflows (protein list analysis, single protein investigation, pathway-centric), and logical progression from mapping to network to enrichment to visualization. | 3 / 3 |
Progressive Disclosure | Well-structured with quick start pointing to helper scripts and reference documentation, clear sections for core operations vs workflows, and appropriate reference to external files (string_reference.md) for detailed API specs. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (533 lines); consider splitting into references/ and linking | Warning |
metadata_version | 'metadata.version' is missing | Warning |
Total | 9 / 11 Passed | |
- Repository
- K-Dense-AI/claude-scientific-skills
- Commit
71add64
- 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.