drugbank-database
Access and analyze comprehensive drug information from the DrugBank database including drug properties, interactions, targets, pathways, chemical structures, and pharmacology data. This skill should be used when working with pharmaceutical data, drug discovery research, pharmacology studies, drug-drug interaction analysis, target identification, chemical similarity searches, ADMET predictions, or any task requiring detailed drug and drug target information from DrugBank.
85
85%
Does it follow best practices?
Impact
81%
1.55xAverage score across 3 eval scenarios
Passed
No known issues
Quality
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 well-crafted skill description that excels across all dimensions. It provides specific capabilities, includes natural trigger terms that domain experts would use, explicitly states both what the skill does and when to use it, and has a clear distinctive niche in pharmaceutical/drug research. The description uses proper third-person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'drug properties, interactions, targets, pathways, chemical structures, and pharmacology data' as well as specific use cases like 'drug-drug interaction analysis, target identification, chemical similarity searches, ADMET predictions'. | 3 / 3 |
Completeness | Clearly answers both what ('Access and analyze comprehensive drug information...including drug properties, interactions, targets, pathways, chemical structures, and pharmacology data') AND when ('This skill should be used when working with pharmaceutical data, drug discovery research, pharmacology studies...'). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'drug information', 'DrugBank', 'pharmaceutical data', 'drug discovery', 'pharmacology', 'drug-drug interaction', 'chemical similarity', 'ADMET', 'drug target'. These are terms researchers and pharmacologists would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Very clear niche focused specifically on DrugBank database and pharmaceutical/pharmacology domain. The specific mention of DrugBank, ADMET predictions, and drug-specific terminology makes it highly unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
70%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill demonstrates strong organizational structure with clear workflows and excellent progressive disclosure to reference files. However, it sacrifices actionability by deferring nearly all executable code to external references, and includes some verbose capability lists that could be more concise. The skill serves well as a navigation hub but provides limited standalone utility.
Suggestions
Add at least one complete, executable code example in the main skill (e.g., a minimal drug lookup or interaction check) so users can immediately test functionality without loading reference files.
Condense the capability bullet lists - many items could be grouped or summarized since Claude can infer related capabilities from a few examples.
Remove or relocate the detailed database statistics (9,591 drugs, 2,037 FDA-approved, etc.) as this information is time-sensitive and not essential for using the skill.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably organized but includes some unnecessary verbosity, such as the detailed statistics in the overview (9,591 drugs, 2,037 FDA-approved, etc.) and repetitive 'When to use' sections that could be more concise. The capability lists are comprehensive but could be tightened. | 2 / 3 |
Actionability | Provides some concrete guidance like installation commands and a version-pinning code snippet, but most actual implementation is deferred to reference files. The main skill lacks executable examples for core operations like querying drugs or extracting interactions. | 2 / 3 |
Workflow Clarity | Workflows are clearly sequenced with numbered steps for multiple use cases (drug discovery, polypharmacy safety, repurposing, pharmacology study). Each step references the appropriate reference file, making the process easy to follow. | 3 / 3 |
Progressive Disclosure | Excellent structure with a clear overview, organized capability sections, and well-signaled one-level-deep references to modular documentation files. Navigation is straightforward with consistent 'Reference: See X' patterns throughout. | 3 / 3 |
Total | 10 / 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
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.