uniprot-database
Direct REST API access to UniProt. Protein searches, FASTA retrieval, ID mapping, Swiss-Prot/TrEMBL. For Python workflows with multiple databases, prefer bioservices (unified interface to 40+ services). Use this for direct HTTP/REST work or UniProt-specific control.
90
86%
Does it follow best practices?
Impact
92%
1.04xAverage score across 6 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 an excellent skill description that clearly articulates specific capabilities (protein searches, FASTA retrieval, ID mapping), includes abundant natural trigger terms from the bioinformatics domain, and explicitly addresses both when to use this skill and when to prefer an alternative (bioservices). The description successfully carves out a distinct niche while helping Claude make informed skill selection decisions.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Protein searches, FASTA retrieval, ID mapping, Swiss-Prot/TrEMBL' - these are distinct, actionable capabilities in the bioinformatics domain. | 3 / 3 |
Completeness | Clearly answers both what ('Protein searches, FASTA retrieval, ID mapping') and when ('Use this for direct HTTP/REST work or UniProt-specific control'), plus provides guidance on when NOT to use it (prefer bioservices for Python workflows with multiple databases). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'UniProt', 'REST API', 'Protein searches', 'FASTA', 'ID mapping', 'Swiss-Prot', 'TrEMBL', 'HTTP/REST' - these are exactly what bioinformatics users would mention. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche - explicitly differentiates from bioservices skill by specifying when to use each, and focuses on UniProt-specific REST API work which is a narrow, well-defined domain. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid skill with excellent actionability through concrete API endpoints, query examples, and clear field specifications. The progressive disclosure is well-executed with appropriate references to detailed documentation. Main weaknesses are some verbosity in the overview sections and missing validation/error handling guidance for multi-step operations like ID mapping.
Suggestions
Remove or condense the 'Overview' and 'When to Use This Skill' sections - Claude doesn't need to be told what UniProt is or when to use it
Add error handling and validation steps to the ID Mapping workflow (e.g., 'Check status returns FINISHED before retrieving results; handle RUNNING/ERROR states')
Add rate limiting guidance with specific numbers (requests per second) rather than vague 'implement delays'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill includes some unnecessary explanatory content (e.g., 'UniProt is the world's leading comprehensive protein sequence...') and the 'When to Use This Skill' section largely restates capabilities. However, most content is reasonably efficient with good code examples. | 2 / 3 |
Actionability | Provides concrete, executable query patterns, specific API endpoints with exact URLs, clear accession number formats, and real examples. The Python implementation section references a helper script with specific function signatures. | 3 / 3 |
Workflow Clarity | The ID Mapping workflow shows a clear 3-step sequence, but lacks validation checkpoints or error handling guidance. No feedback loops for failed requests or rate limiting errors. Batch operations mention limitations but no verification steps. | 2 / 3 |
Progressive Disclosure | Well-structured with clear sections, appropriate references to external files (api_fields.md, id_mapping_databases.md, query_syntax.md), and one-level-deep navigation. Content is appropriately split between overview and detailed references. | 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.