pdb-database
Access RCSB PDB for 3D protein/nucleic acid structures. Search by text/sequence/structure, download coordinates (PDB/mmCIF), retrieve metadata, for structural biology and drug discovery.
81
77%
Does it follow best practices?
Impact
83%
1.69xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/pdb-database/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 is a well-crafted description with strong specificity and excellent trigger terms covering the structural biology domain. The main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill. The domain-specific terminology makes it highly distinctive.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about protein structures, PDB files, molecular coordinates, or needs to search the Protein Data Bank.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Search by text/sequence/structure, download coordinates (PDB/mmCIF), retrieve metadata' - these are clear, actionable capabilities with specific file formats mentioned. | 3 / 3 |
Completeness | Clearly answers 'what' (access RCSB PDB, search, download, retrieve metadata) but lacks an explicit 'Use when...' clause. The use cases are implied through domain mentions (structural biology, drug discovery) but not explicitly stated as triggers. | 2 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'RCSB PDB', 'protein', 'nucleic acid structures', 'PDB', 'mmCIF', 'structural biology', 'drug discovery', 'coordinates', 'sequence', 'structure search'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with specific domain (RCSB PDB, protein/nucleic acid structures) and technical terms (mmCIF, PDB format) that create a clear niche unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 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, actionable skill with excellent code examples that are immediately executable. The main weaknesses are verbosity in introductory sections (explaining what PDB is, listing use cases Claude can infer) and missing validation checkpoints in batch/multi-step workflows. Trimming explanatory content and adding explicit validation steps would elevate this skill.
Suggestions
Remove or significantly condense the 'Overview', 'When to Use This Skill', 'Common Use Cases', and 'Key Concepts' sections - Claude already knows these concepts and can infer appropriate use cases
Add explicit validation steps to batch operations (e.g., verify downloaded file integrity, check response status codes, validate parsed structure data)
Consider moving the BioPython parsing example to the references file since it's a separate library concern
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill includes some unnecessary explanations (e.g., 'RCSB PDB is the worldwide repository...', 'Key Concepts' section explaining basic terms Claude knows). The 'When to Use This Skill' section is largely redundant. However, the code examples are reasonably efficient. | 2 / 3 |
Actionability | Excellent executable code examples throughout - all Python snippets are copy-paste ready with proper imports, real PDB IDs, and complete syntax. Download URLs are concrete and functional. The examples cover the full range of common operations. | 3 / 3 |
Workflow Clarity | While individual operations are clear, the batch operations section lacks validation/error recovery beyond a basic try-except. No explicit checkpoints for multi-step workflows like 'search -> download -> parse'. The skill presents capabilities but not validated workflows. | 2 / 3 |
Progressive Disclosure | Good structure with clear sections, a referenced 'references/api_reference.md' for detailed documentation, and well-organized external resource links. The main content stays focused on quick-start patterns while pointing to deeper resources. | 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.