alphafold-database
Access AlphaFold 200M+ AI-predicted protein structures. Retrieve structures by UniProt ID, download PDB/mmCIF files, analyze confidence metrics (pLDDT, PAE), for drug discovery and structural biology.
77
77%
Does it follow best practices?
Impact
69%
1.38xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/alphafold-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 strong, technically specific description that clearly identifies the skill's domain (AlphaFold protein structures) and lists concrete capabilities. 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 terminology is appropriate for the target audience and provides excellent distinctiveness.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about protein structures, AlphaFold predictions, UniProt lookups, or needs to analyze protein folding confidence scores.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Retrieve structures by UniProt ID', 'download PDB/mmCIF files', 'analyze confidence metrics (pLDDT, PAE)'. Also specifies use cases: 'drug discovery and structural biology'. | 3 / 3 |
Completeness | Clearly answers 'what' (access AlphaFold structures, retrieve by UniProt ID, download files, analyze metrics) but lacks an explicit 'Use when...' clause. The 'when' is only implied through the domain context. | 2 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'AlphaFold', 'protein structures', 'UniProt ID', 'PDB', 'mmCIF', 'pLDDT', 'PAE', 'drug discovery', 'structural biology'. These are domain-specific but exactly what users in this field would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche: AlphaFold-specific, protein structures, UniProt IDs, specific file formats (PDB/mmCIF), and domain-specific metrics (pLDDT, PAE). 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 executable code examples covering multiple access patterns for AlphaFold DB. The main weaknesses are verbosity in explanatory sections (explaining concepts Claude knows) and missing validation checkpoints in multi-step workflows like batch processing and bulk downloads. The progressive disclosure is well-handled with appropriate external references.
Suggestions
Remove or significantly condense the 'When to Use This Skill' and 'Key Concepts' sections - Claude already understands these concepts and use cases
Add explicit validation steps to batch processing workflow (e.g., verify file integrity after download, check response status codes before proceeding)
Add a verification step after bulk Google Cloud downloads to confirm all expected files were retrieved successfully
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but includes some unnecessary explanations (e.g., explaining what pLDDT thresholds mean when Claude would know this, the 'When to Use This Skill' section is verbose). The 'Key Concepts' section explains basic terminology Claude already understands. Could be tightened by ~30%. | 2 / 3 |
Actionability | Excellent executable code examples throughout - all Python snippets are copy-paste ready with proper imports, real URLs, and complete function definitions. Covers multiple access methods (Biopython, direct API, Google Cloud) with working code for each. | 3 / 3 |
Workflow Clarity | While individual operations are clear, multi-step workflows lack explicit validation checkpoints. The batch processing section doesn't include verification steps for downloaded files. The bulk download workflow doesn't validate successful downloads before proceeding. | 2 / 3 |
Progressive Disclosure | Well-structured with clear sections progressing from simple (Biopython) to advanced (Google Cloud bulk access). References external 'references/api_reference.md' for detailed API documentation. Content is appropriately split between overview and detailed examples. | 3 / 3 |
Total | 10 / 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 (512 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.