molfeat
Molecular featurization for ML (100+ featurizers). ECFP, MACCS, descriptors, pretrained models (ChemBERTa), convert SMILES to features, for QSAR and molecular ML.
74
70%
Does it follow best practices?
Impact
78%
1.41xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/molfeat/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, domain-specific description with excellent specificity and trigger term coverage for cheminformatics users. Its main weakness is the lack of an explicit 'Use when...' clause, which would help Claude know precisely when to select this skill. The technical terminology is appropriate for the target audience and creates a clear, distinctive niche.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about molecular fingerprints, chemical featurization, converting SMILES strings to feature vectors, or building QSAR models.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and tools: ECFP, MACCS, descriptors, pretrained models (ChemBERTa), convert SMILES to features, QSAR, and molecular ML. These are concrete, domain-specific capabilities. | 3 / 3 |
Completeness | The 'what' is well-covered (molecular featurization with specific methods), and the 'when' is implied by listing use cases like QSAR and molecular ML, but there is no explicit 'Use when...' clause with trigger guidance, which caps this at 2 per the rubric. | 2 / 3 |
Trigger Term Quality | Excellent coverage of natural terms a cheminformatics user would use: 'ECFP', 'MACCS', 'SMILES', 'featurization', 'QSAR', 'ChemBERTa', 'molecular ML', 'descriptors'. These are precisely the keywords someone in this domain would mention. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche — molecular featurization for ML with specific cheminformatics terms like ECFP, MACCS, SMILES, and ChemBERTa. Very unlikely to conflict with other skills given the specialized domain vocabulary. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is highly actionable with excellent code examples and good progressive disclosure to reference files, but it is far too verbose for its purpose. It over-explains concepts Claude already knows (what ML tasks are, what fingerprints are for), repeats similar patterns across sections, and includes unnecessary framing like the 'When to Use This Skill' section. Trimming redundancy and trusting Claude's existing knowledge could cut this by 40-50% without losing any actionable content.
Suggestions
Remove the 'When to Use This Skill' and 'Overview' sections entirely—Claude already knows what molecular featurization is and when it's needed.
Consolidate the 'Choosing the Right Featurizer' and 'Common Featurizers Reference' table into a single concise section to eliminate redundancy.
Integrate validation steps directly into workflows (e.g., check for None values after featurization with ignore_errors=True, validate feature matrix shape before model training).
Remove explanatory comments like 'Most popular, general-purpose' and 'Fast, good for scaffold hopping' that Claude can infer, keeping only the code and the reference table.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~350+ lines. It explains concepts Claude already knows (what QSAR is, what virtual screening is, what similarity searching is), includes a lengthy 'When to Use This Skill' section that's unnecessary, and repeats similar code patterns multiple times. The 'Core Concepts' section explains basic OOP hierarchy that Claude can infer. Many sections like 'Choosing the Right Featurizer' and 'Common Workflows' have significant overlap. | 1 / 3 |
Actionability | The skill provides fully executable, copy-paste ready code examples throughout. Installation commands are specific, code snippets use real imports and function calls, and examples include expected outputs (e.g., shape annotations). The featurizer reference table with dimensions and speed is highly actionable. | 3 / 3 |
Workflow Clarity | Workflows like QSAR model building and virtual screening are clearly sequenced, but there are no validation checkpoints. For batch processing of large datasets with potentially invalid SMILES, there's no explicit validate-then-proceed pattern. The error handling section exists but is separate from the workflows rather than integrated as validation steps within them. | 2 / 3 |
Progressive Disclosure | The skill has a clear overview structure with well-signaled references to three separate files (api_reference.md, available_featurizers.md, examples.md). Each reference includes a description of contents and a 'When to load' guide. The grep search tip for finding specific featurizers is a nice touch. References are one level deep. | 3 / 3 |
Total | 9 / 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 (510 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
25e1c0f
- 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.