molfeat
Molecular featurization for ML (100+ featurizers). ECFP, MACCS, descriptors, pretrained models (ChemBERTa), convert SMILES to features, for QSAR and molecular ML.
Install with Tessl CLI
npx tessl i github:K-Dense-AI/claude-scientific-skills --skill molfeatOverall
score
85%
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
83%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 excels at listing concrete capabilities and using domain-appropriate terminology that cheminformatics users would naturally use. The main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill over others.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user needs to convert molecular structures to ML features, mentions fingerprints, or asks about QSAR modeling.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and tools: 'ECFP, MACCS, descriptors, pretrained models (ChemBERTa), convert SMILES to features' with clear use cases 'for QSAR and molecular ML'. | 3 / 3 |
Completeness | Clearly answers 'what' (molecular featurization with specific methods) but lacks an explicit 'Use when...' clause. The 'for QSAR and molecular ML' implies when but doesn't provide explicit trigger guidance. | 2 / 3 |
Trigger Term Quality | Excellent coverage of natural domain-specific terms users would say: 'ECFP', 'MACCS', 'SMILES', 'featurizers', 'QSAR', 'molecular ML', 'ChemBERTa', 'descriptors' - these are exactly what a cheminformatics user would search for. | 3 / 3 |
Distinctiveness Conflict Risk | Highly specialized niche with distinct domain-specific triggers (ECFP, MACCS, SMILES, ChemBERTa, QSAR). Extremely unlikely to conflict with other skills due to the specialized cheminformatics vocabulary. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable skill for molecular featurization. Its main strength is the comprehensive, executable code examples covering diverse workflows from basic featurization to production pipelines. The progressive disclosure is excellent with clear navigation to reference materials. The primary weakness is moderate verbosity in introductory sections that explain concepts Claude would already understand.
Suggestions
Remove or significantly condense the 'When to Use This Skill' section - Claude can infer appropriate use cases from the content itself
Tighten the Overview paragraph to focus on unique capabilities rather than explaining what molecular featurization is
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but includes some unnecessary verbosity, such as the 'When to Use This Skill' section listing obvious use cases Claude would infer, and the overview paragraph explaining what molfeat does when the examples demonstrate it clearly. The content could be tightened by ~20-30%. | 2 / 3 |
Actionability | Excellent actionability with fully executable, copy-paste ready code examples throughout. Every workflow includes concrete Python code with proper imports, realistic parameters, and expected outputs. The examples cover installation, basic usage, advanced patterns, and troubleshooting. | 3 / 3 |
Workflow Clarity | Multi-step workflows are clearly sequenced with explicit steps. The QSAR model building, virtual screening pipeline, and similarity search workflows have clear progression. Error handling is addressed with ignore_errors parameter, and reproducibility is covered with config saving. | 3 / 3 |
Progressive Disclosure | Excellent structure with a clear overview, quick start, then progressively detailed sections. References to external files (api_reference.md, available_featurizers.md, examples.md) are well-signaled with clear descriptions of when to load each. The grep tip for searching references is a nice touch. | 3 / 3 |
Total | 11 / 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 — 13 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (511 lines); consider splitting into references/ and linking | Warning |
description_trigger_hint | Description may be missing an explicit 'when to use' trigger hint (e.g., 'Use when...') | Warning |
metadata_version | 'metadata.version' is missing | Warning |
Total | 13 / 16 Passed | |
- 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.