deepchem
Molecular ML with diverse featurizers and pre-built datasets. Use for property prediction (ADMET, toxicity) with traditional ML or GNNs when you want extensive featurization options and MoleculeNet benchmarks. Best for quick experiments with pre-trained models, diverse molecular representations. For graph-first PyTorch workflows use torchdrug; for benchmark datasets use pytdc.
79
75%
Does it follow best practices?
Impact
83%
1.36xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/deepchem/SKILL.mdQuality
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 defines its domain (molecular ML with featurizers), specifies concrete use cases (ADMET, toxicity property prediction, MoleculeNet benchmarks), and explicitly differentiates itself from related skills (torchdrug, pytdc). The description is information-dense without being verbose, uses appropriate domain-specific trigger terms, and provides clear guidance on when to select this skill versus alternatives.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and capabilities: 'property prediction (ADMET, toxicity)', 'diverse featurizers', 'pre-built datasets', 'traditional ML or GNNs', 'extensive featurization options', 'MoleculeNet benchmarks', 'pre-trained models', 'diverse molecular representations'. | 3 / 3 |
Completeness | Clearly answers both 'what' (molecular ML with featurizers, property prediction, pre-built datasets) and 'when' ('Use for property prediction...when you want extensive featurization options and MoleculeNet benchmarks', 'Best for quick experiments'). Also includes explicit boundary guidance ('For graph-first PyTorch workflows use torchdrug; for benchmark datasets use pytdc'). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords a user in this domain would use: 'molecular', 'ADMET', 'toxicity', 'property prediction', 'GNNs', 'featurization', 'MoleculeNet', 'pre-trained models', 'molecular representations'. Also references related tools (torchdrug, pytdc) for disambiguation. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with explicit differentiation from related skills (torchdrug for graph-first PyTorch, pytdc for benchmark datasets). The niche of molecular ML with diverse featurizers and MoleculeNet benchmarks is clearly carved out, minimizing conflict risk. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
50%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 executable code examples and clear workflows, but is severely bloated—much of the content (featurizer decision trees, model selection tables, common pitfalls, best practices patterns) belongs in reference files rather than the main SKILL.md. The repeated emphasis on scaffold splitting across multiple sections and explanations of basic ML concepts waste tokens. Validation checkpoints are absent from workflows despite molecular featurization being error-prone.
Suggestions
Move the featurizer decision tree, model selection table, common patterns, and common pitfalls sections to reference files, keeping only a brief summary with links in SKILL.md
Remove the 'When to Use This Skill' section entirely—it restates obvious use cases that Claude can infer from the content
Add validation checkpoints to workflows, e.g., checking featurization success (failed SMILES return empty arrays), verifying dataset shapes after splitting, and checking metric scores before proceeding to predictions
Consolidate the scaffold splitting advice to a single prominent mention rather than repeating it in splitting, patterns, and pitfalls sections
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~400+ lines. Explains concepts Claude already knows (what SMILES are, what random forests are, what overfitting is), includes redundant 'When to Use This Skill' section listing obvious use cases, repeats scaffold splitting advice 3+ times, and provides extensive tables/guides that belong in reference files rather than the main skill body. | 1 / 3 |
Actionability | All code examples are concrete, executable, and copy-paste ready. Includes complete workflows from data loading through evaluation, specific CLI commands for scripts, and real library API calls with actual parameters. | 3 / 3 |
Workflow Clarity | Three complete workflows (A, B, C) are clearly sequenced with numbered steps, but none include validation checkpoints or error recovery loops. For a library where featurization can fail on invalid SMILES and model training can silently produce poor results, there are no explicit verification steps between stages. | 2 / 3 |
Progressive Disclosure | References to `references/api_reference.md`, `references/workflows.md`, and `scripts/` are well-signaled and one level deep. However, the main skill body contains far too much content that should be in reference files (full featurizer decision trees, complete model selection tables, extensive pitfalls section), undermining the overview nature of SKILL.md. | 2 / 3 |
Total | 8 / 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 (596 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.