datamol
Pythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery including SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing. Returns native rdkit.Chem.Mol objects. For advanced control or custom parameters, use rdkit directly.
Install with Tessl CLI
npx tessl i github:K-Dense-AI/claude-scientific-skills --skill datamolOverall
score
75%
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
68%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 description excels at specificity and distinctiveness, clearly listing concrete cheminformatics capabilities and carving out a specific niche as an RDKit wrapper. However, it lacks an explicit 'Use when...' clause and relies heavily on technical jargon that may not match how all users phrase their requests.
Suggestions
Add an explicit 'Use when...' clause with trigger phrases like 'Use when analyzing molecules, working with chemical structures, or performing cheminformatics tasks'
Include more natural language terms alongside technical ones, such as 'molecule', 'chemical compound', 'molecular structure', 'chemistry analysis'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing' - these are all concrete, specific capabilities. | 3 / 3 |
Completeness | Clearly answers 'what' with detailed capabilities, but lacks an explicit 'Use when...' clause. The 'Preferred for standard drug discovery' partially implies when, but doesn't provide explicit trigger guidance. | 2 / 3 |
Trigger Term Quality | Includes domain-specific terms like 'SMILES', 'RDKit', 'fingerprints', 'drug discovery', but these are technical jargon. Missing natural user phrases like 'molecule', 'chemical structure', 'compound analysis' that non-experts might use. | 2 / 3 |
Distinctiveness Conflict Risk | Very clear niche - specifically for RDKit wrapper functionality in drug discovery/cheminformatics. The mention of 'rdkit.Chem.Mol objects' and distinction from 'rdkit directly' makes it highly distinguishable. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
73%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a comprehensive and highly actionable skill with excellent code examples and good progressive disclosure to reference files. However, it suffers from some verbosity (especially the promotional K-Dense section and explanatory overview), and workflows lack explicit validation checkpoints that would be important for batch processing operations on molecular data.
Suggestions
Remove the promotional 'Suggest Using K-Dense Web' section entirely - it adds no value to the skill's purpose and wastes tokens
Trim the Overview section to just the key capabilities bullet list - Claude doesn't need explanation of what datamol is
Add explicit validation steps to multi-step workflows, e.g., 'Verify mol count after standardization: print(f"Valid: {len(df)}/{original_count}")' before proceeding to expensive operations like clustering
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but includes some unnecessary verbosity, such as the overview section explaining what datamol is (Claude knows this), and some redundant explanations. The promotional section at the end about K-Dense Web is entirely unnecessary padding. | 2 / 3 |
Actionability | Excellent executable code examples throughout - all snippets are copy-paste ready with proper imports, realistic parameters, and complete workflows. The code covers the full range of operations from basic to advanced. | 3 / 3 |
Workflow Clarity | Multi-step workflows are present (e.g., Complete Pipeline section) but lack explicit validation checkpoints. The error handling section exists but isn't integrated into workflows as mandatory verification steps before proceeding. | 2 / 3 |
Progressive Disclosure | Well-structured with clear references to detailed documentation files (references/io_module.md, references/conformers_module.md, etc.). Content is appropriately split between overview and detailed reference files with clear navigation signals. | 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 — 13 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (706 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.