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.
73
66%
Does it follow best practices?
Impact
81%
3.24xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/datamol/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 that clearly lists concrete capabilities and uses natural terminology from computational chemistry. Its main weakness is the lack of an explicit 'Use when...' clause, which would help Claude know precisely when to select this skill. The boundary guidance ('For advanced control... use rdkit directly') is a nice touch for distinctiveness.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about cheminformatics tasks, molecular analysis, SMILES strings, chemical fingerprints, or drug discovery workflows.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing. Also specifies return type (native rdkit.Chem.Mol objects) and when to use RDKit directly instead. | 3 / 3 |
Completeness | Clearly answers 'what does this do' with specific capabilities and even distinguishes from raw RDKit usage. However, there is no explicit 'Use when...' clause or equivalent trigger guidance, which per the rubric caps completeness at 2. | 2 / 3 |
Trigger Term Quality | Includes strong natural keywords a user in this domain would use: 'RDKit', 'SMILES', 'drug discovery', 'fingerprints', 'descriptors', 'conformers', 'clustering', 'standardization'. These are the exact terms a computational chemist would naturally mention. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche — cheminformatics/drug discovery with specific mention of RDKit, SMILES, fingerprints, and conformers. Very unlikely to conflict with other skills. Also explicitly delineates boundary with raw RDKit usage. | 3 / 3 |
Total | 11 / 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.
This skill is highly actionable with excellent executable code examples covering the full breadth of datamol's capabilities. However, it is far too verbose for a SKILL.md - it reads more like comprehensive documentation than a concise skill file, with extensive inline content that should be delegated to the referenced files. The workflow clarity would benefit from integrated validation steps rather than separate error handling sections.
Suggestions
Reduce the SKILL.md to a concise overview (~100-150 lines) with quick-start examples for the most common operations, and move detailed examples (SAR analysis, virtual screening, ML integration, scaffold splitting) into the reference files.
Remove explanations of concepts Claude already knows: basic Python patterns (Counter, list comprehensions, pandas groupby), what SMILES/InChI are, how sklearn works, and obvious error handling patterns.
Integrate validation checkpoints directly into multi-step workflows (e.g., 'Verify standardization succeeded before computing descriptors') rather than having a separate Error Handling section.
Eliminate the 'Best Practices' section which largely repeats guidance already demonstrated in code examples above it, or consolidate it into a brief checklist.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~500+ lines, explaining many concepts Claude already knows (e.g., what SMILES is, how to iterate lists, basic pandas operations, sklearn usage). The overview section restates what's in the description. Many code examples include obvious patterns like list comprehensions and Counter usage that don't need to be spelled out. The 'Best Practices' section largely repeats guidance already shown in examples above. | 1 / 3 |
Actionability | The skill provides fully executable, copy-paste ready code examples throughout. Every section includes concrete Python code with specific function calls, parameters, and expected outputs. The complete pipeline examples are particularly actionable. | 3 / 3 |
Workflow Clarity | The complete pipeline example in 'Common Workflows' shows a clear sequence with numbered steps, and the standardization workflow includes None-checking. However, there are no explicit validation checkpoints or feedback loops for error recovery in the multi-step pipelines - errors are only handled in a separate 'Error Handling' section rather than integrated into workflows. | 2 / 3 |
Progressive Disclosure | The skill does reference external files (references/core_api.md, references/io_module.md, etc.) which is good, but the main file itself contains an enormous amount of inline content that could be in those reference files. The SKILL.md should be a concise overview pointing to details, but instead it duplicates much of what the reference files likely contain. | 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 (705 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
b58ad7e
- 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.