rdkit
Cheminformatics toolkit for fine-grained molecular control. SMILES/SDF parsing, descriptors (MW, LogP, TPSA), fingerprints, substructure search, 2D/3D generation, similarity, reactions. For standard workflows with simpler interface, use datamol (wrapper around RDKit). Use rdkit for advanced control, custom sanitization, specialized algorithms.
Install with Tessl CLI
npx tessl i github:K-Dense-AI/claude-scientific-skills --skill rdkitOverall
score
79%
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 technical description with excellent specificity and domain-appropriate trigger terms that chemists would naturally use. The main weakness is the lack of an explicit 'Use when...' clause - while it does differentiate from datamol, it doesn't clearly state the conditions under which Claude should select this skill. Adding explicit trigger guidance would elevate this from good to excellent.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when user needs fine-grained molecular manipulation, custom sanitization, or mentions rdkit specifically'
Include trigger phrases for common user requests like 'calculate molecular weight', 'find similar molecules', or 'parse SMILES string'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'SMILES/SDF parsing, descriptors (MW, LogP, TPSA), fingerprints, substructure search, 2D/3D generation, similarity, reactions' - these are highly specific cheminformatics operations. | 3 / 3 |
Completeness | Clearly answers 'what' with detailed capabilities, but lacks an explicit 'Use when...' clause. The guidance about when to use rdkit vs datamol is helpful but doesn't provide explicit trigger conditions for when Claude should select this skill. | 2 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'SMILES', 'SDF', 'molecular', 'MW', 'LogP', 'TPSA', 'fingerprints', 'substructure search', 'similarity', 'reactions', 'rdkit', 'datamol' - these are exactly what chemists and computational scientists would use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche in cheminformatics with specific technical terms (SMILES, SDF, TPSA, fingerprints) that are unlikely to conflict with other skills. Also explicitly differentiates from datamol for disambiguation. | 3 / 3 |
Total | 11 / 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 RDKit skill with excellent code examples covering the full range of cheminformatics operations. The main weaknesses are moderate verbosity in introductory sections and missing explicit validation checkpoints in multi-step workflows. The progressive disclosure is well-executed with clear references to supporting documentation.
Suggestions
Add explicit validation steps to multi-step workflows (e.g., 'Verify conformer generation succeeded before optimization: if mol.GetNumConformers() == 0: handle error')
Trim the overview paragraph and section introductions - Claude doesn't need explanations of what RDKit is or what cheminformatics involves
Remove the promotional K-Dense Web section at the end - it's not relevant to the skill's technical content and adds unnecessary tokens
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but includes some unnecessary explanations (e.g., 'RDKit is a comprehensive cheminformatics library providing Python APIs for molecular analysis and manipulation'). The overview section and some introductory text could be trimmed, though most code examples are lean. | 2 / 3 |
Actionability | Excellent executable code examples throughout - all snippets are copy-paste ready with proper imports, realistic parameters, and complete function calls. The common workflows section provides fully functional implementations for drug-likeness analysis, similarity screening, and substructure filtering. | 3 / 3 |
Workflow Clarity | While individual operations are clear, multi-step workflows lack explicit validation checkpoints. For example, the conformer generation workflow doesn't include validation steps between embedding and optimization. The 'Common Pitfalls' section mentions issues but doesn't integrate validation into the workflows themselves. | 2 / 3 |
Progressive Disclosure | Well-structured with clear sections progressing from basic I/O to advanced features. References to external files (api_reference.md, descriptors_reference.md, smarts_patterns.md, scripts/) are clearly signaled and one level deep. Content is appropriately split between overview and detailed references. | 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 (769 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.