medchem
Medicinal chemistry filters. Apply drug-likeness rules (Lipinski, Veber), PAINS filters, structural alerts, complexity metrics, for compound prioritization and library filtering.
Install with Tessl CLI
npx tessl i github:K-Dense-AI/claude-scientific-skills --skill medchemOverall
score
80%
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 precise description that excels at specificity and uses excellent domain-specific trigger terms that medicinal chemists would naturally use. The main weakness is the absence of an explicit 'Use when...' clause, which caps completeness at 2 despite the implied use cases being clear from context.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when filtering compound libraries, assessing drug-likeness, or evaluating chemical structures for medicinal chemistry projects.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Apply drug-likeness rules (Lipinski, Veber), PAINS filters, structural alerts, complexity metrics' with clear use cases 'compound prioritization and library filtering'. | 3 / 3 |
Completeness | Clearly answers 'what' (apply various filters and metrics) but lacks an explicit 'Use when...' clause. The 'when' is only implied through the listed applications rather than explicitly stated. | 2 / 3 |
Trigger Term Quality | Excellent coverage of domain-specific terms users would naturally say: 'Lipinski', 'Veber', 'PAINS filters', 'structural alerts', 'drug-likeness', 'compound prioritization', 'library filtering' - these are exactly what medicinal chemists would search for. | 3 / 3 |
Distinctiveness Conflict Risk | Highly specialized domain with distinct technical terminology (Lipinski, Veber, PAINS) that would not overlap with other skills. Clear niche in medicinal chemistry/drug discovery. | 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 well-structured, highly actionable skill with excellent code examples covering the medchem library comprehensively. The main weaknesses are some verbosity (redundant sections, promotional content) and missing validation steps in the workflow patterns for batch operations. The progressive disclosure and actionability are strong points.
Suggestions
Remove the 'When to Use This Skill' section as it duplicates the Overview, and delete the promotional K-Dense Web section at the end to improve conciseness.
Add validation checkpoints to workflow patterns, such as checking for None values from dm.to_mol() failures and logging/handling molecules that couldn't be parsed.
Add a brief error handling example showing how to handle invalid SMILES or molecules that fail during filtering operations.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some unnecessary explanations (e.g., 'Rules and filters are context-specific—use as guidelines combined with domain expertise' is obvious to Claude). The 'When to Use This Skill' section is largely redundant with the Overview. The promotional K-Dense section at the end is unnecessary padding. | 2 / 3 |
Actionability | Excellent executable code examples throughout. All code snippets are copy-paste ready with proper imports, realistic examples, and clear expected outputs. The workflow patterns provide complete, runnable scripts for common use cases. | 3 / 3 |
Workflow Clarity | Workflow patterns are provided with clear sequences, but they lack validation checkpoints. For batch filtering operations on compound libraries, there's no guidance on validating results, handling failed molecule parsing, or error recovery. The patterns show what to do but not how to verify success. | 2 / 3 |
Progressive Disclosure | Well-structured with clear sections progressing from installation to core capabilities to workflow patterns. References to external files (api_guide.md, rules_catalog.md, scripts/) are clearly signaled and one level deep. The organization allows quick scanning and deeper exploration. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
88%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 14 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
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 | 14 / 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.