medchem

Medicinal chemistry filters. Apply drug-likeness rules (Lipinski, Veber), PAINS filters, structural alerts, complexity metrics, for compound prioritization and library filtering.

3.50x

Quality

58%

Does it follow best practices?

Impact

63%

3.50x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./scientific-skills/medchem/SKILL.md

Quality

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 with well-chosen technical trigger terms that users in medicinal chemistry would naturally use. Its main weakness is the absence of an explicit 'Use when...' clause, which caps the completeness score. Adding trigger guidance would make this an excellent description.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about drug-likeness filtering, ADME property checks, compound triage, or chemical library curation.'

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: applying drug-likeness rules (Lipinski, Veber), PAINS filters, structural alerts, complexity metrics, compound prioritization, and library filtering.	3 / 3
Completeness	The 'what' is well-covered with specific filters and actions, but there is no explicit 'Use when...' clause or equivalent trigger guidance telling Claude when to select this skill. The 'when' is only implied by the domain context.	2 / 3
Trigger Term Quality	Includes strong natural keywords a medicinal chemist would use: 'Lipinski', 'Veber', 'PAINS filters', 'structural alerts', 'drug-likeness', 'compound prioritization', 'library filtering', 'medicinal chemistry'. These are terms users in this domain would naturally mention.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive niche in medicinal chemistry filtering with specific named rules (Lipinski, Veber, PAINS). Very unlikely to conflict with other skills given the specialized domain terminology.	3 / 3
	Total	11 / 12 Passed

Implementation

35%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill is comprehensive but excessively verbose, trying to document the entire medchem library rather than providing a focused, efficient guide for Claude. The content would benefit significantly from moving detailed per-module API examples to reference files and keeping only the most common workflows inline. Some API examples appear speculative or inaccurate, which undermines the skill's reliability.

Suggestions

Reduce the main file to ~100 lines by moving detailed per-module API documentation (sections 4-8) into the referenced api_guide.md, keeping only the most common 2-3 patterns inline.

Remove the 'When to Use This Skill' and 'Overview' explanatory sections—Claude doesn't need to be told what medicinal chemistry filters are.

Add validation steps to workflow patterns: verify SMILES parsing succeeded (check for None molecules), log counts at each filtering stage, and validate output before writing files.

Verify all code examples against the actual medchem API—the Query Language, ComplexityFilter, and Constraints sections appear to describe APIs that may not exist in the library.

Dimension	Reasoning	Score
Conciseness	The skill is extremely verbose at ~300+ lines, explaining many concepts Claude already knows (what drug-likeness rules are, what structural alerts are, what complexity metrics are). The 'When to Use This Skill' section is unnecessary padding. Many sections include redundant explanations alongside code. The 'Best Practices' section contains generic advice like 'context matters' and 'document filtering decisions' that don't add actionable value.	1 / 3
Actionability	Code examples are provided throughout and appear mostly executable, but several are likely inaccurate or speculative about the actual API (e.g., the result format descriptions are vague like 'Results are returned as dictionaries with pass/fail status', the complexity module API and query language API look fabricated). The Medchem Query Language section in particular appears to describe functionality that may not exist in the library, reducing trustworthiness.	2 / 3
Workflow Clarity	The workflow patterns section provides reasonable multi-step sequences for compound triage and lead optimization, but lacks validation checkpoints. There's no guidance on verifying that molecules parsed correctly, no error handling for invalid SMILES, and no validation that filter results are sensible before saving outputs. For batch operations on compound libraries, this is a significant gap.	2 / 3
Progressive Disclosure	The skill references external files (references/api_guide.md, references/rules_catalog.md, scripts/filter_molecules.py) which is good progressive disclosure, but the main file itself is a monolithic wall covering 8 major capability areas in excessive detail. Much of the per-module API documentation (sections 4-8) should be in the referenced api_guide.md rather than inline.	2 / 3
	Total	7 / 12 Passed

Validation

90%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	10 / 11 Passed

Repository: K-Dense-AI/claude-scientific-skills
Commit: b58ad7e

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.