adme-property-predictor

Predict ADME pharmacokinetic properties and drug-likeness of small molecules using validated cheminformatics models. Supports absorption, distribution, metabolism, excretion prediction, QED/MPO scoring, and batch library screening from SMILES input.

Quality

76%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./scientific-skills/Data analysis/adme-property-predictor/SKILL.md

Quality

Discovery

67%

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 technically detailed description that excels at specificity and distinctiveness within its specialized domain. However, it relies heavily on technical jargon that may not match natural user queries, and it lacks explicit trigger guidance ('Use when...') which limits its completeness score.

Suggestions

Add a 'Use when...' clause with explicit triggers, e.g., 'Use when analyzing drug candidates, screening compound libraries, or evaluating molecule properties'

Include more natural language variations alongside technical terms, such as 'drug properties', 'molecule analysis', 'compound screening', or 'pharmaceutical evaluation'

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: 'Predict ADME pharmacokinetic properties', 'drug-likeness', 'QED/MPO scoring', 'batch library screening', with clear input format 'SMILES input'.	3 / 3
Completeness	Clearly answers 'what' with detailed capabilities but lacks an explicit 'Use when...' clause or equivalent trigger guidance. The 'when' is only implied through the technical domain description.	2 / 3
Trigger Term Quality	Includes domain-specific terms like 'ADME', 'pharmacokinetic', 'SMILES', 'QED/MPO', 'drug-likeness' but these are technical jargon. Missing more natural variations users might say like 'drug properties', 'molecule screening', or 'compound analysis'.	2 / 3
Distinctiveness Conflict Risk	Highly specialized niche in cheminformatics/pharmacology with distinct technical terms (ADME, SMILES, QED/MPO) that are unlikely to conflict with other skills.	3 / 3
	Total	10 / 12 Passed

Implementation

85%

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 skill with strong actionability and clear workflows. The content provides executable code, specific CLI examples, and explicit validation/fallback paths. Minor verbosity in the capability descriptions and property tables could be trimmed, but overall the skill effectively guides Claude through ADME prediction tasks.

Suggestions

Consider moving the detailed property interpretation tables to a reference file to reduce the main skill's token footprint while preserving the quick-reference value.

Dimension	Reasoning	Score
Conciseness	The skill is reasonably efficient but includes some unnecessary content like the 'Key Capabilities' bullet list that duplicates information found in the detailed sections, and the extensive property tables could be more condensed or moved to reference files.	2 / 3
Actionability	Provides fully executable CLI commands and Python code examples with specific parameters, clear input/output formats, and copy-paste ready examples for single compound and batch processing workflows.	3 / 3
Workflow Clarity	Clear 5-step workflow with explicit validation checkpoints, well-defined fallback behavior for missing inputs, and specific error handling instructions that prevent proceeding without valid input.	3 / 3
Progressive Disclosure	Well-structured with quick check, workflow overview, detailed capabilities, and clear one-level-deep references to external documentation (lipinski_rules.md, qsar_models.md, etc.) for deeper details.	3 / 3
	Total	11 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: aipoch/medical-research-skills
Commit: ca9aaa4

Reviewed: 4 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.