medchem

Medicinal chemistry screening filters for compound prioritization; use when you need to apply drug-likeness rules, PAINS/structural alerts, and complexity metrics to triage or optimize libraries.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Evidence Insight/medchem/SKILL.md

Quality

Content

65%Weight 40%Scale 1-5

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

The body delivers an excellent runnable example, but it duplicates module coverage across two sections, omits validation for a batch workflow, and fails to link the existing reference/script bundle files. Tightening redundancy and adding both validation and bundle pointers would raise it substantially.

Suggestions

Add a validation/verification checkpoint in the example workflow (e.g., check that all SMILES parsed to valid molecules and that result columns are non-empty before exporting the CSV).

Reference the bundle files from the body — point Implementation Details to references/api_guide.md, the rule/alert lists to references/rules_catalog.md, and mention scripts/filter_molecules.py as a production-ready batch runner.

Merge or trim the overlap between Key Features and Implementation Details so each module is described once rather than twice.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of basic-concept padding, but the Key Features and Implementation Details sections cover the same modules (rules, structural, complexity, constraints, groups) with notable overlap that could be tightened into one section.	3 / 5
Actionability	The Example Usage block is a complete, copy-paste-ready, end-to-end pipeline (load SMILES, Ro5+Veber, alerts, complexity, decision, CSV export) covering the common screening case.	5 / 5
Workflow Clarity	The example has a clear numbered sequence, but this is a batch operation over compound libraries with no validation/verification step (e.g., confirming molecules parsed, checking result columns before export), which caps workflow clarity at 3 per the rubric.	3 / 5
Progressive Disclosure	The body has section structure, but the provided bundle files (references/api_guide.md, references/rules_catalog.md, scripts/filter_molecules.py) are never referenced or linked, while API detail and rule catalogs that belong in those files are inlined.	3 / 5
	Total	14 / 20 Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that concisely states both capability and explicit use-when triggers with domain-specific keywords. The only minor gap is that a few synonyms a user might naturally say live only in the body.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "apply drug-likeness rules, PAINS/structural alerts, and complexity metrics to triage or optimize libraries" — giving comprehensive coverage rather than a single generic verb.	5 / 5
Completeness	Explicitly answers both what ("Medicinal chemistry screening filters for compound prioritization") and when ("use when you need to apply drug-likeness rules, PAINS/structural alerts, and complexity metrics to triage or optimize libraries") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural domain keywords (drug-likeness rules, PAINS, structural alerts, complexity metrics, triage) are present, but a few common synonyms a user might say (medchem, toxicophores, drug-like) are only in the body, not the description.	4 / 5
Distinctiveness Conflict Risk	The medicinal-chemistry screening niche has distinct, domain-specific triggers that are unlikely to fire for unrelated skills, giving minimal conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Evidence Insight/medchem/SKILL.md
Commit: 63c61d3

Reviewed: 12 hours 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.