medchem

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

Quality

71%

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 ./bundled/skills/medchem/SKILL.md

Quality

Content

72%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 is highly actionable with executable examples and well-structured progressive disclosure to real bundle files, but it is somewhat verbose and its batch-filtering workflows lack explicit validation checkpoints.

Suggestions

Add explicit validation/verification steps to the Workflow Patterns (e.g. inspect counts of filtered-out molecules, sanity-check a sample of flagged alerts before discarding) to lift workflow clarity past the batch cap of 3.

Consolidate the eight capability sections' repeated import boilerplate and parallelize the examples to reduce token overhead.

Trim the Overview paragraph, which restates content already conveyed by the description, to improve conciseness.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with runnable code blocks, but the eight near-identical capability sections and repeated 'import medchem as mc' boilerplate add padding that could be tightened, and the Overview re-states what the description already covers.	3 / 5
Actionability	Provides copy-paste-ready, executable code for every module plus concrete commands ('uv pip install medchem', the filter_molecules.py CLI invocation) covering the common cases comprehensively.	5 / 5
Workflow Clarity	The Workflow Patterns show rough sequences (triage, lead optimization) but lack validation checkpoints; per the batch-operation cap, a destructive/batch filtering skill with no verify-then-proceed feedback loop cannot score above 3.	3 / 5
Progressive Disclosure	SKILL.md is a concise overview with three real one-level-deep bundle files (references/api_guide.md, references/rules_catalog.md, scripts/filter_molecules.py), each clearly signaled and summarized in the Resources section; all referenced paths exist.	5 / 5
	Total	16 / 20 Passed

Description

71%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.

The description is specific and distinctive with strong concrete action verbs and named rule families, but it lacks an explicit 'Use when...' trigger clause, capping completeness at 3.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when filtering compound libraries for drug-likeness, prioritizing leads, or flagging PAINS/structural alerts.'

Include common user-facing synonyms or file extensions (SMILES, SDF, .sdf) to broaden trigger-term coverage.

Keep the named-rule list but ensure the trigger guidance names the typical workflows (triage, lead optimization) users will actually request.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Apply drug-likeness rules (Lipinski, Veber), PAINS filters, structural alerts, complexity metrics' — with named rule families, giving comprehensive coverage of capabilities.	5 / 5
Completeness	Has a clear 'what' (the filtering actions), but no explicit 'Use when...' trigger clause; the 'when' is only weakly implied by the trailing purpose phrase 'for compound prioritization and library filtering'.	3 / 5
Trigger Term Quality	Includes natural terms users say ('drug-likeness', 'PAINS filters', 'structural alerts', 'compound prioritization', 'library filtering') plus named rules, but misses common synonyms/extensions like 'SMILES' or '.sdf'.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear medicinal-chemistry niche with distinct triggers (Lipinski/Veber/PAINS/structural alerts) that would not plausibly fire for other skills, so conflict risk is minimal.	5 / 5
	Total	17 / 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/medchem/SKILL.md
Commit: d5ae560

Reviewed: 1 day 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.