medchem

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

Quality

73%

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 ./backend/cli/skills/chemistry/medchem/SKILL.md

Quality

Content

65%Weight 40%Scale 1-3

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

Highly actionable with abundant executable examples, but the body is over-long and duplicative of its own references, and the batch workflows lack validation checkpoints; both conciseness and progressive disclosure sit at 2.

Suggestions

Trim the body to an overview plus a quick-start example and move the full per-module API walkthrough into references/api_guide.md, linking each capability section to it.

Remove the duplicated NIBR/common-alerts examples by keeping them in one place (either the module section or the functional API section).

Add a validation/verification checkpoint to the workflow patterns (e.g. inspect pass counts, confirm input parsing succeeded, log how many molecules were dropped and why) since these are batch operations.

Dimension	Reasoning	Score
Conciseness	The ~395-line body avoids explaining concepts Claude already knows (no padding about what SMILES or Lipinski are), but it carries redundancy — NIBR/common-alerts examples appear in both section 2 and the functional-API section 3, and the inline rule/group catalogs duplicate references/rules_catalog.md — so it is 'mostly efficient but could be tightened' (level 2) rather than lean (level 3).	2 / 3
Actionability	Sections are dominated by concrete, import-bearing, copy-paste-ready code (e.g. 'mc.rules.basic_rules.rule_of_five(smiles)') plus a real CLI invocation for the bundled script, matching the level-3 fully-executable anchor; it is above level 2 because examples are complete rather than pseudocode.	3 / 3
Workflow Clarity	Three workflow patterns give clear sequences, but these are batch library-filtering operations with no validation/verification checkpoints or error-feedback loops, which per the rubric caps workflow clarity at 2; it is above level 1 because steps are explicitly sequenced.	2 / 3
Progressive Disclosure	Bundle files exist and are clearly signaled one level deep in a Resources section, but the SKILL.md body itself is a near-monolithic full-API walkthrough (8 capability sections with code) that duplicates content belonging in references/api_guide.md — the level-2 'content that should be separate is inline' anchor — so it falls below level 3 despite good reference signaling.	2 / 3
	Total	9 / 12 Passed

Description

82%Weight 40%Scale 1-3

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 specific, well-keyed description that clearly conveys what the skill does and occupies a distinct niche, but it lacks an explicit 'Use when...' trigger clause, capping completeness at 2.

Suggestions

Add an explicit trigger clause, e.g. 'Use when filtering compound libraries by drug-likeness, applying PAINS/structural alerts, or prioritizing hits for lead optimization.'

Consider adding the natural term 'drug discovery' to broaden trigger coverage for users phrasing tasks at that level.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Apply drug-likeness rules (Lipinski, Veber), PAINS filters, structural alerts, complexity metrics, for compound prioritization and library filtering' — matching the level-3 anchor of several specific actions rather than the level-2 single-domain example.	3 / 3
Completeness	The 'what' is clearly stated but there is no 'Use when...' clause or equivalent explicit trigger guidance, so per the judging guideline completeness is capped at 2; it is above level 1 because the capability description is concrete.	2 / 3
Trigger Term Quality	Natural domain terms a medicinal chemist would say are well covered ('drug-likeness rules', 'Lipinski', 'PAINS filters', 'structural alerts', 'compound prioritization', 'library filtering'), matching the level-3 good-coverage anchor; it is above level 2 because it includes common phrasings rather than just one keyword.	3 / 3
Distinctiveness Conflict Risk	'Medicinal chemistry filters' with the named rules/alerts is a clear niche with distinct triggers unlikely to conflict with other skills, matching the level-3 clear-niche anchor rather than the overlapping level-2 example.	3 / 3
	Total	11 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/chemistry/medchem/SKILL.md
Commit: dc00e07

Reviewed: 11 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.