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

Quality

Content

68%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 an action-dense, well-organized API tour with mostly executable examples and sensible progressive disclosure to real bundle files. Its main weakness is the absence of explicit validation checkpoints in the batch-filtering workflows, which caps workflow clarity.

Suggestions

Add explicit validation/verification steps to the workflow patterns (e.g. assert non-empty filtered set, check expected pass counts, log how many molecules were dropped and why) so batch operations include feedback loops.

Define or load `mol_list`/`candidate_mols` in the examples (or note they are placeholders) to make the code fully runnable end-to-end.

Convert the Resources entries to markdown links and consider moving the longer capability walkthroughs into the reference files to tighten the SKILL.md overview.

Dimension	Reasoning	Score
Conciseness	Largely efficient and code-forward with no padding about basic concepts, but repetitive `import medchem as mc` lines and some re-listed capability catalogs are minor trim opportunities that keep it just below 5.	4 / 5
Actionability	Concrete, copy-paste-ready code with real SMILES, class/method names, and parameters throughout; minor gaps such as undefined `mol_list`/`candidate_mols` placeholders and illustrative-only query strings keep it at 4 rather than 5.	4 / 5
Workflow Clarity	Three named workflow patterns give a reasonable batch-filtering sequence, but the workflows involve batch operations on compound libraries with no explicit validation/verification checkpoints or error-feedback loops; per the rubric's batch-operation cap, workflow_clarity cannot exceed 3.	3 / 5
Progressive Disclosure	Well-structured overview plus eight capability sections with concise inline examples, and a Resources section signaling real one-level-deep bundle files (api_guide.md, rules_catalog.md, filter_molecules.py); minor gaps are plain-path references and fairly long inline capability sections that could push more detail into the reference files.	4 / 5
	Total	15 / 20 Passed

Description

75%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, distinctive, and rich in natural domain trigger terms, but it lacks an explicit "Use when..." trigger clause, leaving the "when to use" guidance only weakly implied and capping completeness at 3.

Suggestions

Add an explicit "Use when..." clause, e.g. "Use when applying drug-likeness rules, PAINS or structural-alert filtering, or prioritizing compound libraries."

Include a few natural synonyms (e.g. "drug-like", "PAINS-free", "synthetic accessibility") to broaden trigger coverage toward a 5.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "drug-likeness rules (Lipinski, Veber)", "PAINS filters", "structural alerts", "complexity metrics", "compound prioritization", "library filtering" — giving comprehensive coverage, matching the anchor-5 example.	5 / 5
Completeness	Provides a clear "what" via concrete actions, but the only "when" signal ("for compound prioritization and library filtering") is weakly implied rather than an explicit "Use when..." clause, so per the guideline completeness is capped at 3.	3 / 5
Trigger Term Quality	Includes natural domain terms users would say (Lipinski, Veber, PAINS, structural alerts, drug-likeness) but lacks the synonym/extension breadth of a 5; a few natural variations are missing.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (medicinal chemistry filters) with distinct, specialized triggers (Lipinski, Veber, PAINS) and minimal overlap risk with other skills.	5 / 5
	Total	17 / 20 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: 5f2a37b

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.