rdkit

Cheminformatics toolkit for fine-grained molecular control. SMILES/SDF parsing, descriptors (MW, LogP, TPSA), fingerprints, substructure search, 2D/3D generation, similarity, reactions. For standard workflows with simpler interface, use datamol (wrapper around RDKit). Use rdkit for advanced control, custom sanitization, specialized algorithms.

Quality

82%

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

Quality

Content

65%

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

Highly actionable with comprehensive executable examples, but the body is an oversized inline reference that duplicates content promised in (missing) bundle files, and workflows lack explicit validation feedback loops for batch operations.

Suggestions

Move the per-capability API reference blocks into the referenced files (references/api_reference.md, descriptors_reference.md, smarts_patterns.md) and actually create those files so the inline body shrinks to an overview with signaled links.

Add explicit validate-fix-retry checkpoints to batch/destructive workflows (e.g. SDF writing, similarity screening) rather than only implicit None-checks.

Trim overview prose like 'RDKit is a comprehensive cheminformatics library...' that restates context Claude already knows.

Dimension	Reasoning	Score
Conciseness	Mostly concrete API code, but the ~750-line body is a large inline reference dump with overview prose ('RDKit is a comprehensive cheminformatics library...') and inline material that belongs in the referenced files, so it could be tightened considerably.	2 / 3
Actionability	Provides extensive executable, copy-paste-ready code with specific module paths and function calls (Chem.MolFromSmiles, AllChem.GetMorganFingerprintAsBitVect, etc.) plus complete workflow functions.	3 / 3
Workflow Clarity	Workflows are present as clear functions with None-checks, but batch/destructive operations (SDF writing, similarity screening) lack explicit validate-fix-retry feedback loops, which caps clarity per the rubric.	2 / 3
Progressive Disclosure	References are clearly signaled one level deep (api_reference.md, smarts_patterns.md, scripts/*.py), but those bundle files do not actually exist and the bulk of the API reference remains inline rather than split out.	2 / 3
	Total	9 / 12 Passed

Description

100%

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, specific description that names concrete capabilities, includes natural trigger terms, and gives explicit when-to-use guidance distinguishing it from the datamol alternative. It is concise without padding.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'SMILES/SDF parsing, descriptors (MW, LogP, TPSA), fingerprints, substructure search, 2D/3D generation, similarity, reactions' — matching the anchor for several specific concrete actions.	3 / 3
Completeness	Explicitly answers both what it does (the capability list) and when to use it ('Use rdkit for advanced control, custom sanitization, specialized algorithms'), with an explicit 'Use when'-style trigger clause.	3 / 3
Trigger Term Quality	Uses natural domain terms a cheminformatics user would actually say — 'SMILES', 'SDF', 'descriptors', 'fingerprints', 'substructure search', 'similarity', 'rdkit', 'datamol' — with good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	Carves a clear niche by contrasting rdkit against datamol ('For standard workflows with simpler interface, use datamol'), making conflict with a simpler-wrapper skill unlikely.	3 / 3
	Total	12 / 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
skill_md_line_count	SKILL.md is long (769 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning

	Total	14 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/pharma/rdkit/SKILL.md
Commit: df37802

Reviewed: 3 minutes 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.