datamol

Pythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery including SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing. Returns native rdkit.Chem.Mol objects. For advanced control or custom parameters, use rdkit directly.

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/datamol/SKILL.md

Quality

Content

78%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.

A well-structured, code-rich skill body that uses progressive disclosure effectively to keep the overview lean while delegating detail to real reference files. The main improvements are tightening redundant prose and converting placeholder examples into fully executable snippets.

Suggestions

Tighten the Overview to avoid re-stating the frontmatter description, and condense the citation boilerplate.

Replace placeholder calls like 'dm.operation(...)' with a concrete function example (e.g., dm.descriptors.batch_compute_many_descriptors) so guidance is copy-paste ready.

Dimension	Reasoning	Score
Conciseness	Largely efficient with code-forward sections, but minor over-explanation remains: the Overview re-states the description and the 'Citing Scientific Agent Skills' section is lengthy boilerplate that could be trimmed. Fits anchor 4 rather than 5 because of the redundant overview paragraph and verbose citation instructions.	4 / 5
Actionability	Mostly executable guidance with real code in Best Practices, Error Handling, and ML Integration, but placeholders like 'dm.operation(..., n_jobs=-1, progress=True)' and delegation to reference files leave minor gaps. Not a 5 because some examples are illustrative pseudocode rather than copy-paste-ready.	4 / 5
Workflow Clarity	Validation checkpoints are present for batch/parsing operations ('Check for None values after molecule parsing', safe_to_mol try/except feedback, troubleshooting section), though the main end-to-end workflows live in references rather than sequenced inline. Avoids the batch-operation cap of 3 because feedback loops are explicit; not a 5 because inline workflows are not fully sequenced.	4 / 5
Progressive Disclosure	SKILL.md is a clear overview with well-signaled one-level-deep references — a capabilities table linking to core_workflows.md/workflow_patterns.md plus a Reference Documentation section listing all 8 reference files, each verified to exist. Matches anchor 5: content appropriately split, references one level deep, easy navigation.	5 / 5
	Total	17 / 20 Passed

Description

80%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, capability-rich description that concretely enumerates datamol's actions and carves out a distinct niche against raw rdkit. Its main weakness is the absence of an explicit 'Use when...' trigger clause, leaving the 'when' mildly implicit.

Suggestions

Add an explicit 'Use when ...' clause naming user-facing triggers (e.g., 'Use when the user mentions SMILES, molecular descriptors, fingerprints, clustering, or standardizing molecules').

Include a couple of natural synonyms users say ('molecules', 'molecular structures') to round out trigger term coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing' — giving comprehensive coverage of capabilities rather than vague language.	5 / 5
Completeness	Clearly answers 'what' (Pythonic RDKit wrapper with listed capabilities) and provides a 'when' via 'Preferred for standard drug discovery including...', though the trigger could be more explicit and tied to user phrasings.	4 / 5
Trigger Term Quality	Strong natural domain keywords (SMILES parsing, descriptors, fingerprints, clustering, 3D conformers, drug discovery) that a cheminformatics user would say, but a few common synonyms (molecules, molecular) and equivalents are absent.	4 / 5
Distinctiveness Conflict Risk	Has a clear niche (datamol/RDKit wrapper for standard drug discovery) and explicitly draws the boundary with rdkit ('For advanced control or custom parameters, use rdkit directly'), leaving only minor overlap risk with a raw rdkit skill.	4 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/datamol/SKILL.md
Commit: 9cf7d9a

Reviewed: 5 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.