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

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 ./skills/datamol/SKILL.md

Quality

Content

80%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 and well-structured with excellent progressive disclosure via verified reference files. The main weakness is workflow clarity: batch and remote-write operations lack explicit validation/retry checkpoints, which caps that dimension at 3.

Suggestions

Add explicit validate-fix-retry feedback loops for batch operations (e.g. after read_sdf, check for None/invalid rows and retry standardize on failures) and for remote writes (verify credentials and file existence before write).

Trim the version/dependency commentary (lazy loading flag, RDKit-since-0.12.2 note) into a short 'Compatibility' note or move to a reference file to improve conciseness.

Add a short numbered end-to-end pipeline directly in SKILL.md (load -> standardize -> validate -> analyze) with an explicit validation step to lift workflow clarity.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete code and short bullets, but a few sections restate what Claude likely knows (lazy loading note, dependency details, version history) that could be trimmed.	4 / 5
Actionability	Fully executable copy-paste-ready examples throughout (to_mol, standardize_mol, read_sdf, fingerprints, descriptors with n_jobs), with concrete commands and import conventions covering common cases.	5 / 5
Workflow Clarity	Workflows are organized by capability with some validation (None checks, safe_to_mol), but batch/destructive operations like library processing and remote writes lack explicit validate-fix-retry checkpoints, capping this at 3.	3 / 5
Progressive Disclosure	Clear overview SKILL.md with a table mapping the ten workflow areas and three end-to-end pipelines, all pointing to real one-level-deep reference files with well-signaled navigation; content is appropriately split.	5 / 5
	Total	17 / 20 Passed

Description

66%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 conveys a clear niche, but it lacks an explicit 'Use when...' trigger clause, which limits its completeness and, to a lesser degree, its trigger-term quality. Adding a concrete trigger phrase would raise the two capped dimensions.

Suggestions

Append a 'Use when...' clause with concrete triggers, e.g. 'Use when working with molecules, SMILES, fingerprints, clustering, conformers, or standard drug-discovery cheminformatics.'

Add common synonyms users say naturally such as 'molecules', 'chemistry', or 'Tanimoto similarity' to broaden trigger coverage.

Clarify the boundary with raw RDKit (e.g. 'use rdkit directly for advanced/custom-parameter cases') as an explicit 'when not to use' hint.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions (SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing) with comprehensive coverage of datamol's domain, though it is a single dense sentence with minor gaps.	4 / 5
Completeness	A clear 'what' is present, but there is no 'Use when...' clause or equivalent explicit trigger guidance for when Claude should select this skill, which caps completeness at 3.	3 / 5
Trigger Term Quality	Strong natural terms (SMILES, descriptors, fingerprints, clustering, conformers, drug discovery) but a few common synonyms and the 'when to use' phrasing a user would naturally say are missing.	4 / 5
Distinctiveness Conflict Risk	The cheminformatics niche (datamol over RDKit for standard drug discovery) is fairly distinct with minimal conflict risk, though 'drug discovery' is broad enough to slightly overlap with related RDKit skills.	4 / 5
	Total	15 / 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: b2a92ba

Reviewed: 3 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.