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

77%

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

72%

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 real reference files, but it is somewhat long and its batch/cloud workflows lack explicit validation feedback loops. Tightening inline version detail and adding checkpoints would raise the weaker dimensions.

Suggestions

Move time-sensitive version detail (e.g., '0.12.5, June 2024') into a clearly marked version/deprecated section to improve conciseness per the guidelines.

Add explicit validate→fix→retry checkpoints for destructive/batch operations (cloud writes, batch reactions) to lift workflow_clarity to 3.

Trim re-explanation of basics and consolidate overlapping examples to reduce the ~715-line length.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and code-forward, but at ~715 lines it re-explains some basics and inlines time-sensitive detail (e.g., 'PyPI stable: 0.12.5, June 2024'), so it could be tightened.	2 / 3
Actionability	Provides extensive fully executable, copy-paste-ready code with concrete functions, parameters, and expected outputs (e.g., dm.to_mol, dm.descriptors.compute_many_descriptors, dm.conformers.generate).	3 / 3
Workflow Clarity	Multi-step pipelines (loading→filtering→analysis, virtual screening) are clearly sequenced, but batch/destructive operations such as cloud writes and batch reactions lack explicit validation checkpoints and feedback loops.	2 / 3
Progressive Disclosure	Overview body is well structured with six clearly signaled one-level-deep references (all confirmed to exist as real files) plus a dedicated Reference Documentation section for easy navigation.	3 / 3
	Total	10 / 12 Passed

Description

82%

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, trigger-rich, and distinctive, but lacks an explicit 'Use when...' trigger clause so completeness is capped. It clearly communicates what the skill does and when it is preferred.

Suggestions

Add an explicit 'Use when...' trigger clause (e.g., 'Use when working with molecules, SMILES, fingerprints, or standard drug-discovery workflows') to lift completeness to 3.

Reinforce the natural trigger phrasing already present by listing a few user-facing synonyms (e.g., 'molecules, compounds, SMILES, drug-likeness') alongside the technical terms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing') plus a concrete return type ('Returns native rdkit.Chem.Mol objects'), matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Clearly answers 'what' but the 'when' is only implied via 'Preferred for standard drug discovery' with no explicit 'Use when...' trigger clause, which per the guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Includes natural cheminformatics terms users would actually say (SMILES parsing, descriptors, fingerprints, clustering, 3D conformers, drug discovery), giving good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (datamol/RDKit cheminformatics) and explicitly routes advanced cases to rdkit directly, making it unlikely to trigger for the wrong skill.	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
skill_md_line_count	SKILL.md is long (724 lines); consider splitting into references/ and linking	Warning
relative_links	Relative link issues: 2 missing	Warning

	Total	14 / 16 Passed

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/datamol/SKILL.md
Commit: 757b63b

Reviewed: about 12 hours 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.