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

86%

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

72%

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

The content is highly actionable with well-organized, real reference files and clear navigation. Its main weaknesses are length/redundancy and implicit rather than explicit validation checkpoints in batch workflows.

Suggestions

Consolidate the repeated scaffold-grouping and descriptor-computation code so each pattern appears once, linking from the pipeline examples instead of duplicating them.

Add explicit validation gates to batch workflows (e.g., 'Verify all molecules parsed and standardized before computing descriptors') and a validate-fix-retry loop for batch reaction application.

Trim inline clarifications of well-known concepts (e.g., 'Tanimoto distance = 1 - Tanimoto similarity') or move them to the relevant reference file to reduce body length.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient executable code, but ~700 lines with notable redundancy — scaffold grouping and descriptor computation each reappear across 'Core Workflows' and 'Common Workflows and Patterns' — so it could be tightened rather than being fully lean.	2 / 3
Actionability	Provides fully executable, copy-paste-ready code with real function names and parameters throughout (e.g., dm.to_mol('CCO'), dm.conformers.generate(mol, n_confs=50, ...)), matching the 'fully executable' anchor.	3 / 3
Workflow Clarity	Multi-step pipelines are numbered and sequenced, but validation is implicit (e.g., df[df['mol'].notna()]) rather than explicit gate-style checkpoints, so batch/destructive workflows lack the validate-fix-retry feedback loops the rubric rewards.	2 / 3
Progressive Disclosure	References are clearly signaled inline ('Refer to references/io_module.md for...'), re-listed in a dedicated Reference Documentation section, one level deep, and all six referenced files actually exist in ./references/.	3 / 3
	Total	10 / 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.

The description is concise, specific, and uses appropriate third-person voice. It clearly states capabilities, an explicit usage trigger, and a boundary against using rdkit directly.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing' — matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Answers both what ('Pythonic wrapper around RDKit... Returns native rdkit.Chem.Mol objects') and when via the explicit trigger 'Preferred for standard drug discovery including...', so it is not capped at 2.	3 / 3
Trigger Term Quality	Includes natural cheminformatics terms a user would say — 'SMILES parsing', 'descriptors', 'fingerprints', 'clustering', '3D conformers', 'drug discovery' — giving good coverage of likely triggers.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear cheminformatics niche with distinct triggers and an explicit boundary ('For advanced control or custom parameters, use rdkit directly'), making wrong-skill conflict unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

75%

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 — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (710 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 2 missing	Warning

	Total	12 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/chemistry/datamol/SKILL.md
Commit: 52845c3

Reviewed: about 11 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.